cmarkea
/

Meta-Llama-3.1-70B-Instruct-4bit

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

Cyrile commited on Aug 28, 2024

Commit

d56c04a

·

verified ·

1 Parent(s): 9557e31

Update config.json

Files changed (1) hide show

config.json +1 -3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -23,8 +23,6 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",

 {
+  "_name_or_path": "cmarkea/Meta-Llama-3.1-70B-Instruct-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",