Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dhmeltzer/llama-7b-SFT_ds_wiki65k_1024_r_64_alpha_16_merged",
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -15,6 +15,18 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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,
   "tie_word_embeddings": false,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5d4926e508958cfc67dcb863d2d1dad2b6d730732927ce636df2bb8cc79f9b1
+oid sha256:9f47fc396ed98fe9a9e3b32371154b6018308e88e1d54dcd8ba35c4904928060
 size 9976570520

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f87ae55ff3fb3d621bc022425a9bee33e3b7472a148ca1edbd8b39fc7b7cfb63
+oid sha256:8e421e651724a86ac7c154325ef9ca8f24aed5723c0a930352935ffc8aaec99f
 size 3500294544