webbigdata
/

C3TR-Adapter_gptq

text-generation-inference

4-bit precision

Model card Files Files and versions Community

dahara1 commited on May 21

Commit

25c5517

•

1 Parent(s): ca9fb88

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -40,7 +40,7 @@ config = AutoConfig.from_pretrained(model_name)
 config.quantization_config["use_exllama"] = False
 config.quantization_config["exllama_config"] = {"version":2}
-# adust your gpu memory size. 0 means first gpu.
 max_memory={0: "12GiB", "cpu": "10GiB"}
 quantized_model = AutoModelForCausalLM.from_pretrained(model_name

 config.quantization_config["use_exllama"] = False
 config.quantization_config["exllama_config"] = {"version":2}
+# adjust your gpu memory size. 0 means first gpu.
 max_memory={0: "12GiB", "cpu": "10GiB"}
 quantized_model = AutoModelForCausalLM.from_pretrained(model_name