Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dhmeltzer/llama-7b-SFT_eli5_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 sha256:347476758ada3bd787682aae97dbfa725e81b0ee19258ddc2bcbf2f17326e0ba
+oid sha256:340064c9e2d4115ec1d94c54b66b58986f05113fe1544f82507be7a4d57c6171
 size 9976570520

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:422532b24a7b4deb1a1863aa691ac2c38421a4593a6237ebb3d42815a2637535
+oid sha256:af4dd88bdd4b800dc3dccde63c3c99cdba58601ad10189909eb13241b086358a
 size 3500294544