Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dhmeltzer/llama-7b-SFT_ds_eli5_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:dcd2d11682a34829a7911520e84deebe4633c85a0e959ac2d1cccafe4ebe1772
+oid sha256:eb259221b78b66655fa5a0ffc6d3acbdca42705ee8162193455d695c063ec1fb
 size 9976570520

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bae7281e8285035e2a804bedefb18463ebd95ebeb527b30de01978d6cd25cc8
+oid sha256:26eccaa18e4b987844b162325bd2d5a563a5e8a3cb410b0a0e56c483baf8a898
 size 3500294544