Trained with Unsloth

config.json

@@ -1,24 +1,24 @@
 {
-  "_name_or_path": "unsloth/SmolLM2-135M",
+  "_name_or_path": "unsloth/SmolLM2-360M-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 576,
-  "initializer_range": 0.041666666666666664,
-  "intermediate_size": 1536,
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
   "is_llama_config": true,
   "max_position_embeddings": 16384,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
   "pad_token_id": 49152,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
@@ -30,9 +30,15 @@
   },
   "rope_theta": 100000,
   "tie_word_embeddings": true,
-  "torch_dtype": "float16",
-  "transformers_version": "4.46.2",
-  "unsloth_version": "2024.11.9",
+  "torch_dtype": "bfloat16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.46.3",
+  "unsloth_version": "2024.12.4",
   "use_cache": true,
   "vocab_size": 49153
 }

generation_config.json

@@ -1,8 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "max_length": 16384,
   "pad_token_id": 49152,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.46.3"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e2ba5d9d5177b3ab662d9d4a83b8af75ad0445ecd8d77ccc30e09bb2bd337b
+size 723676832