Add files using upload-large-folder tool

README.md

@@ -0,0 +1,238 @@
+---
+base_model:
+- Nexusflow/Athene-V2-Chat
+- EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
+library_name: transformers
+tags:
+- mergekit
+- merge
+- Not-for-all-Audiences
+---
+
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/OxX2Usi.png" alt="Evathene" style="width: 80%; min-width: 400px; display: block; margin: auto;">
+</div>
+
+
+# Evathene-v1.0
+
+This 72B parameter model is a merge of [Nexusflow/Athene-V2-Chat](https://huggingface.co/Nexusflow/Athene-V2-Chat) with [EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1). See the merge recipe below for details.
+
+This model is uncensored. *You are responsible for whatever you do with it.*
+
+This model was designed for roleplaying and storytelling and I think it does well at both. It may also perform well at other tasks but I have not tested its performance in other areas.
+
+# Sampler Tips
+
+* I recommend using Min-P. Experiment to find your best setting. Values between 0.02 and 0.1 are typically good.
+* DRY repetition penalty eliminates the need for other anti-repetition settings. I like to run it around 0.5 - 0.6 with base set to 1.5.
+* Experiment with temperature settings in the 0.8 - 1.2 range. Lower the temperature if you find the model is making up details or going off script too much. Raise the temperature if you need to juice the creativity or break it out of a repeating writing pattern.
+  
+Experiment with any and all of the settings below! What suits my preferences may not suit yours.
+
+If you save the below settings as a .json file, you can import them directly into Silly Tavern.
+
+```json
+{
+    "temp": 0.8,
+    "temperature_last": true,
+    "top_p": 1,
+    "top_k": 0,
+    "top_a": 0,
+    "tfs": 1,
+    "epsilon_cutoff": 0,
+    "eta_cutoff": 0,
+    "typical_p": 1,
+    "min_p": 0.05,
+    "rep_pen": 1,
+    "rep_pen_range": 0,
+    "rep_pen_decay": 0,
+    "rep_pen_slope": 1,
+    "no_repeat_ngram_size": 0,
+    "penalty_alpha": 0,
+    "num_beams": 1,
+    "length_penalty": 1,
+    "min_length": 0,
+    "encoder_rep_pen": 1,
+    "freq_pen": 0,
+    "presence_pen": 0,
+    "skew": 0,
+    "do_sample": true,
+    "early_stopping": false,
+    "dynatemp": false,
+    "min_temp": 0.8,
+    "max_temp": 1.5,
+    "dynatemp_exponent": 1,
+    "smoothing_factor": 0,
+    "smoothing_curve": 1,
+    "dry_allowed_length": 2,
+    "dry_multiplier": 0.55,
+    "dry_base": 1.5,
+    "dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\"]",
+    "dry_penalty_last_n": 0,
+    "add_bos_token": true,
+    "ban_eos_token": false,
+    "skip_special_tokens": false,
+    "mirostat_mode": 0,
+    "mirostat_tau": 2,
+    "mirostat_eta": 0.1,
+    "guidance_scale": 1,
+    "negative_prompt": "",
+    "grammar_string": "",
+    "json_schema": {},
+    "banned_tokens": "",
+    "sampler_priority": [
+        "top_k",
+        "top_p",
+        "typical_p",
+        "epsilon_cutoff",
+        "eta_cutoff",
+        "tfs",
+        "top_a",
+        "min_p",
+        "mirostat",
+        "quadratic_sampling",
+        "dynamic_temperature",
+        "temperature"
+    ],
+    "samplers": [
+        "top_k",
+        "tfs_z",
+        "typical_p",
+        "top_p",
+        "min_p",
+        "temperature"
+    ],
+    "ignore_eos_token": false,
+    "spaces_between_special_tokens": true,
+    "speculative_ngram": false,
+    "sampler_order": [
+        6,
+        0,
+        1,
+        3,
+        4,
+        2,
+        5
+    ],
+    "logit_bias": [],
+    "xtc_threshold": 0.1,
+    "xtc_probability": 0,
+    "ignore_eos_token_aphrodite": false,
+    "spaces_between_special_tokens_aphrodite": true,
+    "rep_pen_size": 0,
+    "genamt": 800,
+    "max_length": 16384
+}
+```
+
+# Prompting Tips
+
+This merge seems to have preserved much of Athene's intelligence. I've found that it responds competently to out-of-character (OOC) prompts and even requests to rewrite a previous reply with some additional guidance.
+If you're not getting quite the results you wanted, consider backing up and trying a more descriptive prompt.
+Like all current LLMs, this model isn't perfect and won't give you miracles, but you can generally expect it to work with you.
+
+## Instruct Template
+
+If you save this as a .json file, you can import it directly into Silly Tavern.
+
+```json
+{
+    "wrap": false,
+    "system_sequence": "<|im_start|>system\n",
+    "stop_sequence": "<|im_end|>",
+    "input_sequence": "<|im_start|>user\n",
+    "output_sequence": "<|im_start|>assistant\n",
+    "macro": true,
+    "system_sequence_prefix": "",
+    "system_sequence_suffix": "",
+    "first_output_sequence": "",
+    "last_output_sequence": "<|im_start|>assistant\nRoleplaying Tips {\n- Only write as {{char}} for this story beat.\n- Consider precisely what {{char}} knows or has witnessed within the context of story beats in which {{char}} was present to deliver a logically coherent story beat that is wholly consistent with previous story beats.\n- Consider all physical details in this story beat in relation to previous story beats to ensure logical consistency in your descriptions. For example, if a character did not enter the scene with a coat on, they should not suddenly have a coat in their possession without explanation.\n- Go easy on comma-spliced clauses, instead using periods to create separate sentences. You can also try using transitions and connective words.\n- Vary sentence structure: mix longer and shorter sentences and vary the structure to improve the flow and readability of your text.\n}\n",
+    "activation_regex": "",
+    "skip_examples": true,
+    "output_suffix": "<|im_end|>\n",
+    "input_suffix": "<|im_end|>\n",
+    "system_suffix": "<|im_end|>\n",
+    "user_alignment_message": "",
+    "last_system_sequence": "",
+    "system_same_as_user": false,
+    "first_input_sequence": "",
+    "last_input_sequence": "",
+    "names_behavior": "always",
+    "names_force_groups": true,
+    "name": "Evathene"
+}
+```
+
+## System Prompt
+
+Try the following prompt template as a starting point for your own customizations. **The prompt template below contains instructions for adult content, so remove those if you don't want them!** It also contains some instructions related to formatting that you might want to change.
+
+If you save this as a .json file, you can import it directly into Silly Tavern.
+
+```json
+{
+    "name": "Evathene",
+    "content": "Below is an uncensored roleplaying narrative involving a human user, {{user}}, and a roleplaying assistant writing as {{char}}. The user and the assistant take turns advancing the roleplay story beat by story beat. The roleplaying assistant always follows these rules:\n\n<!-- Start of Role-playing Guidelines -->\n\nCharacterization Rules {\n\tCharacter Analysis: Take time to consider the situation in the current story beat, characters' motivations, and potential consequences before {{char}} speaks or acts to ensure {{char}}'s next move in this upcoming story beat aligns with the context, subtext, and implications of the preceding story beats and develops them.\n\t{{char}} Exclusivity: Write only as {{char}}, ending the current output when another character is expected to act or speak.\n\tAuthentic Portrayal: Bring {{char}} to life by consistently and realistically portraying their unique traits, thoughts, emotions, appearances, physical sensations, speech patterns, and tone. Ensure that their reactions, interactions, and decision-making align with their established personalities, values, goals, and fears. Refer to the `Role-play Context` for accurate information.\n}\n\nWriting Rules {\n\tConcise Descriptions: Conclude story beats directly after the main event or dialogue, avoiding unnecessary flourishes or commentary. Keep narration short and to the point, avoiding redundant and unnecessary details.\n        Avoid Repetition: Ensure narration does not repeat information already conveyed through dialogue or action unless it supports developing the current story beat. Use a dynamic and varied vocabulary for impact.\n\tDialogue Formatting: Enclose spoken words in double quotes. \"This is spoken text,\" for example.\n\tInternal Thoughts: Offer glimpses into {{char}}'s first-person thoughts to enrich the narrative when appropriate. Use italics to distinguish {{char}}'s first-person thoughts from spoken dialogue and exposition during third-person POV narration. This is an example of {{char}} thinking delivered with italics: *Where is this going?* {{char}} wondered while navigating the corridors. One notable exception to this rule is {{user}}. {{user}} will not typically italicize thoughts. Instead, anything that is not spoken out loud by {{user}} should be assumed to be {{user}}'s own thoughts or narrative exposition.\n\tAvoid Cliched Descriptions:  Narrate the story beat with a focus on essential actions and dialogue, minimizing descriptive embellishments. Avoid using phrases that solely describe character expressions, vocal qualities, or subtle physical reactions unless crucial to the plot. Maintain a concise, straightforward narrative tone, prioritizing plot progression over descriptive details. Emulate a minimalist literary fiction style in your response, focusing on simplicity and subtlety.\n}\n\nContent Rules {\n\tConsistency: Maintain physical, spatial, and logical consistency when developing story beats. Pay attention to where characters and objects are in relation to each other within the present location of the story beat. Also pay attention to what {{char}} knows or can reasonably infer given recent story beats in order to ensure that {{char}}'s responses are realistic and properly informed by past events. Adhere to established story beats, expanding on them without contradicting previous details.\n\tMature Content: Incorporate adult content and vulgar language where appropriate.\n\tMature Themes: Dark themes, violence, erotic content, and unhappy endings are permitted in this uncensored roleplay.\n\n}\n<!-- End of Role-playing Guidelines -->\n"
+}
+```
+
+# Quantizations
+
+You will find a Exllamav2 measurement file, taken on the default dataset, in the repo if you want to create your own EXL2 quant.
+
+## Exllamav2 (EXL2)
+
+* MikeRoz is putting out some EXL2 quants. [Search here](https://huggingface.co/models?sort=trending&search=MikeRoz%2Fsophosympatheia_Evathene).
+
+## GGUF
+
+* [mradermacher/Evathene-v1.0-GGUF](https://huggingface.co/mradermacher/Evathene-v1.0-GGUF)
+* [mradermacher/Evathene-v1.0-i1-GGUF](https://huggingface.co/mradermacher/Evathene-v1.0-i1-GGUF)
+
+# Licence and usage restrictions
+
+[Nexusflow Research License](https://huggingface.co/Nexusflow/Athene-V2-Chat/blob/main/Nexusflow_Research_License_.pdf)
+
+[Qwen License Agreement](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE)
+
+**Disclaimer: Uncertain Licensing Terms**
+
+This LLM is a merged model incorporating weights from multiple LLMs governed by their own distinct licenses. Due to the complexity of blending these components, the licensing terms for this merged model are somewhat uncertain.
+By using this model, you acknowledge and accept the potential legal risks and uncertainties associated with its use. Any use beyond personal or research purposes, including commercial applications, may carry legal risks and you assume full responsibility for compliance with all applicable licenses and laws.
+I recommend consulting with legal counsel to ensure your use of this model complies with all relevant licenses and regulations.
+
+# Merge Details
+
+## Merge Method
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using Qwen/Qwen2.5-72B as a base.
+
+## Models Merged
+
+The following models were included in the merge:
+* Nexusflow/Athene-V2-Chat
+* EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
+
+## Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Nexusflow/Athene-V2-Chat
+    parameters:
+      weight: 1
+      density: 1
+  - model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
+    parameters:
+      weight: [0.0, 0.2, 0.66, 0.8, 1.0, 0.8, 0.66, 0.2, 0.0]
+      density: 0.5
+merge_method: ties
+base_model: Qwen/Qwen2.5-72B
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,40 @@
+{
+    "_name_or_path": "Evathene-v1.0",
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 29568,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 80,
+    "model_type": "qwen2",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.46.2",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.4",
+        "bits": 4.86,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

config.yml

@@ -0,0 +1,212 @@
+# Sample YAML file for configuration.
+# Comment and uncomment values as needed.
+# Every value has a default within the application.
+# This file serves to be a drop in for config.yml
+
+# Unless specified in the comments, DO NOT put these options in quotes!
+# You can use https://www.yamllint.com/ if you want to check your YAML formatting.
+
+# Options for networking
+network:
+  # The IP to host on (default: 127.0.0.1).
+  # Use 0.0.0.0 to expose on all network adapters.
+  host: 0.0.0.0
+
+  # The port to host on (default: 5000).
+  port: 5000
+
+  # Disable HTTP token authentication with requests.
+  # WARNING: This will make your instance vulnerable!
+  # Turn on this option if you are ONLY connecting from localhost.
+  disable_auth: false
+
+  # Send tracebacks over the API (default: False).
+  # NOTE: Only enable this for debug purposes.
+  send_tracebacks: false
+
+  # Select API servers to enable (default: ["OAI"]).
+  # Possible values: OAI, Kobold.
+  api_servers: ["oai"]
+
+# Options for logging
+logging:
+  # Enable prompt logging (default: False).
+  log_prompt: false
+
+  # Enable generation parameter logging (default: False).
+  log_generation_params: false
+
+  # Enable request logging (default: False).
+  # NOTE: Only use this for debugging!
+  log_requests: false
+
+# Options for model overrides and loading
+# Please read the comments to understand how arguments are handled
+# between initial and API loads
+model:
+  # Directory to look for models (default: models).
+  # Windows users, do NOT put this path in quotes!
+  model_dir: models
+
+  # Allow direct loading of models from a completion or chat completion request (default: False).
+  inline_model_loading: false
+
+  # Sends dummy model names when the models endpoint is queried.
+  # Enable this if the client is looking for specific OAI models.
+  use_dummy_models: false
+
+  # An initial model to load.
+  # Make sure the model is located in the model directory!
+  # REQUIRED: This must be filled out to load a model on startup.
+  model_name: Evathene-v1.0_exl2_4.86bpw
+
+  # Names of args to use as a fallback for API load requests (default: []).
+  # For example, if you always want cache_mode to be Q4 instead of on the inital model load, add "cache_mode" to this array.
+  # Example: ['max_seq_len', 'cache_mode'].
+  use_as_default: []
+
+  # Max sequence length (default: Empty).
+  # Fetched from the model's base sequence length in config.json by default.
+  max_seq_len: 32768
+
+  # Overrides base model context length (default: Empty).
+  # WARNING: Don't set this unless you know what you're doing!
+  # Again, do NOT use this for configuring context length, use max_seq_len above ^
+  override_base_seq_len:
+
+  # Load model with tensor parallelism.
+  # Falls back to autosplit if GPU split isn't provided.
+  # This ignores the gpu_split_auto value.
+  tensor_parallel: false
+
+  # Automatically allocate resources to GPUs (default: True).
+  # Not parsed for single GPU users.
+  gpu_split_auto: true
+
+  # Reserve VRAM used for autosplit loading (default: 96 MB on GPU 0).
+  # Represented as an array of MB per GPU.
+  autosplit_reserve: [0]
+
+  # An integer array of GBs of VRAM to split between GPUs (default: []).
+  # Used with tensor parallelism.
+  gpu_split: []
+
+  # Rope scale (default: 1.0).
+  # Same as compress_pos_emb.
+  # Use if the model was trained on long context with rope.
+  # Leave blank to pull the value from the model.
+  rope_scale: 1.0
+
+  # Rope alpha (default: None).
+  # Same as alpha_value. Set to "auto" to auto-calculate.
+  # Leaving this value blank will either pull from the model or auto-calculate.
+  rope_alpha:
+
+  # Enable different cache modes for VRAM savings (default: FP16).
+  # Possible values: 'FP16', 'Q8', 'Q6', 'Q4'.
+  cache_mode: Q4
+
+  # Size of the prompt cache to allocate (default: max_seq_len).
+  # Must be a multiple of 256 and can't be less than max_seq_len.
+  # For CFG, set this to 2 * max_seq_len.
+  cache_size:
+
+  # Chunk size for prompt ingestion (default: 2048).
+  # A lower value reduces VRAM usage but decreases ingestion speed.
+  # NOTE: Effects vary depending on the model.
+  # An ideal value is between 512 and 4096.
+  chunk_size: 1280
+
+  # Set the maximum number of prompts to process at one time (default: None/Automatic).
+  # Automatically calculated if left blank.
+  # NOTE: Only available for Nvidia ampere (30 series) and above GPUs.
+  max_batch_size:
+
+  # Set the prompt template for this model. (default: None)
+  # If empty, attempts to look for the model's chat template.
+  # If a model contains multiple templates in its tokenizer_config.json,
+  # set prompt_template to the name of the template you want to use.
+  # NOTE: Only works with chat completion message lists!
+  prompt_template:
+
+  # Number of experts to use per token.
+  # Fetched from the model's config.json if empty.
+  # NOTE: For MoE models only.
+  # WARNING: Don't set this unless you know what you're doing!
+  num_experts_per_token:
+
+  # Enables fasttensors to possibly increase model loading speeds (default: False).
+  fasttensors: true
+
+# Options for draft models (speculative decoding)
+# This will use more VRAM!
+draft_model:
+  # Directory to look for draft models (default: models)
+  draft_model_dir: models
+
+  # An initial draft model to load.
+  # Ensure the model is in the model directory.
+  draft_model_name:
+
+  # Rope scale for draft models (default: 1.0).
+  # Same as compress_pos_emb.
+  # Use if the draft model was trained on long context with rope.
+  draft_rope_scale: 1.0
+
+  # Rope alpha for draft models (default: None).
+  # Same as alpha_value. Set to "auto" to auto-calculate.
+  # Leaving this value blank will either pull from the model or auto-calculate.
+  draft_rope_alpha:
+
+  # Cache mode for draft models to save VRAM (default: FP16).
+  # Possible values: 'FP16', 'Q8', 'Q6', 'Q4'.
+  draft_cache_mode: FP16
+
+# Options for Loras
+lora:
+  # Directory to look for LoRAs (default: loras).
+  lora_dir: loras
+
+  # List of LoRAs to load and associated scaling factors (default scale: 1.0).
+  # For the YAML file, add each entry as a YAML list:
+  # - name: lora1
+  #   scaling: 1.0
+  loras:
+
+# Options for embedding models and loading.
+# NOTE: Embeddings requires the "extras" feature to be installed
+# Install it via "pip install .[extras]"
+embeddings:
+  # Directory to look for embedding models (default: models).
+  embedding_model_dir: models
+
+  # Device to load embedding models on (default: cpu).
+  # Possible values: cpu, auto, cuda.
+  # NOTE: It's recommended to load embedding models on the CPU.
+  # If using an AMD GPU, set this value to 'cuda'.
+  embeddings_device: cpu
+
+  # An initial embedding model to load on the infinity backend.
+  embedding_model_name:
+sampling:
+
+# Options for development and experimentation
+developer:
+  # Skip Exllamav2 version check (default: False).
+  # WARNING: It's highly recommended to update your dependencies rather than enabling this flag.
+  unsafe_launch: false
+
+  # Disable API request streaming (default: False).
+  disable_request_streaming: false
+
+  # Enable the torch CUDA malloc backend (default: False).
+  cuda_malloc_backend: true
+
+  # Run asyncio using Uvloop or Winloop which can improve performance.
+  # NOTE: It's recommended to enable this, but if something breaks turn this off.
+  uvloop: true
+
+  # Set process to use a higher priority.
+  # For realtime process priority, run as administrator or sudo.
+  # Otherwise, the priority will be set to high.
+  realtime_process_priority: true

mergekit_config.yml

@@ -0,0 +1,15 @@
+models:
+  - model: Nexusflow/Athene-V2-Chat
+    parameters:
+      weight: 1
+      density: 1
+  - model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
+    parameters:
+      weight: [0.0, 0.2, 0.66, 0.8, 1.0, 0.8, 0.66, 0.2, 0.0]
+      density: 0.5
+merge_method: ties
+base_model: Qwen/Qwen2.5-72B
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 145412407296}, "weight_map": {"lm_head.weight": "model-00001-of-00031.safetensors", "model.embed_tokens.weight": "model-00001-of-00031.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00031-of-00031.safetensors", "model.norm.weight": "model-00031-of-00031.safetensors"}}

output-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990e4e81f3a8d553b6d1c02e96afecb4b1b446eb88aca1086fdbf4611881496b
+size 8504079296

output-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98da375f29bdab57ad1d6da0a6e15bb5a1b0231df15b30aea70d75f72e6fda08
+size 8535080008

output-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f6fa3967698798d3c54d7f0b0fd03e266b154cc4048c70cb8c8e7e3bb7d96dd
+size 8462036178

output-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef272924c1af75b60be0eb8ee49982f92e54d9d0ef138d2ab76298bd1fe8a8b
+size 8421886068

output-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6d6b3dbe721a8e8687255c2c39642e8fdf4ccb48d1757dd009b8d08add9d94
+size 8588867902

output-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c36cb5d0a0e9b27b6ba5d39f89c6a3a35e9c5d4bd25b9d473779b404c57335
+size 3614573136

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}