You can deploy this model and start earning money today!

RichardErkhov/
EpistemeAI_-_Fireball-MathMistral-Nemo-Base-2407-gguf

Name: EpistemeAI_-_Fireball-MathMistral-Nemo-Base-2407-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Fireball-MathMistral-Nemo-Base-2407 - GGUF

Model creator: https://huggingface.co/EpistemeAI/
Original model: https://huggingface.co/EpistemeAI/Fireball-MathMistral-Nemo-Base-2407/

Name	Quant method	Size
Fireball-MathMistral-Nemo-Base-2407.Q2_K.gguf	Q2_K	4.46GB
Fireball-MathMistral-Nemo-Base-2407.IQ3_XS.gguf	IQ3_XS	4.94GB
Fireball-MathMistral-Nemo-Base-2407.IQ3_S.gguf	IQ3_S	5.18GB
Fireball-MathMistral-Nemo-Base-2407.Q3_K_S.gguf	Q3_K_S	5.15GB
Fireball-MathMistral-Nemo-Base-2407.IQ3_M.gguf	IQ3_M	5.33GB
Fireball-MathMistral-Nemo-Base-2407.Q3_K.gguf	Q3_K	5.67GB
Fireball-MathMistral-Nemo-Base-2407.Q3_K_M.gguf	Q3_K_M	5.67GB
Fireball-MathMistral-Nemo-Base-2407.Q3_K_L.gguf	Q3_K_L	6.11GB
Fireball-MathMistral-Nemo-Base-2407.IQ4_XS.gguf	IQ4_XS	6.33GB
Fireball-MathMistral-Nemo-Base-2407.Q4_0.gguf	Q4_0	6.59GB
Fireball-MathMistral-Nemo-Base-2407.IQ4_NL.gguf	IQ4_NL	6.65GB
Fireball-MathMistral-Nemo-Base-2407.Q4_K_S.gguf	Q4_K_S	6.63GB
Fireball-MathMistral-Nemo-Base-2407.Q4_K.gguf	Q4_K	6.96GB
Fireball-MathMistral-Nemo-Base-2407.Q4_K_M.gguf	Q4_K_M	6.96GB
Fireball-MathMistral-Nemo-Base-2407.Q4_1.gguf	Q4_1	7.26GB
Fireball-MathMistral-Nemo-Base-2407.Q5_0.gguf	Q5_0	7.93GB
Fireball-MathMistral-Nemo-Base-2407.Q5_K_S.gguf	Q5_K_S	7.93GB
Fireball-MathMistral-Nemo-Base-2407.Q5_K.gguf	Q5_K	8.13GB
Fireball-MathMistral-Nemo-Base-2407.Q5_K_M.gguf	Q5_K_M	8.13GB
Fireball-MathMistral-Nemo-Base-2407.Q5_1.gguf	Q5_1	8.61GB
Fireball-MathMistral-Nemo-Base-2407.Q6_K.gguf	Q6_K	9.37GB
Fireball-MathMistral-Nemo-Base-2407.Q8_0.gguf	Q8_0	12.13GB

Original model description:

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 and Huggingface's TRL library.

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 and Huggingface's TRL library.

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.

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:

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"
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.

RichardErkhov/EpistemeAI_-_Fireball-MathMistral-Nemo-Base-2407-gguf