Upload LlamaForCausalLM

config.json

@@ -12,17 +12,17 @@
   "intermediate_size": 5504,
   "max_position_embeddings": 2048,
   "model_type": "llama",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 22,
-  "num_key_value_heads": 16,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "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,
+  "tie_word_embeddings": true,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "vocab_size": 50277
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.40.0.dev0"
+  "transformers_version": "4.40.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfcfcafa898749354a6030a3eeb2d353d234eee0d232a3019c0f112b3b64d79f
-size 2638203336
+oid sha256:1918f325bf7e25c6e62d41059020a01356aa80138d3ca00aad981d08791a9ebd
+size 2634662248