Upload LlamaForCausalLM

config.json

@@ -1,22 +1,20 @@
 {
-  "_name_or_path": "GeneZC/MiniChat-3B",
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 3072,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 4096,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 24,
-  "num_key_value_heads": 24,
-  "pad_token_id": 0,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
   "pretraining_tp": 1,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float32",
@@ -35,7 +33,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.35.2",
   "use_cache": true,
-  "vocab_size": 49216
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.36.2"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014161a345febff9c6a315f0bc958eb6fd7edab0c401429e63058045cc2fe150
-size 3326065384
+oid sha256:b4a1b39e03c68fbe5c4482e4f6201740d6780c13ebeceda4081d7066b19b2438
+size 1232827368