CoolFace
Modelpublic

adamksn/Llama3.1-8B-Enigma-GGUF

sourceHugging Facellama3.1updated 2y agoView on Hugging Face
0likes251downloads
Model Card

Description

This repo contains GGUF format model files for Llama3.1-8B-Enigma.

Files Provided

NameQuantBitsFile SizeRemark
llama3.1-8b-enigma.Q2_K.ggufQ2_K23.18 GB2.96G, +3.5199 ppl @ Llama-3-8B
llama3.1-8b-enigma.Q3_K.ggufQ3_K34.02 GB3.74G, +0.6569 ppl @ Llama-3-8B
llama3.1-8b-enigma.Q4_0.ggufQ4_044.66 GB4.34G, +0.4685 ppl @ Llama-3-8B
llama3.1-8b-enigma.Q4_K.ggufQ4_K44.92 GB4.58G, +0.1754 ppl @ Llama-3-8B
llama3.1-8b-enigma.Q5_K.ggufQ5_K55.73 GB5.33G, +0.0569 ppl @ Llama-3-8B
llama3.1-8b-enigma.Q6_K.ggufQ6_K66.60 GB6.14G, +0.0217 ppl @ Llama-3-8B
llama3.1-8b-enigma.Q8_0.ggufQ8_088.54 GB7.96G, +0.0026 ppl @ Llama-3-8B

Parameters

pathtypearchitecturerope_thetasliding_winmax_pos_embed
ValiantLabs/Llama3.1-8B-EnigmallamaLlamaForCausalLM500000.0null131072

Original Model Card

image/jpeg

Enigma is a code-instruct model built on Llama 3.1 8b.

Version

This is the 2024-09-04 release of Enigma for Llama 3.1 8b, enhancing code-instruct and general chat capabilities.

Help us and recommend Enigma to your friends! We're excited for more Enigma releases in the future.

Right now, we're working on more new Build Tools to come very soon, built on Llama 3.1 :)

Prompting Guide

Enigma uses the Llama 3.1 Instruct prompt format. The example script below can be used as a starting point for general chat:

python
import transformers
import torch

model_id = "ValiantLabs/Llama3.1-8B-Enigma"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are Enigma, a highly capable code assistant."},
    {"role": "user", "content": "Can you explain virtualization to me?"}
]

outputs = pipeline(
    messages,
    max_new_tokens=1024,
)

print(outputs[0]["generated_text"][-1])

The Model

Enigma is built on top of Llama 3.1 8b Instruct, using high quality code-instruct data and general chat data in Llama 3.1 Instruct prompt style to supplement overall performance.

Our current version of Enigma is trained on code-instruct data from sequelbox/Tachibana and general chat data from sequelbox/Supernova.

image/jpeg

Enigma is created by Valiant Labs.

Check out our HuggingFace page for Shining Valiant 2 and our other Build Tools models for creators!

Follow us on X for updates on our models!

We care about open source. For everyone to use.

We encourage others to finetune further from our models.