Instructions to use inflatebot/G2-9B-Blackout-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inflatebot/G2-9B-Blackout-R1 with Transformers:

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

pipe = pipeline("text-generation", model="inflatebot/G2-9B-Blackout-R1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inflatebot/G2-9B-Blackout-R1")
model = AutoModelForCausalLM.from_pretrained("inflatebot/G2-9B-Blackout-R1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inflatebot/G2-9B-Blackout-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inflatebot/G2-9B-Blackout-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inflatebot/G2-9B-Blackout-R1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/inflatebot/G2-9B-Blackout-R1

SGLang

How to use inflatebot/G2-9B-Blackout-R1 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 "inflatebot/G2-9B-Blackout-R1" \
    --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": "inflatebot/G2-9B-Blackout-R1",
		"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 "inflatebot/G2-9B-Blackout-R1" \
        --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": "inflatebot/G2-9B-Blackout-R1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use inflatebot/G2-9B-Blackout-R1 with Docker Model Runner:
```
docker model run hf.co/inflatebot/G2-9B-Blackout-R1
```

inflatebot commited on Sep 12, 2024

Commit

6ceb6aa

verified ·

1 Parent(s): 3e833cf

Rename 1boy, robot, mech, humanoid, faceless, bodysuit, tactical gear, m4 carbine, blac s-3977080432.png to blackout.png

Browse files

Files changed (2) hide show

.gitattributes +1 -0
1boy, robot, mech, humanoid, faceless, bodysuit, tactical gear, m4 carbine, blac s-3977080432.png → blackout.png +0 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 1boy,[[:space:]]robot,[[:space:]]mech,[[:space:]]humanoid,[[:space:]]faceless,[[:space:]]bodysuit,[[:space:]]tactical[[:space:]]gear,[[:space:]]m4[[:space:]]carbine,[[:space:]]blac[[:space:]]s-3977080432.png filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 1boy,[[:space:]]robot,[[:space:]]mech,[[:space:]]humanoid,[[:space:]]faceless,[[:space:]]bodysuit,[[:space:]]tactical[[:space:]]gear,[[:space:]]m4[[:space:]]carbine,[[:space:]]blac[[:space:]]s-3977080432.png filter=lfs diff=lfs merge=lfs -text
+blackout.png filter=lfs diff=lfs merge=lfs -text

1boy, robot, mech, humanoid, faceless, bodysuit, tactical gear, m4 carbine, blac s-3977080432.png → blackout.png RENAMED Viewed

File without changes