Instructions to use EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo with Transformers:

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

pipe = pipeline("text-generation", model="EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo")
model = AutoModelForCausalLM.from_pretrained("EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo")
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

vLLM

How to use EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo

SGLang

How to use EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo 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 "EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo" \
    --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": "EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo",
		"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 "EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo" \
        --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": "EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo 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 EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo 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 EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo",
    max_seq_length=2048,
)

Docker Model Runner
How to use EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo with Docker Model Runner:
```
docker model run hf.co/EpistemeAI2/Fireball-MathMistral-Nemo-Base-2407-v2dpo
```

Fireball-MathMistral-Nemo-Base-2407-v2dpo / README.md

legolasyiu

Update README.md

6b7d851 verified almost 2 years ago

preview code

raw

history blame contribute delete

3.38 kB

metadata

base_model: EpistemeAI/Fireball-MathMistral-Nemo-Base-2407
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mistral
  - trl

Uploaded model

Developed by: EpistemeAI
License: apache-2.0
Finetuned from model : EpistemeAI/Fireball-MathMistral-Nemo-Base-2407

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Fireball-MathMistral-Nemo-Base-2407-v2dpo

This model is fine-tune to provide better math response than Mistral-Nemo-Base-2407, Google Gemma 2 9B, Llama 3.1 8B and others similar models.

Training Dataset

DPO (Direct Preference Optimization) training with math datasets.

This Mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Model Card for EpistemeAI's Fireball-MathMistral-Nemo-Base-2407-v2dpo

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.

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

NOTE: Until a new release has been made, you need to install transformers from source:
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.

from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407-v2dpo"
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))

Unlike previous Mistral models, Mistral Nemo requires smaller temperatures. We recommend to use a temperature of 0.3.

Note

EpistemeAI/Fireball-MathMistral-Nemo-Base-2407-v2dpo is a pretrained base model and therefore does not have any moderation mechanisms.