Upload LlamaForCausalLM

README.md

@@ -1,7 +1,7 @@
 ---
-license: cc-by-sa-4.0
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 language:
 - az
-base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 library_name: transformers
----
+license: cc-by-sa-4.0
+---

config.json

@@ -23,8 +23,8 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
     "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
@@ -33,8 +33,8 @@
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4278523727eea1a697368bdd862d09ea1c9578fa5bceddef2e99dfaa135ea1
-size 4977222696
+oid sha256:a6c5742790fc8b97ceeab68bf524d6b829e8090ebbb24d28e14cd09b95fc523e
+size 4996772687

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9a36ad418b0cd9b253f65771552d7dc05cf1abf1170b94de4b4d546aac255d
-size 1050673280
+oid sha256:ac1df3a0376a4bab63ddeaf73409c84f32b54f2eb3371f8a1a6988b486a72340
+size 4090014257