Instructions to use sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss with Transformers:

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

pipe = pipeline("text-generation", model="sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss")
model = AutoModelForCausalLM.from_pretrained("sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss

SGLang

How to use sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss 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 "sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss" \
    --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": "sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss",
		"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 "sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss" \
        --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": "sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss with Docker Model Runner:
```
docker model run hf.co/sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss
```

sandmanbuzz commited on Feb 22, 2024

Commit

a2b1cbd

verified ·

1 Parent(s): 995d097

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -1,3 +1,3 @@
-Bro [literally posts like a bone stock ass lora](https://huggingface.co/LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss-LoRA) with no model, and that's a huge pain in the ass to work with because loras are a pain in the ass to work with. So here's an fp16 of it.
 Dude's got some exl2s of the instruct version, but no fp16 of that either, and it's like... who even uses exl2? What am I, a caveman?


1	+ Bro [literally posts like a bone stock ass lora](https://huggingface.co/LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss-LoRA) with no model, and that's a huge pain in the ass to work with because loras are a pain in the ass to work with. So here's an fp16 of it. We kinda had to make shit up to get this applied, because, like I said, loras are a huge pain in the ass.
2
3	Dude's got some exl2s of the instruct version, but no fp16 of that either, and it's like... who even uses exl2? What am I, a caveman?