Instructions to use smallstepai/Misal-7B-base-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smallstepai/Misal-7B-base-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="smallstepai/Misal-7B-base-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("smallstepai/Misal-7B-base-v0.1")
model = AutoModelForCausalLM.from_pretrained("smallstepai/Misal-7B-base-v0.1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use smallstepai/Misal-7B-base-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smallstepai/Misal-7B-base-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smallstepai/Misal-7B-base-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/smallstepai/Misal-7B-base-v0.1

SGLang

How to use smallstepai/Misal-7B-base-v0.1 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 "smallstepai/Misal-7B-base-v0.1" \
    --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": "smallstepai/Misal-7B-base-v0.1",
		"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 "smallstepai/Misal-7B-base-v0.1" \
        --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": "smallstepai/Misal-7B-base-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use smallstepai/Misal-7B-base-v0.1 with Docker Model Runner:
```
docker model run hf.co/smallstepai/Misal-7B-base-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Misal-7B-base-v0.1

It is a language model based on Meta's Llama2 architecture, pretrained using Marathi Text Data.

Built by - smallstep.ai

Making of Misal?

Detailed blog here.

Pretraining :

During the pretraining phase of our large language model, the model was exposed to a vast corpus of text data comprising approximately 2 billion Marathi tokens. This corpus primarily consisted of newspaper data spanning the years 2016 to 2022, sourced primarily from the CulturaX dataset. In addition to this, we supplemented our training data with additional sources such as l3cube, ai4bharat, and other internet-based datasets.