metadata

inference: false
license: other

Want to contribute? TheBloke's Patreon page

Dromedary-65B-LoRA GGML

These files are GGML format model files for Dromedary-65B-LoRA.

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

Repositories available

Compatibility

Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`

I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit 2d5db48.

They should be compatible with all current UIs and libraries that use llama.cpp, such as those listed at the top of this README.

New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`

These new quantisation methods are only compatible with llama.cpp as of June 6th, commit 2d43387.

They will NOT be compatible with koboldcpp, text-generation-ui, and other UIs and libraries yet. Support is expected to come over the next few days.

Explanation of the new k-quant methods

The new methods available are:

GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name	Quant method	Bits	Size	Max RAM required	Use case
dromedary-lora-65B.ggmlv3.q2_K.bin	q2_K	2	27.33 GB	29.83 GB	New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors.
dromedary-lora-65B.ggmlv3.q3_K_L.bin	q3_K_L	3	34.55 GB	37.05 GB	New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
dromedary-lora-65B.ggmlv3.q3_K_M.bin	q3_K_M	3	31.40 GB	33.90 GB	New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
dromedary-lora-65B.ggmlv3.q3_K_S.bin	q3_K_S	3	28.06 GB	30.56 GB	New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
dromedary-lora-65B.ggmlv3.q4_0.bin	q4_0	4	36.73 GB	39.23 GB	Original llama.cpp quant method, 4-bit.
dromedary-lora-65B.ggmlv3.q4_1.bin	q4_1	4	40.81 GB	43.31 GB	Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
dromedary-lora-65B.ggmlv3.q4_K_M.bin	q4_K_M	4	39.28 GB	41.78 GB	New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K
dromedary-lora-65B.ggmlv3.q4_K_S.bin	q4_K_S	4	36.73 GB	39.23 GB	New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
dromedary-lora-65B.ggmlv3.q5_0.bin	q5_0	5	44.89 GB	47.39 GB	Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
dromedary-lora-65B.ggmlv3.q5_1.bin	q5_1	5	48.97 GB	51.47 GB	Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
dromedary-lora-65B.ggmlv3.q5_K_M.bin	q5_K_M	5	46.20 GB	48.70 GB	New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K
dromedary-lora-65B.ggmlv3.q5_K_S.bin	q5_K_S	5	44.89 GB	47.39 GB	New k-quant method. Uses GGML_TYPE_Q5_K for all tensors

Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

How to run in `llama.cpp`

I use the following command line; adjust for your tastes and needs:

./main -t 10 -ngl 32 -m dromedary-lora-65B.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"

Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

How to run in `text-generation-webui`

Further instructions here: text-generation-webui/docs/llama.cpp-models.md.

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

Special thanks to: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.

Patreon special mentions: Ajan Kanaga, Kalila, Derek Yates, Sean Connelly, Luke, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, trip7s trip, Jonathan Leane, Talal Aujan, Artur Olbinski, Cory Kujawski, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Johann-Peter Hartmann.

Thank you to all my generous patrons and donaters!

Original model card: Dromedary-65B-LoRA

Dromedary Model Card

NOTE: This "delta model" cannot be used directly.
Users have to apply it on top of the original LLaMA weights to get actual Dromedary weights.
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.