Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM-135M-Instruct",
+  "_name_or_path": "HuggingFaceTB/SmolLM-135M",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "hidden_act": "silu",
   "hidden_size": 576,
   "initializer_range": 0.02,
@@ -17,14 +17,13 @@
   "num_attention_heads": 9,
   "num_hidden_layers": 30,
   "num_key_value_heads": 3,
-  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float16",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.43.3",
   "use_cache": true,
   "vocab_size": 49152
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 2,
-  "transformers_version": "4.42.4"
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.43.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f9cbfff45ca702a49ecc3c3231285073c928f39285b01ecc5ebe511a26d959
+oid sha256:589625e7fd982bcb58652b010540c976fd5a69fe389da4760347f9c15204a4f3
 size 269060280