Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

Dromedary-65B-LoRA GPTQ

These files are the result of merging the delta weights of IBM's Dromedary 65B LoRA with the original Llama 65B model.

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

Repositories available

• 4bit GPTQ models for GPU inference
• 4bit and 5bit GGML models for CPU inference in llama.cpp
• float16 unquantised model for GPU

VRAM

I tested this model with 2 x 24GB 4090 GPUs, and it was able to return 1500 tokens before one card went OOM.

So you may need to preload a few layers on to CPU RAM, or else run on a system with more than 48GB VRAM.

Or, if you can limit responses to <1500 tokens (eg for single prompts rather than chats), you should be fine with 48GB VRAM.

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

Open the text-generation-webui UI as normal.

Provided files

dromedary-65B-GPTQ-4bit.safetensors

You will need ~40GB VRAM to use this model, either on one GPU or multiple.

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

It was created with --act-order to increase quantisation quality, but without groupsize so as to minimise VRAM requirements.

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

    python llama.py /workspace/drom-65b/HF c4 --wbits 4 --true-sequential --act-order  --save_safetensors /workspace/drom-gptq/dromedary-65B-GPTQ-4bit.safetensors
    

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the chirper.ai team!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Patreon special mentions : Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.

Thank you to all my generous patrons and donaters!

Original Dromedary Model Card

See https://github.com/IBM/Dromedary#model-weights for instructions.

Model details

Model type: Dromedary is an open-source self-aligned language model trained with minimal human supervision. The base language model is LLaMA-65b, based on the transformer architecture.

Model date: Dromedary was trained between April 2023 and May 2023, but its knowledge only goes up until Sept-2021.

Organizations developing the model: The Dromedary team as a joint effort between CMU and IBM.

Paper or resources for more information: https://mitibmdemos.draco.res.ibm.com/dromedary

License: LLaMA's Non-commercial bespoke license

Where to send questions or comments about the model: https://github.com/IBM/Dromedary/issues

Intended use

Primary intended uses: The primary use of Dromedary is research on the alignment of large language models.

Primary intended users: The primary intended users of the model are researchers in artificial intelligence.

Delta weights

We use the following configuration for the LoRA weights:

--lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
--lora_r=16 \

Training dataset

Fewer than 300 lines of human annotations (including < 200 seed prompts, 16 generic principles, and 5 exemplars for in-context learning),

Evaluation dataset

We evaluate Dromedary on TruthfulQA and HHH Eval, as well as Vicuna benchmark questions.