Instructions to use Sao10K/Fimbulvetr-11B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sao10K/Fimbulvetr-11B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Sao10K/Fimbulvetr-11B-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sao10K/Fimbulvetr-11B-v2")
model = AutoModelForCausalLM.from_pretrained("Sao10K/Fimbulvetr-11B-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sao10K/Fimbulvetr-11B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sao10K/Fimbulvetr-11B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sao10K/Fimbulvetr-11B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Sao10K/Fimbulvetr-11B-v2

SGLang

How to use Sao10K/Fimbulvetr-11B-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 "Sao10K/Fimbulvetr-11B-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": "Sao10K/Fimbulvetr-11B-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 "Sao10K/Fimbulvetr-11B-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": "Sao10K/Fimbulvetr-11B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sao10K/Fimbulvetr-11B-v2 with Docker Model Runner:
```
docker model run hf.co/Sao10K/Fimbulvetr-11B-v2
```

Holy **** it's really, really good!

#12

by Joure - opened Mar 15, 2024

Discussion

Joure

Mar 15, 2024

•

edited Mar 15, 2024

I've played around pretty much with all the mainstream models, you know the ones that get all the attention but after trying this, I think it's my favorite model so far. I usually run 7B models, I can run quantized 70B models as I do have the system RAM but I prefer using VRAM for obvious reasons. And this one right here hits the sweet spot. It's fast but really, really good, I am amazed.

It really keeps the conversation going and stays in-character. I use models to test characters. Basically let's say I'm writing a story and instead of me just writing the characters and thinking for them I like to use local LLM's to "live" these characters. It's very much like getting to know a person and more so, I can get a reaction from certain story-beats. I can then combine that with my own ideas and I feel characters become a lot more real.

Sorry, long story but yeah, this model does an incredibly job at keeping characters stay, um, in-character. Kudos and thanks, I'll deffo gonna be keeping an eye on you from now on. Thank you so much for the contribution!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment