Instructions to use djelia/bm-mistral-7b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use djelia/bm-mistral-7b-v1 with Transformers:

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

pipe = pipeline("text-generation", model="djelia/bm-mistral-7b-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("djelia/bm-mistral-7b-v1")
model = AutoModelForCausalLM.from_pretrained("djelia/bm-mistral-7b-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use djelia/bm-mistral-7b-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/djelia/bm-mistral-7b-v1

SGLang

How to use djelia/bm-mistral-7b-v1 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 "djelia/bm-mistral-7b-v1" \
    --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": "djelia/bm-mistral-7b-v1",
		"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 "djelia/bm-mistral-7b-v1" \
        --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": "djelia/bm-mistral-7b-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use djelia/bm-mistral-7b-v1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for djelia/bm-mistral-7b-v1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for djelia/bm-mistral-7b-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for djelia/bm-mistral-7b-v1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="djelia/bm-mistral-7b-v1",
    max_seq_length=2048,
)

Docker Model Runner
How to use djelia/bm-mistral-7b-v1 with Docker Model Runner:
```
docker model run hf.co/djelia/bm-mistral-7b-v1
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

bm-mistral-7b-v1

Mistral 7B v0.3 fine-tuned for Bambara (Bamanankan) on four tasks, all prompted in Bambara: Bambara→French translation, French→Bambara translation, sentiment classification, and ASR transcription correction.

MistralForCausalLM, 7.25B parameters in bfloat16 — 32 layers, hidden size 4096, 32 attention heads with 8 KV heads (GQA), 32,768-token vocabulary, 32,768-token context, RoPE theta 1e6, no sliding window.

Prompt format

There is no chat template. The model expects a Bambara Alpaca-style prompt, with the task written as a Bambara instruction under ### ɲɛfɔli:, the user content under ### Donnafɛnw:, and generation starting after ### Jaabi:.

Usage

The repo ships merged weights alongside the LoRA adapter; load the merged weights with AutoModelForCausalLM.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "djelia/bm-mistral-7b-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)

ALPACA_PROMPT = """Nin ye baara dɔ ɲɛfɔli ye, min bɛ donnafɛnw ni sigidaw fara ɲɔgɔn kan. I ka kan ka jaabi sɛbɛn min bɛ ɲinini dafa ka ɲɛ.

### ɲɛfɔli:
{}

### Donnafɛnw:
{}

### Jaabi:
"""

TRANSLATE_BM_FR = """I ye kanbaara kɛla min bɛ kuma yɛlɛma ka bɔ "bambara" la ka taa "français" la.
I bɛna kuma sɔrɔ "bambara" la, i ka kan ka o yɛlɛma ka kɛ "français" ye.
I ka kan ka yɛlɛmali dɔrɔn di, ka to kunnafoni wɛrɛw ni kow ɲɛfɔli la."""

prompt = ALPACA_PROMPT.format(TRANSLATE_BM_FR, "I ni ce, i ka kɛnɛ wa?")
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=300, pad_token_id=tokenizer.pad_token_id)
print(tokenizer.decode(output[0], skip_special_tokens=True).split("Jaabi:")[-1].strip())

Swap TRANSLATE_BM_FR for the Bambara instruction of whichever task you want. The tokenizer sets add_bos_token=True, so <s> is prepended for you, and padding_side is already "left" for batched generation.

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for djelia/bm-mistral-7b-v1

Base model

mistralai/Mistral-7B-v0.3

Quantized

unsloth/mistral-7b-v0.3-bnb-4bit

Finetuned

(664)

this model

Finetunes

1 model

djelia
/

bm-mistral-7b-v1

You need to agree to share your contact information to access this model

bm-mistral-7b-v1

Prompt format

Usage

Model tree for djelia/bm-mistral-7b-v1

Space using djelia/bm-mistral-7b-v1 1