Views
No views yet
| Branch | Bits | Description |
|---|---|---|
| 8_0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| 6_5 | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, recommended. |
| 5_0 | 5.0 | Slightly lower quality vs 6.5, but usable |
| 4_25 | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. |
| 3_5 | 3.5 | Lower quality, only use if you have to. |
git clone --single-branch --branch 6_5 https://huggingface.co/qgallouedec_-_online-dpo-qwen2-4-exl2 online-dpo-qwen2-4-6_5pip3 install huggingface-hub--revision parameter. For example, to download the 6.5 bpw branch:
Linux:huggingface-cli download qgallouedec_-_online-dpo-qwen2-4-exl2 --revision 6_5 --local-dir online-dpo-qwen2-4-6_5 --local-dir-use-symlinks Falsehuggingface-cli download qgallouedec_-_online-dpo-qwen2-4-exl2 --revision 6_5 --local-dir online-dpo-qwen2-4-6.5 --local-dir-use-symlinks False1from transformers import pipeline
2
3question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
4generator = pipeline("text-generation", model="qgallouedec/online-dpo-qwen2-4", device="cuda")
5output = generator([{"role": "user", "content": question}], max_new_tokens=500)[0]
6print(output["generated_text"][1]["content"])