模型:
TheBloke/minotaur-13B-GPTQ
任务:
文本生成类库:
Transformers数据集:
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 3Awinglian/evals 3Acamel-ai/chemistry 3Acamel-ai/physics 3Acamel-ai/biology 3Acamel-ai/math 3Agsm8k 3Ariddle_sense 3Aopenai/summarize_from_feedback 3Ahellaswag 3Ametaeval/ScienceQA_text_only 3Ateknium/GPTeacher-General-Instruct 3AQingyiSi/Alpaca-CoT 3Aehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered许可:
otherChat & support: my new Discord server
Want to contribute? TheBloke's Patreon page
These files are GPTQ 4bit model files for OpenAccess AI Collective's Minotaur 13B .
It is the result of quantising to 4bit using GPTQ-for-LLaMa .
USER: prompt goes here ASSISTANT:
Please make sure you're using the latest version of text-generation-webui
First make sure you have AutoGPTQ installed:
pip install auto-gptq
Then try the following example code:
from transformers import AutoTokenizer, pipeline, logging from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig import argparse model_name_or_path = "TheBloke/minotaur-13B-GPTQ" model_basename = "minotaur-13B-GPTQ-4bit-128g.no-act.order" use_triton = False tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) model = AutoGPTQForCausalLM.from_quantized(model_name_or_path, model_basename=model_basename, use_safetensors=True, trust_remote_code=True, device="cuda:0", use_triton=use_triton, quantize_config=None) print("\n\n*** Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline # Prevent printing spurious transformers error when using pipeline with AutoGPTQ logging.set_verbosity(logging.CRITICAL) prompt = "Tell me about AI" prompt_template=f'''### Human: {prompt} ### Assistant:''' print("*** Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, temperature=0.7, top_p=0.95, repetition_penalty=1.15 ) print(pipe(prompt_template)[0]['generated_text'])
minotaur-13B-GPTQ-4bit-128g.no-act.order.safetensors
This will work with AutoGPTQ and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
It was created with group_size 128 to increase inference accuracy, but without --act-order (desc_act) to increase compatibility and improve inference speed.
For further support, and discussions on these models and AI in general, join us at:
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.
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!
? Donate to OpenAccess AI Collective to help us keep building great tools and models!
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
Chat only style prompts using USER: , ASSISTANT: .
Minotaur 13B model is fine-tuned on the following openly available datasets:
Special thanks to Nanobit for helping with Axolotl and TheBloke for quantizing these models are more accessible to all.
HF Demo in Spaces available in the Community ChatBot Arena under the OAAIC Chatbots tab.
Minotaur was built with Axolotl on 6XA100 80GB
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)
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 |
- 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.