Hugging Face's logo

webbigdata
/
C3TR-Adapter_gptq

Translation
Safetensors
Japanese
English
gptq
gemma
text-generation-inference
nlp
4-bit precision
Model card Files
xet
Community
dahara1 commited on
Commit
25c5517
·
verified ·
1 Parent(s): ca9fb88

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -40,7 +40,7 @@ config = AutoConfig.from_pretrained(model_name)
40
  config.quantization_config["use_exllama"] = False
41
  config.quantization_config["exllama_config"] = {"version":2}
42
 
43
- # adust your gpu memory size. 0 means first gpu.
44
  max_memory={0: "12GiB", "cpu": "10GiB"}
45
 
46
  quantized_model = AutoModelForCausalLM.from_pretrained(model_name
 
40
  config.quantization_config["use_exllama"] = False
41
  config.quantization_config["exllama_config"] = {"version":2}
42
 
43
+ # adjust your gpu memory size. 0 means first gpu.
44
  max_memory={0: "12GiB", "cpu": "10GiB"}
45
 
46
  quantized_model = AutoModelForCausalLM.from_pretrained(model_name