Upload LlamaForCausalLM

config.json

@@ -1,12 +1,16 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-1B",
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128256,
-  "eos_token_id": 128257,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 2048,
@@ -18,7 +22,6 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 16,
   "num_key_value_heads": 8,
-  "pad_token_id": 128257,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
@@ -33,5 +36,5 @@
   "torch_dtype": "float16",
   "transformers_version": "4.46.3",
   "use_cache": true,
-  "vocab_size": 128258
+  "vocab_size": 128256
 }

generation_config.json

@@ -1,9 +1,11 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 128256,
+  "bos_token_id": 128000,
   "do_sample": true,
-  "eos_token_id": 128257,
-  "pad_token_id": 128257,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "temperature": 0.6,
   "top_p": 0.9,
   "transformers_version": "4.46.3"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98eed763487dfd5137ab4429d4f662374a12ef7bc741955b8cabcc631b162d61
-size 2471653656
+oid sha256:18f334a637395e9cc9046af7996a0bb891f2fc589e18d286891cc04bd950e373
+size 2471645464