Instructions to use KoboldAI/fairseq-dense-2.7B-Janeway with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoboldAI/fairseq-dense-2.7B-Janeway with Transformers:

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

pipe = pipeline("text-generation", model="KoboldAI/fairseq-dense-2.7B-Janeway")

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

tokenizer = AutoTokenizer.from_pretrained("KoboldAI/fairseq-dense-2.7B-Janeway")
model = AutoModelForCausalLM.from_pretrained("KoboldAI/fairseq-dense-2.7B-Janeway", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KoboldAI/fairseq-dense-2.7B-Janeway with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KoboldAI/fairseq-dense-2.7B-Janeway"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/fairseq-dense-2.7B-Janeway",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KoboldAI/fairseq-dense-2.7B-Janeway

SGLang

How to use KoboldAI/fairseq-dense-2.7B-Janeway 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 "KoboldAI/fairseq-dense-2.7B-Janeway" \
    --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": "KoboldAI/fairseq-dense-2.7B-Janeway",
		"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 "KoboldAI/fairseq-dense-2.7B-Janeway" \
        --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": "KoboldAI/fairseq-dense-2.7B-Janeway",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KoboldAI/fairseq-dense-2.7B-Janeway with Docker Model Runner:
```
docker model run hf.co/KoboldAI/fairseq-dense-2.7B-Janeway
```

fairseq-dense-2.7B-Janeway

Commit History

Sep 26, 2025

00:33
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
dcf54d8

Apr 16, 2022

16:46
Small fix

mrseeker87

f5a0d4c

Mar 20, 2022

13:00
Adding welcome text

mrseeker87

28a3b8c

Feb 24, 2022

07:54
typo

mrseeker87

f2885be

Feb 21, 2022

14:38
Wrong config

mrseeker87

99ec323
12:41
Initial commit

mrseeker87

5366a06
11:45
Update README.md

system HF Staff

9eefbc0
11:45
initial commit

system HF Staff

6f62099

Commit History

Sep 26, 2025

Adding `safetensors` variant of this model⁠

Apr 16, 2022

Small fix

Mar 20, 2022

Adding welcome text

Feb 24, 2022

typo

Feb 21, 2022

Wrong config

Initial commit

Update README.md

initial commit