GGUF
conversational
wenhuach commited on
Commit
96c8a95
·
verified ·
1 Parent(s): 192f089

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -395,7 +395,7 @@ for n, m in model.named_modules():
395
  elif isinstance(m, torch.nn.Linear) and (not "expert" in n or "shared_experts" in n) and n != "lm_head":
396
  layer_config[n] = {"bits": 4}
397
 
398
- autoround = AutoRound(model, tokenizer, iters=0, layer_config=layer_config, batch_size=8, nsamples=512)
399
  autoround.quantize_and_save("/models/DeepSeek-R1-0528-q2ks", format="gguf:q2_k_s")
400
  ```
401
 
 
395
  elif isinstance(m, torch.nn.Linear) and (not "expert" in n or "shared_experts" in n) and n != "lm_head":
396
  layer_config[n] = {"bits": 4}
397
 
398
+ autoround = AutoRound(model, tokenizer, iters=0, layer_config=layer_config, batch_size=8, nsamples=512, low_gpu_mem_usage=True)
399
  autoround.quantize_and_save("/models/DeepSeek-R1-0528-q2ks", format="gguf:q2_k_s")
400
  ```
401