dangvansam
/

Vistral-7B-Chat-awq

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

dangvansam commited on Feb 22

Commit

c0d6eca

•

1 Parent(s): 14d57ba

Upload config

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -31,7 +31,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
   "transformers_version": "4.38.1",
   "use_cache": true,
   "vocab_size": 38369

 {
+  "_name_or_path": "/mnt/ssd/andrew/viet-llm/quantized_model/Vistral-7B-Chat-awq",
   "architectures": [
     "MistralForCausalLM"
   ],
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.38.1",
   "use_cache": true,
   "vocab_size": 38369