Instructions to use matchaaaaa/Chaifighter-20B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use matchaaaaa/Chaifighter-20B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="matchaaaaa/Chaifighter-20B-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("matchaaaaa/Chaifighter-20B-v2")
model = AutoModelForCausalLM.from_pretrained("matchaaaaa/Chaifighter-20B-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use matchaaaaa/Chaifighter-20B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "matchaaaaa/Chaifighter-20B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "matchaaaaa/Chaifighter-20B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/matchaaaaa/Chaifighter-20B-v2

SGLang

How to use matchaaaaa/Chaifighter-20B-v2 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 "matchaaaaa/Chaifighter-20B-v2" \
    --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": "matchaaaaa/Chaifighter-20B-v2",
		"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 "matchaaaaa/Chaifighter-20B-v2" \
        --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": "matchaaaaa/Chaifighter-20B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use matchaaaaa/Chaifighter-20B-v2 with Docker Model Runner:
```
docker model run hf.co/matchaaaaa/Chaifighter-20B-v2
```

matchaaaaa commited on May 20, 2024

Commit

2499789

verified ·

1 Parent(s): fa4f53e

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -0

README.md CHANGED Viewed

@@ -36,6 +36,16 @@ Below is an instruction that describes a task. Write a response that appropriate
 ### Response:
 ```
 ## Merge Details
 ### Mergekit

 ### Response:
 ```
+## Recommended Settings: Universal-Light *or* Universal-Creative
+Here are some settings ranges that tend to work for me. They aren't strict values, and there's a bit of leeway in them. Feel free to experiment a bit!
+* Temperature:        **1.0** *to* **1.5** (adjust to taste)
+* Min-P:              **0.1** (increasing might help if it goes cuckoo)
+* Repetition Penalty: **1.05** *to* **1.1** (high values aren't needed and usually degrade output)
+* Rep. Penalty Range: **256** *or* **512**
+*all other samplers disabled*
 ## Merge Details
 ### Mergekit