Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: unsloth/llama-3-8b-bnb-4bit
 language:
 - en
 license: apache-2.0
@@ -9,7 +10,6 @@ tags:
 - llama
 - trl
 - sft
-base_model: unsloth/llama-3-8b-bnb-4bit
 ---
 
 # Uploaded  model

config.json

@@ -12,6 +12,7 @@
   "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,
@@ -34,8 +35,8 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.2",
-  "unsloth_version": "2024.5",
+  "transformers_version": "4.42.3",
+  "unsloth_version": "2024.7",
   "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": "4.40.2"
+  "transformers_version": "4.42.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9e8b47e573f4f8a759e9995790a81f0c8bf6d9670e0e6e98c1c05c3f03dbd1
-size 4652072867
+oid sha256:4bdddce718ff91a777df4c092a1e9a044a2223802b457e09f6b0700f618502fb
+size 4652072871

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": 5702577747
+    "total_size": 5702577751
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",