HF中国镜像站's logo

Thireus
/
WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2

Text Generation
Transformers
llama
Model card Files Community
Thireus commited on
Commit
2be6fad
·
1 Parent(s): f8659d0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -49,9 +49,9 @@ ASSISTANT:
49
 
50
  ## Quantization process:
51
 
52
- | Original Model | → | (optional but recommended) Float16 Model* | → | Safetensor Model** | → | EXL2 Model |
53
  | -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
54
- | [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensor** | → | EXL2 |
55
 
56
  Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
57
 
 
49
 
50
  ## Quantization process:
51
 
52
+ | Original Model | → | (optional but recommended) Float16 Model* | → | Safetensors Model** | → | EXL2 Model |
53
  | -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
54
+ | [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
55
 
56
  Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
57