Instructions to use flytech/Ruckus-PyAssi-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flytech/Ruckus-PyAssi-13b with Transformers:

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

pipe = pipeline("text-generation", model="flytech/Ruckus-PyAssi-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flytech/Ruckus-PyAssi-13b")
model = AutoModelForCausalLM.from_pretrained("flytech/Ruckus-PyAssi-13b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use flytech/Ruckus-PyAssi-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flytech/Ruckus-PyAssi-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flytech/Ruckus-PyAssi-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flytech/Ruckus-PyAssi-13b

SGLang

How to use flytech/Ruckus-PyAssi-13b 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 "flytech/Ruckus-PyAssi-13b" \
    --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": "flytech/Ruckus-PyAssi-13b",
		"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 "flytech/Ruckus-PyAssi-13b" \
        --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": "flytech/Ruckus-PyAssi-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flytech/Ruckus-PyAssi-13b with Docker Model Runner:
```
docker model run hf.co/flytech/Ruckus-PyAssi-13b
```

flytech commited on Oct 9, 2023

Commit

c66cc85

1 Parent(s): fb957cd

Training in progress, step 1200

Browse files

Files changed (3) hide show

adapter_model.safetensors +1 -1
events.out.tfevents.1696860510.06440233d7b1.331.0 +2 -2
events.out.tfevents.1696860510.06440233d7b1.331.1 +2 -2

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b3ab78feaf72624f5c9d091dde8319bfbfa85c31e775dd9f99fbce2ad479d6
 size 250422888

 version https://git-lfs.github.com/spec/v1
+oid sha256:7ed0c4bb9dd03fb2841edef7fec79acdf89a39acc89bb68d9baba6780d7be5be
 size 250422888

events.out.tfevents.1696860510.06440233d7b1.331.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3f42b4f593f944348d260594e70c37f200f47d4b6e86d4cd15303fa3cb6937
-size 6471

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed7d09cde43c72d58097060e5f805a993aa62fbfe78ffce53cdaa7c534cd9495
+size 6851

events.out.tfevents.1696860510.06440233d7b1.331.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8f60c3d9a6a3b3ccb7c88ac12bc1c7956ff42bbe5d9d2cb6aa49f7d856ed05
-size 6471

 version https://git-lfs.github.com/spec/v1
+oid sha256:13566e8f54a93a63bcbb904616ab209263de6f646b74af12f0dfeb0f56a7dbce
+size 6851