Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -1,6 +1,9 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- unsloth
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meowterspace42/finetuned_llama_3.1_8b_gsm8k_synth405b",
+  "_name_or_path": "unsloth/Meta-Llama-3.1-8B-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -19,6 +19,18 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,
@@ -31,7 +43,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "unsloth_version": "2024.9",
+  "unsloth_version": "2024.8",
   "use_cache": true,
   "vocab_size": 128256
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1e346d0b6517771831785539dbef166d51d3f4aa1e598d830cb1e26a8cad91
+size 4652072908

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6feef628d893df7809d975f4c3a109a655e5e4126ac4ee28e8e0464504c86b12
+size 1050673280