Instructions to use openaccess-ai-collective/minotaur-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openaccess-ai-collective/minotaur-13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openaccess-ai-collective/minotaur-13b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/minotaur-13b") model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/minotaur-13b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use openaccess-ai-collective/minotaur-13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openaccess-ai-collective/minotaur-13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openaccess-ai-collective/minotaur-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openaccess-ai-collective/minotaur-13b
- SGLang
How to use openaccess-ai-collective/minotaur-13b with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "openaccess-ai-collective/minotaur-13b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openaccess-ai-collective/minotaur-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "openaccess-ai-collective/minotaur-13b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openaccess-ai-collective/minotaur-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openaccess-ai-collective/minotaur-13b with Docker Model Runner:
docker model run hf.co/openaccess-ai-collective/minotaur-13b
- DEPRECATION! This model has been superseded by Minotaur 13B Fixed
- =============================================================================================================================
- =============================================================================================================================
- =============================================================================================================================
- Minotaur 13B
- Prompts
- Training Datasets
- Shoutouts
- Demo
π΅ Donate to OpenAccess AI Collective to help us keep building great tools and models!
DEPRECATION! This model has been superseded by Minotaur 13B Fixed
https://huggingface.co/openaccess-ai-collective/minotaur-13b-fixed
Due to a bug, the initial release dropped a few datasets during training. We've corrected the issue and retrained the model
=============================================================================================================================
=============================================================================================================================
=============================================================================================================================
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 or email 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
- subset of QingyiSi/Alpaca-CoT for roleplay and CoT
- GPTeacher-General-Instruct
- metaeval/ScienceQA_text_only - instruct for concise responses
- openai/summarize_from_feedback - instruct augmented tl;dr summarization
- camel-ai/math
- camel-ai/physics
- camel-ai/chemistry
- camel-ai/biology
- 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
trainsplit - hellaswag - 30K+ rows of instruct augmented for detailed explanations w 30K+ rows, derived from the
trainsplit - riddle_sense - instruct augmented, derived from the
trainsplit - gsm8k - instruct augmented, derived from the
trainsplit - prose generation
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 under the OAAIC Chatbots tab.
Release Notes
Build
Minotaur was built with 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 LLaMA-13B, 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.
- Downloads last month
- 1,001