Hugging Face's logo

Safurai
/
Safurai-Csharp-34B-AWQ

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files Community
davide221 commited on
Commit
64dd6da
·
1 Parent(s): 8051784

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -109,10 +109,9 @@ from awq import AutoAWQForCausalLM
109
  from transformers import AutoTokenizer, TextStreamer
110
 
111
  quant_path = "Safurai/Safurai-Csharp-34B-AWQ"
112
- quant_file = "awq_model_w4_g128.pt"
113
 
114
  # Load model
115
- model = AutoAWQForCausalLM.from_quantized(quant_path, quant_file, fuse_layers=True)
116
  tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
117
  streamer = TextStreamer(tokenizer, skip_special_tokens=True)
118
 
 
109
  from transformers import AutoTokenizer, TextStreamer
110
 
111
  quant_path = "Safurai/Safurai-Csharp-34B-AWQ"
 
112
 
113
  # Load model
114
+ model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
115
  tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
116
  streamer = TextStreamer(tokenizer, skip_special_tokens=True)
117