This is quantized version of
ValiantLabs/Llama3.1-8B-Enigma created using llama.cpp
Enigma is a code-instruct model built on Llama 3.1 8b.
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 :)
Enigma uses the
Llama 3.1 Instruct prompt format. The example script below can be used as a starting point for general chat:
1import transformers
2import torch
3
4model_id = "ValiantLabs/Llama3.1-8B-Enigma"
5
6pipeline = transformers.pipeline(
7 "text-generation",
8 model=model_id,
9 model_kwargs={"torch_dtype": torch.bfloat16},
10 device_map="auto",
11)
12
13messages = [
14 {"role": "system", "content": "You are Enigma, a highly capable code assistant."},
15 {"role": "user", "content": "Can you explain virtualization to me?"}
16]
17
18outputs = pipeline(
19 messages,
20 max_new_tokens=1024,
21)
22
23print(outputs[0]["generated_text"][-1])
Enigma is built on top of Llama 3.1 8b Instruct, using code-instruct data to supplement code-instruct performance using Llama 3.1 Instruct prompt style.
Our current version of the Enigma code-instruct dataset is
sequelbox/Tachibana, supplemented with a small selection of data from
LDJnr/Pure-Dove for general chat consistency.
We care about open source.
For everyone to use.
We encourage others to finetune further from our models.
