Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
+  "_name_or_path": "unsloth/llama-3-8b-Instruct-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": 128009,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -19,7 +19,7 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -34,9 +34,9 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.41.2",
-  "unsloth_version": "2024.6",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "unsloth_version": "2024.7",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,9 +1,9 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "max_length": 4096,
-  "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.41.2"
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "transformers_version": "4.42.4"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065aed31aba3348883ef6f96cf590c21fa22e810daefd5f15a381e28c6237f7a
-size 4652072860
+oid sha256:fcb97bdf82180811b56f447ced0a001d8d9f5b0804502182776ec7ae3efbdcbc
+size 4652072942

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
+oid sha256:674610adfedb7f19d21475a7280d6b34774894e654f1d50f4c24444ba7bd0d04
 size 1050673280

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5702577740
+    "total_size": 5702577758
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",