Instructions to use fblgit/una-cybertron-7b-v2-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fblgit/una-cybertron-7b-v2-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="fblgit/una-cybertron-7b-v2-bf16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fblgit/una-cybertron-7b-v2-bf16")
model = AutoModelForCausalLM.from_pretrained("fblgit/una-cybertron-7b-v2-bf16")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fblgit/una-cybertron-7b-v2-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fblgit/una-cybertron-7b-v2-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fblgit/una-cybertron-7b-v2-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fblgit/una-cybertron-7b-v2-bf16

SGLang

How to use fblgit/una-cybertron-7b-v2-bf16 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 "fblgit/una-cybertron-7b-v2-bf16" \
    --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": "fblgit/una-cybertron-7b-v2-bf16",
		"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 "fblgit/una-cybertron-7b-v2-bf16" \
        --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": "fblgit/una-cybertron-7b-v2-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fblgit/una-cybertron-7b-v2-bf16 with Docker Model Runner:
```
docker model run hf.co/fblgit/una-cybertron-7b-v2-bf16
```

Context length

by mrfakename - opened Dec 5, 2023

Discussion

mrfakename

Dec 5, 2023

Hi, great model - what’s the context length?

fblgit

Owner Dec 5, 2023

32K i believe. That remains unaffected from zephyr generation, I followed their gym.

mrfakename

Dec 5, 2023

Hi, zephyr is 8k right?

fblgit

Owner Dec 5, 2023

i dont have enough GPU to test such thing.. do u ?
But give it a shot, the tok/mod states 32K

fblgit changed discussion status to closed Dec 5, 2023

mrfakename

Dec 5, 2023

Nah, I don’t have a GPU, but thanks for the info!

mo137

Dec 9, 2023

•

edited Dec 9, 2023

Using Exllamav2_HF and alpha=1, the model breaks down above 8k tokens. When I set alpha=2.5, it worked with a 16k token limit.

I think it would be useful to mention in the model card that the base context is 8k.

fblgit

Owner Dec 9, 2023

hmmmmmm.. Interesting... can u share the full config ? I will update and cite you on the readme, thanks

mo137

Dec 10, 2023

No need to mention me. I used the exllamav2_HF loader, 8bpw-h8 exl2 quant, simple-1 preset.

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