README.md

metadata

inference: false
license: other

Tim Dettmers' Guanaco 65B GPTQ

These files are GPTQ 4bit model files for Tim Dettmers' Guanaco 33B.

It is the result of quantising to 4bit using GPTQ-for-LLaMa.

Other repositories available

• 4-bit GPTQ models for GPU inference
• 4-bit, 5-bit and 8-bit GGML models for CPU(+GPU) inference
• Original unquantised fp16 model in HF format

How to easily download and use this model in text-generation-webui

Open the text-generation-webui UI as normal.

1. Click the Model tab.
2. Under Download custom model or LoRA, enter TheBloke/guanaco-65B-GPTQ.
3. Click Download.
4. Wait until it says it's finished downloading.
5. Click the Refresh icon next to Model in the top left.
6. In the Model drop-down: choose the model you just downloaded, guanaco-65B-GPTQ.
7. If you see an error in the bottom right, ignore it - it's temporary.
8. Fill out the GPTQ parameters on the right: Bits = 4, Groupsize = None, model_type = Llama
9. Click Save settings for this model in the top right.
10. Click Reload the Model in the top right.
11. Once it says it's loaded, click the Text Generation tab and enter a prompt!

Provided files

Compatible file - Guanaco-65B-GPTQ-4bit.act-order.safetensors

In the main branch you will find Guanaco-65B-GPTQ-4bit.act-order.safetensors

This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility.

It was created without groupsize to minimise VRAM requirements, to keep it under 24GB VRAM. It was created with the --act-order parameter to maximise accuracy.

• Guanaco-65B-GPTQ-4bit.act-order.safetensors
  • Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
  • Works with AutoGPTQ
  • Works with text-generation-webui one-click-installers
  • Parameters: Groupsize = None. act-order
  • Command used to create the GPTQ:

    python llama.py /workspace/process/TheBloke_guanaco-65B-GGML/HF  wikitext2 --wbits 4 --true-sequential --act-order --save_safetensors /workspace/process/TheBloke_guanaco-65B-GGML/gptq/Guanaco-65B-GPTQ-4bit-128g.no-act-order.safetensors
    

Original model card

Not provided by original model creator.