Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-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,
@@ -19,7 +19,7 @@
   "num_attention_heads": 9,
   "num_hidden_layers": 30,
   "num_key_value_heads": 3,
-  "pad_token_id": 49152,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_interleaved": false,
@@ -27,7 +27,13 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "vocab_size": 49153
+  "vocab_size": 49152
 }

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": 8192,
-  "pad_token_id": 49152,
+  "pad_token_id": 0,
   "transformers_version": "4.46.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b96a8dc3d71a10224f9d2c050bbfa38168d7d8169715a54d8040212cc5c104f6
-size 269061704
+oid sha256:5af571cbf074e6d21a03528d2330792e532ca608f24ac70a143f6b369968ab8c
+size 269060552