Hugging Face's logo

Intel
/
neural-chat-7b-v3-3-int4-inc

Text Generation
Transformers
Safetensors
English
mistral
LLMs
Intel
text-generation-inference
Inference Endpoints
4-bit precision
gptq
Model card Files Community
weiweiz1 commited on
Commit
75cd8eb
•
1 Parent(s): 08a4b22

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ python3 main.py \
31
  --bits 4 \
32
  --iters 1000 \
33
  --enable_minmax_tuning \
34
- --minmax_lr 0.0002 \
35
  --deployment_device 'gpu' \
36
  --scale_dtype 'fp32' \
37
  --disable_quanted_input \
 
31
  --bits 4 \
32
  --iters 1000 \
33
  --enable_minmax_tuning \
34
+ --minmax_lr 0.002 \
35
  --deployment_device 'gpu' \
36
  --scale_dtype 'fp32' \
37
  --disable_quanted_input \