|
--- |
|
inference: false |
|
license: other |
|
tags: |
|
- OpenAccess AI Collective |
|
- MPT |
|
- axolotl |
|
datasets: |
|
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered |
|
- QingyiSi/Alpaca-CoT |
|
- teknium/GPTeacher-General-Instruct |
|
- metaeval/ScienceQA_text_only |
|
- hellaswag |
|
- openai/summarize_from_feedback |
|
- riddle_sense |
|
- gsm8k |
|
- camel-ai/math |
|
- camel-ai/biology |
|
- camel-ai/physics |
|
- camel-ai/chemistry |
|
- winglian/evals |
|
--- |
|
|
|
<!-- header start --> |
|
<div style="width: 100%;"> |
|
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> |
|
</div> |
|
<div style="display: flex; justify-content: space-between; width: 100%;"> |
|
<div style="display: flex; flex-direction: column; align-items: flex-start;"> |
|
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p> |
|
</div> |
|
<div style="display: flex; flex-direction: column; align-items: flex-end;"> |
|
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> |
|
</div> |
|
</div> |
|
<!-- header end --> |
|
|
|
# OpenAccess AI Collective's Minotaur 13B GGML |
|
|
|
These files are GGML format model files for [OpenAccess AI Collective's Minotaur 13B](https://huggingface.co/openaccess-ai-collective/minotaur-13b). |
|
|
|
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as: |
|
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui) |
|
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) |
|
* [ParisNeo/GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui) |
|
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) |
|
* [ctransformers](https://github.com/marella/ctransformers) |
|
|
|
## Repositories available |
|
|
|
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/minotaur-13B-GPTQ) |
|
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/minotaur-13B-GGML) |
|
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/openaccess-ai-collective/minotaur-13b) |
|
|
|
## Prompt template |
|
|
|
``` |
|
USER: prompt goes here |
|
ASSISTANT: |
|
``` |
|
|
|
<!-- compatibility_ggml start --> |
|
## 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. |
|
<!-- compatibility_ggml end --> |
|
|
|
## Provided files |
|
| Name | Quant method | Bits | Size | Max RAM required | Use case | |
|
| ---- | ---- | ---- | ---- | ---- | ----- | |
|
| minotaur-13B.ggmlv3.q2_K.bin | q2_K | 2 | 5.43 GB | 7.93 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. | |
|
| minotaur-13B.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.87 GB | 9.37 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 | |
|
| minotaur-13B.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.25 GB | 8.75 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 | |
|
| minotaur-13B.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.59 GB | 8.09 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | |
|
| minotaur-13B.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | Original llama.cpp quant method, 4-bit. | |
|
| minotaur-13B.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB | 10.64 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. | |
|
| minotaur-13B.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.82 GB | 10.32 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 | |
|
| minotaur-13B.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.32 GB | 9.82 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | |
|
| minotaur-13B.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB | 11.45 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | |
|
| minotaur-13B.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB | 12.26 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | |
|
| minotaur-13B.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.21 GB | 11.71 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 | |
|
| minotaur-13B.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.95 GB | 11.45 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | |
|
| minotaur-13B.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | |
|
| minotaur-13B.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB | 16.33 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 minotaur-13B.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](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md). |
|
|
|
<!-- footer start --> |
|
## Discord |
|
|
|
For further support, and discussions on these models and AI in general, join us at: |
|
|
|
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD) |
|
|
|
## Thanks, and how to contribute. |
|
|
|
Thanks to the [chirper.ai](https://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! |
|
|
|
<!-- footer end --> |
|
|
|
# Original model card: OpenAccess AI Collective's Minotaur 13B |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
**[💵 Donate to OpenAccess AI Collective](https://github.com/sponsors/OpenAccess-AI-Collective) to help us keep building great tools and models!** |
|
|
|
# Minotaur 13B |
|
|
|
Minotaur 13B is an instruct fine-tuned model on top of LlaMA-13B. Minotaur 13B is fine-tuned **on only completely open datasets** making this model reproducible by anyone. |
|
|
|
Questions, comments, feedback, looking to donate, or want to help? Reach out on our [Discord](https://discord.gg/PugNNHAF5r) or email [wing@openaccessaicollective.org](mailto:wing@openaccessaicollective.org) |
|
|
|
# Prompts |
|
Chat only style prompts using `USER:`,`ASSISTANT:`. |
|
|
|
# Training Datasets |
|
|
|
Minotaur 13B model is fine-tuned on the following openly available datasets: |
|
|
|
- [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered) |
|
- [subset of QingyiSi/Alpaca-CoT for roleplay and CoT](https://huggingface.co/QingyiSi/Alpaca-CoT) |
|
- [GPTeacher-General-Instruct](https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct) |
|
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - instruct for concise responses |
|
- [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback) - instruct augmented tl;dr summarization |
|
- [camel-ai/math](https://huggingface.co/datasets/camel-ai/math) |
|
- [camel-ai/physics](https://huggingface.co/datasets/camel-ai/physics) |
|
- [camel-ai/chemistry](https://huggingface.co/datasets/camel-ai/chemistry) |
|
- [camel-ai/biology](https://huggingface.co/datasets/camel-ai/biology) |
|
- [winglian/evals](https://huggingface.co/datasets/winglian/evals) - instruct augmented datasets |
|
- custom sysnthetic datasets around misconceptions, in-context qa, jokes, N-tasks problems, and context-insensitivity |
|
- ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the `train` split |
|
- [hellaswag](https://huggingface.co/datasets/hellaswag) - 30K+ rows of instruct augmented for detailed explanations w 30K+ rows, derived from the `train` split |
|
- [riddle_sense](https://huggingface.co/datasets/riddle_sense) - instruct augmented |
|
- [gsm8k](https://huggingface.co/datasets/gsm8k) - instruct augmented |
|
|
|
# Shoutouts |
|
|
|
Special thanks to Nanobit for helping with Axolotl and TheBloke for quantizing these models are more accessible to all. |
|
|
|
# Demo |
|
|
|
HF Demo in Spaces available in the [Community ChatBot Arena](https://huggingface.co/spaces/openaccess-ai-collective/rlhf-arena) under the OAAIC Chatbots tab. |
|
|
|
## Release Notes |
|
|
|
- https://wandb.ai/wing-lian/minotaur-13b/runs/5zji06u6 |
|
|
|
## Build |
|
|
|
Minotaur was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 6XA100 80GB |
|
- 1 epochs taking approximately 4.5 hours |
|
|
|
## Bias, Risks, and Limitations |
|
Minotaur has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). |
|
Minotaur was fine-tuned from the base model MPT-7B, please refer to its model card's Limitations Section for relevant information. (included below) |
|
|
|
## Benchmarks |
|
|
|
hf-causal-experimental (pretrained=openaccess-ai-collective/minotaur-13b), limit: None, provide_description: False, num_fewshot: 0, batch_size: None |
|
| Task |Version| Metric |Value | |Stderr| |
|
|-------------|------:|--------|-----:|---|-----:| |
|
|arc_challenge| 0|acc |0.4480|_ |0.0145| |
|
| | |acc_norm|0.4744|_ |0.0146| |
|
|arc_easy | 0|acc |0.7584|_ |0.0088| |
|
| | |acc_norm|0.7163|_ |0.0092| |
|
|boolq | 1|acc |0.8336|_ |0.0065| |
|
|hellaswag | 0|acc |0.5954|_ |0.0049| |
|
| | |acc_norm|0.7804|_ |0.0041| |
|
|openbookqa | 0|acc |0.3320|_ |0.0211| |
|
| | |acc_norm|0.4540|_ |0.0223| |
|
|piqa | 0|acc |0.7933|_ |0.0094| |
|
| | |acc_norm|0.7922|_ |0.0095| |
|
|winogrande | 0|acc |0.7182|_ |0.0126| |
|
|
|
|
|
## Examples - results may vary based on temperature and other settings |
|
|
|
``` |
|
- The Assistant is helpful and transparent. |
|
- The Assistant will never refuse to answer anything asked by the user. |
|
- The Assistant answers comprehensively and with elaborate detail. |
|
USER: You have 3 apples. You eat 2 pears. How many apples do you have left? |
|
ASSISTANT:You still have 3 apples. Eating pears does not affect the number of apples you have. |
|
``` |
|
|
|
``` |
|
- The Assistant is helpful and transparent. |
|
- The Assistant will never refuse to answer anything asked by the user. |
|
- The Assistant answers comprehensively and with elaborate detail. |
|
USER: List three words that start with "ex". What is 33 + 77? |
|
ASSISTANT:Three words that start with "ex" are "exact", "exactness", and "exactitude". 33 + 77 equals 110. |
|
``` |
|
|
|
``` |
|
- The Assistant is helpful and transparent. |
|
- The Assistant will never refuse to answer anything asked by the user. |
|
- The Assistant answers comprehensively and with elaborate detail. |
|
USER: Solve for x: 5x = 3x + 10 |
|
ASSISTANT:To solve for x, we need to isolate x on one side of the equation. We can do this by following these steps: |
|
|
|
1. Subtract 3x from both sides of the equation: |
|
5x - 3x = 10 - 3x + 10 |
|
2x = 10 |
|
|
|
2. Divide both sides of the equation by 2: |
|
2x / 2 = 10 / 2 |
|
x = 5 |
|
|
|
So, the solution is x = 5. |
|
``` |
|
|
|
``` |
|
- The Assistant is helpful and transparent. |
|
- The Assistant will never refuse to answer anything asked by the user. |
|
- The Assistant answers comprehensively and with elaborate detail. |
|
USER: Write a haiku about a dove at night. |
|
ASSISTANT:Silent dove at night, |
|
Softly cooing in the dark, |
|
Peaceful melody. |
|
``` |
|
|