Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
+  "_name_or_path": "unsloth/llama-3.2-1b-instruct-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -11,16 +11,16 @@
     128008,
     128009
   ],
-  "head_dim": 128,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 3072,
+  "hidden_size": 2048,
   "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_attention_heads": 32,
+  "num_hidden_layers": 16,
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
@@ -47,8 +47,8 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float16",
-  "transformers_version": "4.46.2",
-  "unsloth_version": "2024.11.10",
+  "transformers_version": "4.46.3",
+  "unsloth_version": "2024.12.4",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -10,5 +10,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88aa4d5ee4030668d76ee2036f4195ef6627bdb21e11aeecb3abd0f99542e0fa
-size 2242762539
+oid sha256:45247244b0e96858342733d31ea2a441443222d804b6e3b34b9efb96b9330030
+size 1027676590