Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -9,6 +9,8 @@ tags:
 - llama
 - trl
 - sft
+- 4bit
+- LoRA
 base_model: unsloth/llama-3-8b-bnb-4bit
 ---
 

config.json

@@ -12,30 +12,19 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "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": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.39.3",
-  "unsloth_version": "2024.4",
+  "transformers_version": "4.41.2",
+  "unsloth_version": "2024.6",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.41.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e054bf5471c1d164437c0da01ed7de959e1dbc0e0f73d391d602cdfaaccb18eb
-size 4652072882
+oid sha256:bae7df22d0b80b4bd43df58f7a6a4a5f7cf394aea2ba0fafe0662d01c639530d
+size 4652072866

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b53fa307a8988f692ffbfdb1fc2503ae0980a799e3fc9b75f1d5e23781fb37
+oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
 size 1050673280

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5702577762
+    "total_size": 5702577746
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",