OPEA
/

DeepSeek-V3-int4-sym-gguf-q4-0-inc

Inference Endpoints

Model card Files Files and versions Community

cicdatopea commited on 26 days ago

Commit

7b32e98

·

verified ·

1 Parent(s): a85f4d5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -135,7 +135,7 @@ for n, m in block.named_modules():
 from auto_round import AutoRound
-autoround = AutoRound(model=model, tokenizer=tokenizer, layer_config=layer_config, device_map=device_map,
                        iters=200,batch_size=8, seqlen=512)
 autoround.quantize()
 autoround.save_quantized(format="gguf:q4_0", output_dir="tmp_autoround"

 from auto_round import AutoRound
+autoround = AutoRound(model=model, tokenizer=tokenizer, device_map=device_map,
                        iters=200,batch_size=8, seqlen=512)
 autoround.quantize()
 autoround.save_quantized(format="gguf:q4_0", output_dir="tmp_autoround"