Instructions to use RichardErkhov/NingLab_-_eCeLLM-M-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use RichardErkhov/NingLab_-_eCeLLM-M-gguf with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M
Use Docker
docker model run hf.co/RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use RichardErkhov/NingLab_-_eCeLLM-M-gguf with Ollama:
ollama run hf.co/RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use RichardErkhov/NingLab_-_eCeLLM-M-gguf with Docker Model Runner:
docker model run hf.co/RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M
- Lemonade
How to use RichardErkhov/NingLab_-_eCeLLM-M-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull RichardErkhov/NingLab_-_eCeLLM-M-gguf:Q4_K_M
Run and chat with the model
lemonade run user.NingLab_-_eCeLLM-M-gguf-Q4_K_M
List all available models
lemonade list
- Atomic Chat
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
eCeLLM-M - GGUF
- Model creator: https://huggingface.co/NingLab/
- Original model: https://huggingface.co/NingLab/eCeLLM-M/
| Name | Quant method | Size |
|---|---|---|
| eCeLLM-M.Q2_K.gguf | Q2_K | 2.53GB |
| eCeLLM-M.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| eCeLLM-M.Q3_K.gguf | Q3_K | 3.28GB |
| eCeLLM-M.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| eCeLLM-M.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| eCeLLM-M.IQ4_XS.gguf | IQ4_XS | 0.64GB |
| eCeLLM-M.Q4_0.gguf | Q4_0 | 3.83GB |
| eCeLLM-M.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| eCeLLM-M.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| eCeLLM-M.Q4_K.gguf | Q4_K | 1.06GB |
| eCeLLM-M.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| eCeLLM-M.Q4_1.gguf | Q4_1 | 4.24GB |
| eCeLLM-M.Q5_0.gguf | Q5_0 | 4.65GB |
| eCeLLM-M.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| eCeLLM-M.Q5_K.gguf | Q5_K | 4.78GB |
| eCeLLM-M.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| eCeLLM-M.Q5_1.gguf | Q5_1 | 5.07GB |
| eCeLLM-M.Q6_K.gguf | Q6_K | 5.53GB |
| eCeLLM-M.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: cc-by-4.0 datasets: - NingLab/ECInstruct
eCeLLM-M
This repo contains the models for "eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data"
eCeLLM Models
Leveraging ECInstruct, we develop eCeLLM by instruction tuning general-purpose LLMs (base models). The eCeLLM-M model is instruction-tuned from the large base models Mistral-7B Instruct-v0.2.
Citation
@inproceedings{
peng2024ecellm,
title={eCe{LLM}: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data},
author={Bo Peng and Xinyi Ling and Ziru Chen and Huan Sun and Xia Ning},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=LWRI4uPG2X}
}
- Downloads last month
- 15
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit