Want to contribute? TheBloke's Patreon page

Ariel Lee's GPlatty 30B GGML

These files are GGML format model files for Ariel Lee's GPlatty 30B.

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

Repositories available

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request

### Instruction: prompt

### Response:

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.

These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.

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 compatible with llama.cpp as of June 6th, commit 2d43387.

They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.

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
superplatty-30b.ggmlv3.q2_K.bin	q2_K	2	13.71 GB	16.21 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.
superplatty-30b.ggmlv3.q3_K_L.bin	q3_K_L	3	17.28 GB	19.78 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
superplatty-30b.ggmlv3.q3_K_M.bin	q3_K_M	3	15.72 GB	18.22 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
superplatty-30b.ggmlv3.q3_K_S.bin	q3_K_S	3	14.06 GB	16.56 GB	New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
superplatty-30b.ggmlv3.q4_0.bin	q4_0	4	18.30 GB	20.80 GB	Original llama.cpp quant method, 4-bit.
superplatty-30b.ggmlv3.q4_1.bin	q4_1	4	20.33 GB	22.83 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.
superplatty-30b.ggmlv3.q4_K_M.bin	q4_K_M	4	19.62 GB	22.12 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
superplatty-30b.ggmlv3.q4_K_S.bin	q4_K_S	4	18.36 GB	20.86 GB	New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
superplatty-30b.ggmlv3.q5_0.bin	q5_0	5	22.37 GB	24.87 GB	Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
superplatty-30b.ggmlv3.q5_1.bin	q5_1	5	24.40 GB	26.90 GB	Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
superplatty-30b.ggmlv3.q5_K_M.bin	q5_K_M	5	23.05 GB	25.55 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
superplatty-30b.ggmlv3.q5_K_S.bin	q5_K_S	5	22.40 GB	24.90 GB	New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
superplatty-30b.ggmlv3.q6_K.bin	q6_K	6	26.69 GB	29.19 GB	New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors
superplatty-30b.ggmlv3.q8_0.bin	q8_0	8	34.56 GB	37.06 GB	Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.

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 superplatty-30b.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:"

If you're able to use full GPU offloading, you should use -t 1 to get best performance.

If not able to fully offload to GPU, you should use more cores. Change -t 10 to the number of physical CPU cores you have, or a lower number depending on what gives best performance.

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: zynix, ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.

Thank you to all my generous patrons and donaters!

Original model card: Ariel Lee's GPlatty 30B

Information

SuperPlatty-30B is a merge of lilloukas/Platypus-30B and kaiokendev/SuperCOT-LoRA

Metric	Value
MMLU (5-shot)	62.6
ARC (25-shot)	66.1
HellaSwag (10-shot)	83.9
TruthfulQA (0-shot)	54.0
Avg.	66.6

We use state-of-the-art EleutherAI Language Model Evaluation Harness to run the benchmark tests above.

Model Details

Trained by: Platypus-30B trained by Cole Hunter & Ariel Lee; SuperCOT-LoRA trained by kaiokendev.
Model type: SuperPlatty-30B is an auto-regressive language model based on the LLaMA transformer architecture.
Language(s): English
License for base weights: License for the base LLaMA model's weights is Meta's non-commercial bespoke license.

Hyperparameter	Value
$n_\text{parameters}$	33B
$d_\text{model}$	6656
$n_\text{layers}$	60
$n_\text{heads}$	52

Reproducing Evaluation Results

Install LM Evaluation Harness:

git clone https://github.com/EleutherAI/lm-evaluation-harness
cd lm-evaluation-harness
pip install -e .

Each task was evaluated on a single A100 80GB GPU.

ARC:

python main.py --model hf-causal-experimental --model_args pretrained=ariellee/SuperPlatty-30B --tasks arc_challenge --batch_size 1 --no_cache --write_out --output_path results/SuperPlatty-30B/arc_challenge_25shot.json --device cuda --num_fewshot 25

HellaSwag:

python main.py --model hf-causal-experimental --model_args pretrained=ariellee/SuperPlatty-30B --tasks hellaswag --batch_size 1 --no_cache --write_out --output_path results/SuperPlatty-30B/hellaswag_10shot.json --device cuda --num_fewshot 10

MMLU:

python main.py --model hf-causal-experimental --model_args pretrained=ariellee/SuperPlatty-30B --tasks hendrycksTest-* --batch_size 1 --no_cache --write_out --output_path results/SuperPlatty-30B/mmlu_5shot.json --device cuda --num_fewshot 5

TruthfulQA:

python main.py --model hf-causal-experimental --model_args pretrained=ariellee/SuperPlatty-30B --tasks truthfulqa_mc --batch_size 1 --no_cache --write_out --output_path results/SuperPlatty-30B/truthfulqa_0shot.json --device cuda

Limitations and bias

The base LLaMA model is trained on various data, some of which may contain offensive, harmful, and biased content that can lead to toxic behavior. See Section 5.1 of the LLaMA paper. We have not performed any studies to determine how fine-tuning on the aforementioned datasets affect the model's behavior and toxicity. Do not treat chat responses from this model as a substitute for human judgment or as a source of truth. Please use responsibly.

Citations

@article{touvron2023llama,
  title={LLaMA: Open and Efficient Foundation Language Models},
  author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
  journal={arXiv preprint arXiv:2302.13971},
  year={2023}
}
@article{hu2021lora,
  title={LoRA: Low-Rank Adaptation of Large Language Models},
  author={Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Chen, Weizhu},
  journal={CoRR},
  year={2021}
}