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

Libraries

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

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

pipe = pipeline("text-generation", model="ewof/koishi-7b-qlora")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ewof/koishi-7b-qlora")
model = AutoModelForCausalLM.from_pretrained("ewof/koishi-7b-qlora")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ewof/koishi-7b-qlora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ewof/koishi-7b-qlora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use ewof/koishi-7b-qlora 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 "ewof/koishi-7b-qlora" \
    --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": "ewof/koishi-7b-qlora",
		"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 "ewof/koishi-7b-qlora" \
        --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": "ewof/koishi-7b-qlora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ewof/koishi-7b-qlora with Docker Model Runner:
```
docker model run hf.co/ewof/koishi-7b-qlora
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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: 8

Model tree for ewof/koishi-7b-qlora

Quantizations

2 models

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

Collection including ewof/koishi-7b-qlora

mistral

Collection

4 items • Updated Dec 15, 2023