Instructions to use vmombo/bloom-560m-fang-translation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vmombo/bloom-560m-fang-translation with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-560m")
model = PeftModel.from_pretrained(base_model, "vmombo/bloom-560m-fang-translation")

Transformers

How to use vmombo/bloom-560m-fang-translation with Transformers:

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

pipe = pipeline("text-generation", model="vmombo/bloom-560m-fang-translation")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vmombo/bloom-560m-fang-translation", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vmombo/bloom-560m-fang-translation with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vmombo/bloom-560m-fang-translation"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vmombo/bloom-560m-fang-translation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vmombo/bloom-560m-fang-translation

SGLang

How to use vmombo/bloom-560m-fang-translation 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 "vmombo/bloom-560m-fang-translation" \
    --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": "vmombo/bloom-560m-fang-translation",
		"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 "vmombo/bloom-560m-fang-translation" \
        --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": "vmombo/bloom-560m-fang-translation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vmombo/bloom-560m-fang-translation with Docker Model Runner:
```
docker model run hf.co/vmombo/bloom-560m-fang-translation
```

BLOOM-560m — French → Fang Translation

Fine-tuned version of bigscience/bloom-560m for translating French into Fang (a Bantu language spoken in Gabon, Equatorial Guinea, and Cameroon), using LoRA (Low-Rank Adaptation).

Usage

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("bigscience/bloom-560m", dtype=torch.bfloat16)
model = PeftModel.from_pretrained(base, "vmombo/bloom-560m-fang-translation")
tokenizer = AutoTokenizer.from_pretrained("vmombo/bloom-560m-fang-translation")
model.eval()

prompt = "Traduis en fang: Bonjour, comment allez-vous ?\n\nFang:"
inputs = tokenizer(prompt, return_tensors="pt")
with torch.no_grad():
    output = model.generate(**inputs, max_new_tokens=64)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Prompt Format

Traduis en fang: <french sentence>

Fang: <fang translation>

Training Details

Parameter	Value
Base model	bigscience/bloom-560m
Method	LoRA (r=16, alpha=32)
Target modules	query_key_value
Trainable params	1,572,864 (0.28%)
Train samples	9,439
Eval samples	1,049
Epochs	5
Batch size	4 × 4 grad accum
Learning rate	2e-4 (cosine)
Max length	256 tokens
Hardware	Apple Silicon (MPS)

Training Objective

Only the Fang output tokens receive gradient signal — the French prompt is masked with labels=-100. This focuses 100% of learning on the target language rather than wasting capacity predicting French that BLOOM already knows.

Limitations

Fang is a very low-resource language. This model is an early-stage research prototype and may produce inaccurate translations. Contributions of additional Fang text data are welcome.

Author

Developed by vmombo.

Downloads last month: 7

Model tree for vmombo/bloom-560m-fang-translation

Base model

bigscience/bloom-560m

Adapter

(129)

this model