Upload LlamaForCausalLM

README.md

@@ -1,10 +1,10 @@
 ---
+language:
+- ko
+license: apache-2.0
 library_name: transformers
 tags:
 - text-generation-inference
-license: apache-2.0
-language:
-- ko
 metrics:
 - accuracy
 - f1

config.json

@@ -17,21 +17,6 @@
   "num_hidden_layers": 48,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_storage": "uint8",
-    "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,
   "rope_theta": 10000.0,

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48943f9e59243a0c7918b39269c522af46a68206a2b2e27d5b1f5dcc6fc96dcb
+size 4899121936

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9057e870670f6b53324439c1197febfa3d51ca6834558cfef507adcc29146848
+size 4915916080

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fb848a8a53b40b2e50398ea8078be96d2901c7b45015f6ba24a85d5429c181
+size 4999819232

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf912fa97a1a9ff861272194bccb2e55711921c930e53fc3ce264f9b2d0af7c0
+size 4915916080

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847a49afbf0a2ea4b5d2ef40dedd3639667fcda48440da9c00fc5c7d325d9bdd
+size 1879125696