Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/kaggle/input/llama-3/transformers/8b-hf/1",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -19,21 +19,6 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128257,
   "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": 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": 500000.0,

generation_config.json

@@ -1,7 +1,10 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128256,
+  "do_sample": true,
   "eos_token_id": 128257,
+  "max_length": 4096,
   "pad_token_id": 128257,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.41.0"
 }

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b105009f6cd276891d0da58573f932960a0ce3b155d9ac5f3d857017ec6ec8
+size 4976714976

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614751c97e105793b5b9d5cc5a15f23c2c4b00a8cc7b0656ef60b47893a842c8
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd469a74e79763a438c2597f6c53a9b5c80d011bd58e20b636d914677ce1533
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac146a09043bcb032f655a3cacb56793eec649fd64ff5e219aa906968e7f141b
+size 1168155192