Instructions to use openaccess-ai-collective/manticore-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openaccess-ai-collective/manticore-13b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="openaccess-ai-collective/manticore-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/manticore-13b")
model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/manticore-13b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openaccess-ai-collective/manticore-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/manticore-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/manticore-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openaccess-ai-collective/manticore-13b

SGLang

How to use openaccess-ai-collective/manticore-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/manticore-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/manticore-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/manticore-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/manticore-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openaccess-ai-collective/manticore-13b with Docker Model Runner:
```
docker model run hf.co/openaccess-ai-collective/manticore-13b
```

manticore-13b / README.md

winglian

upload the epoch threee model

5f96fb2 about 3 years ago

3.14 kB

datasets:
  - anon8231489123/ShareGPT_Vicuna_unfiltered
  - ehartford/wizard_vicuna_70k_unfiltered
  - ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
  - QingyiSi/Alpaca-CoT
  - teknium/GPT4-LLM-Cleaned
  - teknium/GPTeacher-General-Instruct
  - metaeval/ScienceQA_text_only
  - hellaswag
  - tasksource/mmlu
  - openai/summarize_from_feedback
language:
  - en
library_name: transformers
pipeline_tag: text-generation

Manticore 13B - Preview Release (previously Wizard Mega)

Manticore 13B is a Llama 13B model fine-tuned on the following datasets:

ShareGPT - based on a cleaned and de-suped subset
WizardLM
Wizard-Vicuna
subset of QingyiSi/Alpaca-CoT for roleplay and CoT
GPT4-LLM-Cleaned
GPTeacher-General-Instruct
ARC-Easy & ARC-Challenge - instruct augmented for detailed responses
mmlu: instruct augmented for detailed responses subset including
- abstract_algebra
- conceptual_physics
- formal_logic
- high_school_physics
- logical_fallacies
hellaswag - 5K row subset of instruct augmented for concise responses
metaeval/ScienceQA_text_only - instruct for concise responses
openai/summarize_from_feedback - instruct augmented tl;dr summarization

Demo

Try out the model in HF Spaces. The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality.

https://huggingface.co/spaces/openaccess-ai-collective/manticore-ggml

Release Notes

https://wandb.ai/wing-lian/manticore-13b/runs/nq3u3uoh/workspace

Build

Manticore was built with Axolotl on 8xA100 80GB

Preview Release: 1 epoch taking 8 hours.
The configuration to duplicate this build is provided in this repo's /config folder.

Bias, Risks, and Limitations

Manticore 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). Manticore was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.

Examples

### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.

### Assistant:

### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar...  

### Assistant: