Trained with Unsloth

README.md

@@ -1,3 +1,7 @@
 ---
 license: apache-2.0
+tags:
+- unsloth
+- trl
+- sft
 ---

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "unsloth_version": "2024.9.post3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "max_length": 131072,
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.1"
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cbd6d16e927a0c5bad54102514e6e18b4a47b3a6eb911e39d678d328d19f55
+oid sha256:4580fcaee24e6679d7a9fc14cfb0fd242c74a61f35e4a8e8944a5f4568dc0043
 size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b770216613ac5c34d7c54bdff1fa616bc4e338a9d0b20af6303e48c295ee23c
-size 1459729952
+oid sha256:4bc3ffecc936a127cb6263141bed4402c0d512e68c6c026029354c7762a20c95
+size 2247734992

model.safetensors.index.json

@@ -1,8 +1,9 @@
 {
   "metadata": {
-    "total_size": 6425499648
+    "total_size": 7213504512
   },
   "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",