Downloads · 30 days
59
3% of all-time downloads
CyberNative-AI_-_Colibri_8b_v0.1-gguf
RichardErkhov/CyberNative-AI_-_Colibri_8b_v0.1-gguf
CyberNative-AI_-_Colibri_8b_v0.1-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
2.1K
Public
Repo size
92.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf108 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 8, 2024
- Updated
- Oct 8, 2024
- SHA
- 715fb6fe
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Colibri_8b_v0.1 - GGUF
- Model creator: https://huggingface.co/CyberNative-AI/
- Original model: https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/
| Name | Quant method | Size |
|---|---|---|
| Colibri_8b_v0.1.Q2_K.gguf | Q2_K | 2.96GB |
| Colibri_8b_v0.1.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| Colibri_8b_v0.1.IQ3_S.gguf | IQ3_S | 3.43GB |
| Colibri_8b_v0.1.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| Colibri_8b_v0.1.IQ3_M.gguf | IQ3_M | 3.52GB |
| Colibri_8b_v0.1.Q3_K.gguf | Q3_K | 3.74GB |
| Colibri_8b_v0.1.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| Colibri_8b_v0.1.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| Colibri_8b_v0.1.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| Colibri_8b_v0.1.Q4_0.gguf | Q4_0 | 4.34GB |
| Colibri_8b_v0.1.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| Colibri_8b_v0.1.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| Colibri_8b_v0.1.Q4_K.gguf | Q4_K | 4.58GB |
| Colibri_8b_v0.1.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| Colibri_8b_v0.1.Q4_1.gguf | Q4_1 | 4.78GB |
| Colibri_8b_v0.1.Q5_0.gguf | Q5_0 | 5.21GB |
| Colibri_8b_v0.1.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| Colibri_8b_v0.1.Q5_K.gguf | Q5_K | 5.34GB |
| Colibri_8b_v0.1.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| Colibri_8b_v0.1.Q5_1.gguf | Q5_1 | 5.65GB |
| Colibri_8b_v0.1.Q6_K.gguf | Q6_K | 6.14GB |
| Colibri_8b_v0.1.Q8_0.gguf | Q8_0 | 7.95GB |
Original model description:
language:
- en license: llama3 library_name: transformers tags:
- cybersecurity
- security
- cybersec
- base
- llama3
Colibri_8b_v0.1
<!-- Provide a quick summary of what the model is/does. --> <img src="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/cybernative_ai_colibri_logo.jpeg" alt="CyberNative-AI/Colibri_8b_v0.1"/>Colibri: Conversational CyberSecurity Model
TRY colibri via huggingface Spaces!
GGUF Quant used in Spaces available here: <a href="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1_q5_gguf">CyberNative-AI/Colibri_8b_v0.1_q5_gguf</a>
Colibri_8b_v0.1 is a conversational model for cybersecurity fine-tuned from the awesome dolphin-2.9-llama3-8b. (llama-3-8b -> cognitivecomputations/dolphin-2.9-llama3-8b -> CyberNative-AI/Colibri_8b_v0.1)
We derived our training dataset by creating Q/A pairs from a huge amount of cybersecurity related texts.
v0.1 trained for 3 epochs using around 35k Q/A pairs FFT on all parameters using a single A100 80gb for 3 hours.
This model is using ChatML prompt template format.
example:
<|im_start|>system
You are Colibri, an advanced cybersecurity AI assistant developed by CyberNative AI.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
ILLEGAL OR UNETHICAL USE IS PROHIBITED!
Use accordingly with the law.
Provided by CyberNative AI
Examples:
<img src="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/Screenshot%20from%202024-05-15%2018-30-44.png" alt="Example1"/> <img src="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/Screenshot%20from%202024-05-15%2018-38-19.png" alt="Example2"/> <img src="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/Screenshot%20from%202024-05-15%2018-50-31.png" alt="Example3"/>- Created
- Oct 8, 2024
- Updated
- Oct 8, 2024