Instructions to use BangorAI/cyfieithydd-7b-fersiwn-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BangorAI/cyfieithydd-7b-fersiwn-2 with Transformers:

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

pipe = pipeline("text-generation", model="BangorAI/cyfieithydd-7b-fersiwn-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BangorAI/cyfieithydd-7b-fersiwn-2")
model = AutoModelForCausalLM.from_pretrained("BangorAI/cyfieithydd-7b-fersiwn-2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BangorAI/cyfieithydd-7b-fersiwn-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BangorAI/cyfieithydd-7b-fersiwn-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BangorAI/cyfieithydd-7b-fersiwn-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BangorAI/cyfieithydd-7b-fersiwn-2

SGLang

How to use BangorAI/cyfieithydd-7b-fersiwn-2 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 "BangorAI/cyfieithydd-7b-fersiwn-2" \
    --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": "BangorAI/cyfieithydd-7b-fersiwn-2",
		"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 "BangorAI/cyfieithydd-7b-fersiwn-2" \
        --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": "BangorAI/cyfieithydd-7b-fersiwn-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BangorAI/cyfieithydd-7b-fersiwn-2 with Docker Model Runner:
```
docker model run hf.co/BangorAI/cyfieithydd-7b-fersiwn-2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mae'r model LLM yn seiliedig ar BangorAI/mistral-7b-cy-epoch-2, sef y model Mistral-7B wedi hyfforddiant parhaus ar gyfer y Gymraeg.

Cafodd y model hyfforddiant cywrain pellach ar ddata Cofnod y Cynulliad a ddarparir gan TechIaith.

Demo

Gallwch roi gynnig ar esiampl o'r model yma: https://demo.bangor.ai/

Fformat Sgwrs

Mae'r hyfforddiant cywrain wedi defnyddio'r fformat canlynol ar gyfer trosi o'r Saesneg i'r Gymraeg (a'r naill ffordd i'r llall).

Cyfieithwch y testun Saesneg canlynol i'r Gymraeg.
### Saesneg:
{prompt}

### Cymraeg:

Sut i'w ddefnyddio

Mae'r model Mistral-7B-v-0.1 sy'n tanseilio'r model yma hefo 4k-sliding-context-window, felly mae'n well pecynnu'r testyn fesul paragraff neu ddau a'u bwydo i mewn i'r LLM yn eu tro.

Hawlfraint

Mae'r data Cofnod y Cynulliad dan drywdded Llywodraeth Agored.

Downloads last month: 4

Model tree for BangorAI/cyfieithydd-7b-fersiwn-2

Quantizations

1 model

BangorAI
/

cyfieithydd-7b-fersiwn-2

Demo

Fformat Sgwrs

Sut i'w ddefnyddio

Hawlfraint

Model tree for BangorAI/cyfieithydd-7b-fersiwn-2

Dataset used to train BangorAI/cyfieithydd-7b-fersiwn-2