Instructions to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-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 NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-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 NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF with Ollama:
```
ollama run hf.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF with Docker Model Runner:
```
docker model run hf.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M
```

Lemonade

How to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Using the new gguf quant method may result in a worse overall performance than that of the old gguf quants.

by TheYuriLover - opened Jan 18, 2024

Discussion

TheYuriLover

Jan 18, 2024

•

edited Jan 18, 2024

Source : https://github.com/ggerganov/llama.cpp/discussions/5006
The problem we have when using a calibration dataset is the overfitting to a certain style and then in consequence, make the model worse on other aspects.

Supposedly, the suggestion to fix this is to use a calibration dataset composed of random tokens instead.

TheYuriLover changed discussion title from Using the new gguf quant method may result in a woese overall performance than that of the old gguf quants. to Using the new gguf quant method may result in a worse overall performance than that of the old gguf quants. Jan 18, 2024

teknium

NousResearch org Jan 18, 2024

Thank you, we reverted to old llama cpp and it fixed it afaik

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment