Upload LlamaForCausalLM

config.json

@@ -1,10 +1,8 @@
 {
-  "_name_or_path": "/root/hf_model_3b",
+  "_name_or_path": "hf_model_3b",
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -16,13 +14,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 26,
   "num_key_value_heads": 32,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391946ccd81558e1a93ff15055d56e9cea1e73cd8615a2379a8157a757500868
+size 6853038093