Upload LlamaForCausalLM

config.json

@@ -1,29 +1,29 @@
 {
-  "_name_or_path": "./model-upload-test/",
+  "_name_or_path": "./TinyLlama-1.1B-Chat-v1.0/",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 14208,
-  "max_position_embeddings": 4096,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
   "use_cache": true,
-  "vocab_size": 100288
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6001da2106d4757498752a021df6c2bdc332c650aae4bae6b0c004dcf14933
+size 2200119864