ValiantLabs_-_Llama3.2-3B-Enigma-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama3.2-3B-Enigma - GGUF

• Model creator: https://huggingface.co/ValiantLabs/
• Original model: https://huggingface.co/ValiantLabs/Llama3.2-3B-Enigma/

Original model description:

language:

• en license: llama3.2 tags:
• enigma
• valiant
• valiant-labs
• llama
• llama-3.2
• llama-3.2-instruct
• llama-3.2-instruct-3b
• llama-3
• llama-3-instruct
• llama-3-instruct-3b
• 3b
• code
• code-instruct
• python
• conversational
• chat
• instruct base_model: meta-llama/Llama-3.2-3B-Instruct datasets:
• sequelbox/Tachibana
• sequelbox/Supernova pipeline_tag: text-generation model_type: llama model-index:
• name: Llama3.2-3B-Enigma results:
  • task: type: text-generation name: Text Generation dataset: name: Winogrande (5-Shot) type: winogrande args: num_few_shot: 5 metrics:
    • type: acc value: 67.96 name: acc
  • task: type: text-generation name: Text Generation dataset: name: ARC Challenge (25-Shot) type: arc-challenge args: num_few_shot: 25 metrics:
    • type: acc_norm value: 47.18 name: normalized accuracy
  • task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics:
    • type: inst_level_strict_acc and prompt_level_strict_acc value: 47.75 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics:
    • type: acc_norm value: 18.81 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics:
    • type: exact_match value: 6.65 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics:
    • type: acc_norm value: 1.45 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics:
    • type: acc_norm value: 4.54 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics:
    • type: acc value: 15.41 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma name: Open LLM Leaderboard

---

Enigma is a code-instruct model built on Llama 3.2 3b.

• High quality code instruct performance with the Llama 3.2 Instruct chat format
• Finetuned on synthetic code-instruct data generated with Llama 3.1 405b. Find the current version of the dataset here!
• Overall chat performance supplemented with generalist synthetic data.

Version

This is the 2024-09-30 release of Enigma for Llama 3.2 3b, enhancing code-instruct and general chat capabilities.

Enigma is also available for Llama 3.1 8b!

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

Prompting Guide

Enigma uses the Llama 3.2 Instruct prompt format. The example script below can be used as a starting point for general chat:

import transformers
import torch

model_id = "ValiantLabs/Llama3.2-3B-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 3.2 3b Instruct, using high quality code-instruct data and general chat data in Llama 3.2 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.

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.

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.