Upload LlamaForCausalLM

config.json

@@ -5,6 +5,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
+  "dtype": "float16",
   "eos_token_id": 128001,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -21,7 +22,7 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
@@ -37,8 +38,7 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.55.4",
+  "transformers_version": "4.56.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -5,5 +5,5 @@
     128001,
     128009
   ],
-  "transformers_version": "4.55.4"
+  "transformers_version": "4.56.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca94decfa7960cff73818497507484e869a7c9bc260600a009390af7804e4044
-size 4652072867
+oid sha256:20f5cde927873dc4452cd3363636969c03a09b9445d087c3917084b15464c886
+size 4652072874

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
     "total_parameters": 8030261248,
-    "total_size": 5702577747
+    "total_size": 5702577754
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",