Instructions to use ar08/Mistral-bengali-10K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ar08/Mistral-bengali-10K with Transformers:

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

pipe = pipeline("text-generation", model="ar08/Mistral-bengali-10K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ar08/Mistral-bengali-10K")
model = AutoModelForCausalLM.from_pretrained("ar08/Mistral-bengali-10K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ar08/Mistral-bengali-10K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ar08/Mistral-bengali-10K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ar08/Mistral-bengali-10K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ar08/Mistral-bengali-10K

SGLang

How to use ar08/Mistral-bengali-10K 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 "ar08/Mistral-bengali-10K" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ar08/Mistral-bengali-10K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ar08/Mistral-bengali-10K" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ar08/Mistral-bengali-10K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ar08/Mistral-bengali-10K with Docker Model Runner:
```
docker model run hf.co/ar08/Mistral-bengali-10K
```

Mistral Bengali Language Model

Welcome to the Mistral Bengali Language Model repository! 🌟

Overview

This repository hosts the Mistral Bengali Language Model, a powerful language model trained on Bengali text data. The model is capable of generating coherent and contextually relevant text in Bengali.

Model Configuration

The Mistral Bengali Language Model has the following configuration:

Model Name: ar08/Mistral-bengali-10K
Embedding Tokens Weight: [32,000, 1,024]
Layers: 12
Layer Norms: 12
Attention Heads: 16
Inference API: Text Generation

Usage

You can use the Mistral Bengali Language Model for various natural language processing tasks such as text generation, text completion, and sentiment analysis.

Text Generation

To generate text using the Mistral Bengali Language Model, you can input a prompt or a sentence to start the generation process. Here's an example of how you can use it:

Downloads last month: 3

Safetensors

Model size

0.2B params

Tensor type

F32