Upload LlamaForCausalLM

config.json

@@ -1,23 +1,25 @@
 {
-  "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.31.0",

generation_config.json

@@ -1,10 +1,7 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
-  "do_sample": true,
   "eos_token_id": 2,
-  "pad_token_id": 32000,
-  "temperature": 0.9,
-  "top_p": 0.6,
+  "max_length": 2048,
+  "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 sha256:2bdeb3e4a32ded0c7cfb9805708bc99ab89ad0cb1036b25ebe489a5a0ffd359a
+size 2200174918