Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "clarkchan/llama3-8b-alpaca-gpt4-chinese",
+  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -17,24 +17,12 @@
   "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": "4.40.0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
   "unsloth_version": "2024.4",
   "use_cache": true,
   "vocab_size": 128256

generation_config.json

@@ -5,5 +5,5 @@
     128001,
     128009
   ],
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.40.1"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74960cd05dc7ba94c495ff96625727b46ac551be6f31edbcc9d0d788361430a
-size 4652072868
+oid sha256:3ff1ada3129795f84608c34e43128aaef0b63a1e7a126869a1b1326ada78e796
+size 4652072940

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
+oid sha256:7c5394fe848f6eafef2a44f085e7b72e5ef0d315f98aa87b3827c2b1e6983b89
 size 1050673280

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5702577748
+    "total_size": 5702577756
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",