Upload LlamaForCausalLM

config.json

@@ -17,26 +17,12 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2758b08d5f76330557382d1dc3cf56aac64c9dc05935dbda9cf914b37bca8675
+oid sha256:931762b572b843dc20f63f005029717175fd4cf35d82385cc9f51f73a4d008d7
 size 4938985248

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb352199a2420bdee5b677993dc272ec379b6d4071cae490c962c2f9dc7d0ce
+oid sha256:cacf02c1f3230f2ce20abc06e1203acc546fc62185e20f941f0bd70944fd9fa1
 size 4947390768

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:071e60f61da9f0fa4896751ca67bc58e2950e4286b3621075aa05cad554c90f1
+oid sha256:78bd7ee5876f1e81e1903af8085d53ef65cfca69e30b0c92c177fcd0c2a1c5ed
 size 3590488736