Instructions to use EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 with Transformers:

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

pipe = pipeline("text-generation", model="EpistemeAI/Fireball-MathMistral-Nemo-Base-2407")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EpistemeAI/Fireball-MathMistral-Nemo-Base-2407")
model = AutoModelForCausalLM.from_pretrained("EpistemeAI/Fireball-MathMistral-Nemo-Base-2407", device_map="auto")
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 EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EpistemeAI/Fireball-MathMistral-Nemo-Base-2407

SGLang

How to use EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 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 "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407" \
    --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": "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407",
		"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 "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407" \
        --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": "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 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 EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 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 EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="EpistemeAI/Fireball-MathMistral-Nemo-Base-2407",
    max_seq_length=2048,
)

Docker Model Runner
How to use EpistemeAI/Fireball-MathMistral-Nemo-Base-2407 with Docker Model Runner:
```
docker model run hf.co/EpistemeAI/Fireball-MathMistral-Nemo-Base-2407
```

Fireball-MathMistral-Nemo-Base-2407 / README.md

legolasyiu

Update README.md

6050da2 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

3.13 kB

	---
	base_model: unsloth/Mistral-Nemo-Base-2407-bnb-4bit
	language:
	- en
	license: apache-2.0
	tags:
	- text-generation-inference
	- transformers
	- unsloth
	- mistral
	- trl
	datasets:
	- meta-math/MetaMathQA
	---

	# Uploaded model

	- Developed by: EpistemeAI
	- License: apache-2.0
	- Finetuned from model : unsloth/Mistral-Nemo-Base-2407-bnb-4bit
	-
	This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

	# Fireball-MathMistral-Nemo-Base-2407

	This model is fine-tune to provide better math response than Mistral-Nemo-Base-2407

	## Training Dataset
	Supervised fine-tuning with datasets with meta-math/MetaMathQA



	This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

	[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

	# Model Card for Mistral-Nemo-Base-2407

	The Fireball-MathMistral-Nemo-Base-2407 Large Language Model (LLM) is a pretrained generative text model of 12B parameters, it significantly outperforms existing models smaller or similar in size.

	For more details about this model please refer to our release [blog post](https://mistral.ai/news/mistral-nemo/).

	## Key features
	- Released under the Apache 2 License
	- Trained with a 128k context window
	- Trained on a large proportion of multilingual and code data
	- Drop-in replacement of Mistral 7B

	## Model Architecture
	Mistral Nemo is a transformer model, with the following architecture choices:
	- Layers: 40
	- Dim: 5,120
	- Head dim: 128
	- Hidden dim: 14,436
	- Activation Function: SwiGLU
	- Number of heads: 32
	- Number of kv-heads: 8 (GQA)
	- Vocabulary size: 2**17 ~= 128k
	- Rotary embeddings (theta = 1M)

	#### Demo

	After installing `mistral_inference`, a `mistral-demo` CLI command should be available in your environment.


	### Transformers

	> [!IMPORTANT]
	> NOTE: Until a new release has been made, you need to install transformers from source:
	> ```sh
	> pip install git+https://github.com/huggingface/transformers.git
	> ```

	If you want to use Hugging Face `transformers` to generate text, you can do something like this.

	```py
	from transformers import AutoModelForCausalLM, AutoTokenizer
	model_id = "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407"
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(model_id)
	inputs = tokenizer("Hello my name is", return_tensors="pt")
	outputs = model.generate(**inputs, max_new_tokens=20)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	> [!TIP]
	> Unlike previous Mistral models, Mistral Nemo requires smaller temperatures. We recommend to use a temperature of 0.3.

	## Note

	`Mistral-Nemo-Base-2407` is a pretrained base model and therefore does not have any moderation mechanisms.