Instructions to use luffycodes/higgs-llama-vicuna-ep25-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luffycodes/higgs-llama-vicuna-ep25-70b with Transformers:

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

pipe = pipeline("text-generation", model="luffycodes/higgs-llama-vicuna-ep25-70b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("luffycodes/higgs-llama-vicuna-ep25-70b")
model = AutoModelForCausalLM.from_pretrained("luffycodes/higgs-llama-vicuna-ep25-70b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use luffycodes/higgs-llama-vicuna-ep25-70b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luffycodes/higgs-llama-vicuna-ep25-70b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luffycodes/higgs-llama-vicuna-ep25-70b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/luffycodes/higgs-llama-vicuna-ep25-70b

SGLang

How to use luffycodes/higgs-llama-vicuna-ep25-70b 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 "luffycodes/higgs-llama-vicuna-ep25-70b" \
    --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": "luffycodes/higgs-llama-vicuna-ep25-70b",
		"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 "luffycodes/higgs-llama-vicuna-ep25-70b" \
        --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": "luffycodes/higgs-llama-vicuna-ep25-70b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use luffycodes/higgs-llama-vicuna-ep25-70b with Docker Model Runner:
```
docker model run hf.co/luffycodes/higgs-llama-vicuna-ep25-70b
```

Higgs Model Card

Github details

Please checkout the repo: https://github.com/luffycodes/Tutorbot-Spock-Phys.

Model details

Model type: Higgs is an open-source educational tutoring chatbot trained by fine-tuning LLaMA-2-70B-chat model on synthetic student-tutorbot conversations generated using specialized prompts. Higgs performs a code soliloquy (an inner monologue) in which Higgs prompts itself through a series of prompts to decide if it's next response to the student would need any math calculations. If Higgs determines that the response might require such a calculation, such as in cases to verify student calculation, it outputs python code. Then, it uses the output of the python code to frame a mathematically accurate reply to the student.

Model date: Higgs was trained between May 2023 and Sept 2023.

Organizations developing the model: The Higgs (Spock) team with members from Rice University and OpenStax.

Where to send questions or comments about the model: Shashank Sonkar (ss164@rice.edu)

If you use this work, please cite: Code Soliloquies for Accurate Calculations in Large Language Models https://arxiv.org/abs/2309.12161

@misc{sonkar2023code,
      title={Code Soliloquies for Accurate Calculations in Large Language Models}, 
      author={Shashank Sonkar and MyCo Le and Xinghe Chen and Lucy Liu and Debshila Basu Mallick and Richard G. Baraniuk},
      year={2023},
      eprint={2309.12161},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 943

Paper for luffycodes/higgs-llama-vicuna-ep25-70b

Code Soliloquies for Accurate Calculations in Large Language Models

Paper • 2309.12161 • Published Sep 21, 2023