You can deploy this model and start earning money today!

RichardErkhov/
EpistemeAI_-_Fireball-12B-gguf

Name: EpistemeAI_-_Fireball-12B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Fireball-12B - GGUF

Model creator: https://huggingface.co/EpistemeAI/
Original model: https://huggingface.co/EpistemeAI/Fireball-12B/

Name	Quant method	Size
Fireball-12B.Q2_K.gguf	Q2_K	4.46GB
Fireball-12B.IQ3_XS.gguf	IQ3_XS	4.94GB
Fireball-12B.IQ3_S.gguf	IQ3_S	5.18GB
Fireball-12B.Q3_K_S.gguf	Q3_K_S	5.15GB
Fireball-12B.IQ3_M.gguf	IQ3_M	5.33GB
Fireball-12B.Q3_K.gguf	Q3_K	5.67GB
Fireball-12B.Q3_K_M.gguf	Q3_K_M	5.67GB
Fireball-12B.Q3_K_L.gguf	Q3_K_L	6.11GB
Fireball-12B.IQ4_XS.gguf	IQ4_XS	6.33GB
Fireball-12B.Q4_0.gguf	Q4_0	6.59GB
Fireball-12B.IQ4_NL.gguf	IQ4_NL	6.65GB
Fireball-12B.Q4_K_S.gguf	Q4_K_S	6.63GB
Fireball-12B.Q4_K.gguf	Q4_K	6.96GB
Fireball-12B.Q4_K_M.gguf	Q4_K_M	6.96GB
Fireball-12B.Q4_1.gguf	Q4_1	7.26GB
Fireball-12B.Q5_0.gguf	Q5_0	7.93GB
Fireball-12B.Q5_K_S.gguf	Q5_K_S	7.93GB
Fireball-12B.Q5_K.gguf	Q5_K	8.13GB
Fireball-12B.Q5_K_M.gguf	Q5_K_M	8.13GB
Fireball-12B.Q5_1.gguf	Q5_1	8.61GB
Fireball-12B.Q6_K.gguf	Q6_K	9.37GB
Fireball-12B.Q8_0.gguf	Q8_0	12.13GB

Original model description:

base_model: EpistemeAI/Fireball-Mistral-Nemo-Base-2407-sft-v2.2a language:

en license: apache-2.0 tags:
text-generation-inference
transformers
unsloth
mistral
trl datasets:
candenizkocak/code-alpaca-297k
yahma/alpaca-cleaned
reciperesearch/dolphin-sft-v0.1-preference pipeline_tag: text-generation model-index:
- name: Fireball-12B results:
  - task: type: text-generation dataset: name: dolphin-sft-v0.1-preference type: reciperesearch/dolphin-sft-v0.1-preference metrics:
    - name: MMLU_PRO type: MMLU value: 26.04
    - name: bbh type: bbh value: 30.67
    - name: IFEval type: IFeval value: 18.34 source: name: Open LLM Leaderboard url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard

Fireball-12B

This model is super fine-tune to provide better coding and better response(from first fine-tune) than Llama-3.1-8B and Google Gemma 2 9B. Further fine tuned with ORPO method with dataset

reciperesearch/dolphin-sft-v0.1-preference

Benchmark

## Training Dataset Supervised fine-tuning with dataset: - candenizkocak/code-alpaca-297k - yahma/alpaca-cleaned

Model Card for Fireball-12B

The Heavy fine-tuned Mistral-Nemo-Base-2407 Large Language Model (LLM) is a pretrained generative text model of 12B parameters trained jointly by Mistral AI and NVIDIA, 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
Pre-trained and instructed versions
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)

Guardrail/Moderation guide:

For guardrailing and moderating prompts against indirect/direct prompt injections and jailbreaking, please follow the SentinelShield AI GitHub repository: SentinelShield AI

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
1pip install mistral_inference 2pip install mistral-demo 3pip 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-12B"
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))

Accelerator mode:

pip install accelerate #GPU A100/L4

from transformers import AutoModelForCausalLM, AutoTokenizer
from accelerate import Accelerator

# Initialize the accelerator
accelerator = Accelerator()

# Define the model ID
model_id = "EpistemeAI/Fireball-12B"

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Load the model and prepare it for distributed setup using accelerate
model = AutoModelForCausalLM.from_pretrained(model_id)

# Move the model to the appropriate device using accelerate
model, = accelerator.prepare(model)

# Prepare inputs
inputs = tokenizer("Hello my name is", return_tensors="pt").to(accelerator.device)

# Generate outputs with the model
outputs = model.generate(**inputs, max_new_tokens=20)

# Decode and print the outputs
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

EpistemeAI/Fireball-12B is a pretrained base model and therefore does not have any moderation mechanisms. Go to Guardrail/Moderation guide section for moderation guide

Citation for yahma/alpaca-cleaned dataset

@misc{alpaca,
  author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
  title = {Stanford Alpaca: An Instruction-following LLaMA model},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
}

Uploaded model

Developed by: EpistemeAI
License: apache-2.0
Finetuned from model : EpistemeAI/Fireball-Mistral-Nemo-Base-2407-sft-v2.2a

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

RichardErkhov/EpistemeAI_-_Fireball-12B-gguf