Instructions to use ewof/koishi-7b-qlora-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ewof/koishi-7b-qlora-gguf with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ewof/koishi-7b-qlora-gguf", dtype="auto")

llama-cpp-python

How to use ewof/koishi-7b-qlora-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ewof/koishi-7b-qlora-gguf",
	filename="ggml-model-F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ewof/koishi-7b-qlora-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ewof/koishi-7b-qlora-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ewof/koishi-7b-qlora-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ewof/koishi-7b-qlora-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ewof/koishi-7b-qlora-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 ewof/koishi-7b-qlora-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ewof/koishi-7b-qlora-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 ewof/koishi-7b-qlora-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ewof/koishi-7b-qlora-gguf:Q4_K_M

Use Docker

docker model run hf.co/ewof/koishi-7b-qlora-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use ewof/koishi-7b-qlora-gguf with Ollama:
```
ollama run hf.co/ewof/koishi-7b-qlora-gguf:Q4_K_M
```

Unsloth Studio

How to use ewof/koishi-7b-qlora-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ewof/koishi-7b-qlora-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ewof/koishi-7b-qlora-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ewof/koishi-7b-qlora-gguf to start chatting

Docker Model Runner
How to use ewof/koishi-7b-qlora-gguf with Docker Model Runner:
```
docker model run hf.co/ewof/koishi-7b-qlora-gguf:Q4_K_M
```

Lemonade

How to use ewof/koishi-7b-qlora-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ewof/koishi-7b-qlora-gguf:Q4_K_M

Run and chat with the model

lemonade run user.koishi-7b-qlora-gguf-Q4_K_M

List all available models

lemonade list

GGUF

little endian

Training

axolotl was used for training on a 6x nvidia a40 gpu cluster.

the a40 GPU cluster has been graciously provided by Arc Compute.

trained on koishi commit 6e675d1 for one epoch

Base Model

rank 16 lora tune of mistralai/Mistral-7B-v0.1 (all modules, merged)

Prompting

The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: <|system|>, <|user|> and <|model|>.

The <|system|> prompt can be used to inject out-of-channel information behind the scenes, while the <|user|> prompt should be used to indicate user input. The <|model|> token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.

Downloads last month: 110

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

ewof
/

koishi-7b-qlora-gguf

GGUF

Training

Base Model

Prompting

Dataset used to train ewof/koishi-7b-qlora-gguf

Collection including ewof/koishi-7b-qlora-gguf

mistral