Quant for 3.5

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -6,69 +6,31 @@ library_name: transformers
 tags:
 - code
 license: mit
-quantized_by: bartowski
-pipeline_tag: text-generation
 ---
+# This is a competitive coding model that should be better than qwen-coder-32b-instruct which we're running on github.gg
 
-## Exllama v2 Quantizations of tqwendo-36b
+## 36B experimental merge was to fix the repetition issues with the huihui-ai coder abliterated.
 
-Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.2.4">turboderp's ExLlamaV2 v0.2.4</a> for quantization.
+There is a draft model to go with this one for speculative decoding and chain of thought reasoning:
+https://huggingface.co/nisten/qwen2.5-coder-7b-abliterated-128k-AWQ
 
-<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
+Using the above 4bit 7b in conjuction with the 36b is meant to setup a chain-of-thought reasoner, evaluator similar to what O1-O3 is probably doing.
+This way the 7b 4bit only uses up an extra 4-6Gb on the gpu, but greatly both speeds up speculative decoding AND also chain-of-throught evals. 
 
-Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
+I.e. in this case the model was able to write an almost working heh.. chat interface for itself in one shot. And this was the WHOLE interface, including python and html and styling and api calls.
 
-Conversion was done using the default calibration dataset.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/ILYi7aFBN1bC-16un3XoJ.png)
 
-Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
-Original model: https://huggingface.co/nisten/tqwendo-36b
+## Merge Details
+### Merge Method
 
+This model was merged using the passthrough merge method.
 
-<a href="https://huggingface.co/bartowski/tqwendo-36b-exl2/tree/8_0">8.0 bits per weight</a>
+### Models Merged
 
-<a href="https://huggingface.co/bartowski/tqwendo-36b-exl2/tree/6_5">6.5 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/tqwendo-36b-exl2/tree/5_5">5.5 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/tqwendo-36b-exl2/tree/4_25">4.25 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/tqwendo-36b-exl2/tree/3_5">3.5 bits per weight</a>
-
-
-## Download instructions
-
-With git:
-
-```shell
-git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/tqwendo-36b-exl2
-```
-
-With huggingface hub (credit to TheBloke for instructions):
-
-```shell
-pip3 install huggingface-hub
-```
-
-To download the `main` (only useful if you only care about measurement.json) branch to a folder called `tqwendo-36b-exl2`:
-
-```shell
-mkdir tqwendo-36b-exl2
-huggingface-cli download bartowski/tqwendo-36b-exl2 --local-dir tqwendo-36b-exl2
-```
-
-To download from a different branch, add the `--revision` parameter:
-
-Linux:
-
-```shell
-mkdir tqwendo-36b-exl2-6_5
-huggingface-cli download bartowski/tqwendo-36b-exl2 --revision 6_5 --local-dir tqwendo-36b-exl2-6_5
-```
-
-Windows (which apparently doesn't like _ in folders sometimes?):
-
-```shell
-mkdir tqwendo-36b-exl2-6.5
-huggingface-cli download bartowski/tqwendo-36b-exl2 --revision 6_5 --local-dir tqwendo-36b-exl2-6.5
-```
+The following models were included in the merge:
+* Qwen/Qwen2.5-Coder-32B-Instruct
+* Qwen/Qwen2.5-Coder-32B
+* huihui-ai/Qwen2.5-32B-Instruct-abliterated

config.json

@@ -0,0 +1,44 @@
+{
+    "_name_or_path": "nisten/tqwendo-36b",
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 27648,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 70,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "factor": 3.0,
+        "original_max_position_embeddings": 98304,
+        "type": "yarn"
+    },
+    "rope_theta": 4000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.45.2",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.4",
+        "bits": 3.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 71379015680}, "weight_map": {"lm_head.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00006-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00006-of-00015.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00006-of-00015.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00007-of-00015.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00007-of-00015.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00007-of-00015.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00007-of-00015.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00007-of-00015.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00007-of-00015.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00007-of-00015.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00007-of-00015.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00008-of-00015.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00015.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00015.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00015.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00008-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00008-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00008-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00015.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00015.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00015.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00008-of-00015.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00015.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00015.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00015.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00015.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00015.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00015.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00009-of-00015.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00015.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00015.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00015.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00009-of-00015.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00009-of-00015.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00009-of-00015.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00015.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00015.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00015.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.49.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00010-of-00015.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00010-of-00015.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00010-of-00015.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00010-of-00015.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00010-of-00015.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00010-of-00015.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00010-of-00015.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00010-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00010-of-00015.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00010-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00010-of-00015.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00010-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00015.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00015.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00015.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00015.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00015.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00015.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00015.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00015.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00015.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.54.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00011-of-00015.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00011-of-00015.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00011-of-00015.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.55.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00012-of-00015.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00015.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00012-of-00015.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00015.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00012-of-00015.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00015.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.56.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00015.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00015.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00015.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00015.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00015.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00015.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.57.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00012-of-00015.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00015.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00012-of-00015.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00015.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00012-of-00015.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00015.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.63.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.58.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00013-of-00015.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00013-of-00015.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00013-of-00015.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.64.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.59.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00013-of-00015.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00015.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00013-of-00015.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00015.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00013-of-00015.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00015.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.65.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00013-of-00015.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00013-of-00015.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00013-of-00015.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.66.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00014-of-00015.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00014-of-00015.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00014-of-00015.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.67.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00014-of-00015.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00014-of-00015.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00014-of-00015.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.68.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00014-of-00015.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00014-of-00015.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00014-of-00015.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.69.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00014-of-00015.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00014-of-00015.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00014-of-00015.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00015-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00015-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00015-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00015-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.safetensors"}}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a06b170be2e084d8881271767362f8fb64d319457cd3d00257393acd988af5e
+size 8588528600

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2799f5f3eb4c04c3f2cba3130d70183a677fffd3e6a90c5a59b8f9c3536950d7
+size 8504367234

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}