78 lines
6.3 KiB
Markdown
78 lines
6.3 KiB
Markdown
|
Quantization made by Richard Erkhov.
|
||
|
|
|
||
|
|
[Github](https://github.com/RichardErkhov)
|
||
|
|
|
||
|
|
[Discord](https://discord.gg/pvy7H8DZMG)
|
||
|
|
|
||
|
|
[Request more models](https://github.com/RichardErkhov/quant_request)
|
||
|
|
|
||
|
|
|
||
|
|
TinyKAI-3B-v0.1 - GGUF
|
||
|
|
- Model creator: https://huggingface.co/Keynote-Technology/
|
||
|
|
- Original model: https://huggingface.co/Keynote-Technology/TinyKAI-3B-v0.1/
|
||
|
|
|
||
|
|
|
||
|
|
| Name | Quant method | Size |
|
||
|
|
| ---- | ---- | ---- |
|
||
|
|
| [TinyKAI-3B-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q2_K.gguf) | Q2_K | 1.84GB |
|
||
|
|
| [TinyKAI-3B-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.IQ3_XS.gguf) | IQ3_XS | 1.84GB |
|
||
|
|
| [TinyKAI-3B-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.IQ3_S.gguf) | IQ3_S | 1.84GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q3_K_S.gguf) | Q3_K_S | 1.84GB |
|
||
|
|
| [TinyKAI-3B-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.IQ3_M.gguf) | IQ3_M | 1.92GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q3_K.gguf) | Q3_K | 1.99GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q3_K_M.gguf) | Q3_K_M | 1.99GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q3_K_L.gguf) | Q3_K_L | 2.06GB |
|
||
|
|
| [TinyKAI-3B-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.IQ4_XS.gguf) | IQ4_XS | 1.86GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q4_0.gguf) | Q4_0 | 1.84GB |
|
||
|
|
| [TinyKAI-3B-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.IQ4_NL.gguf) | IQ4_NL | 1.86GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q4_K_S.gguf) | Q4_K_S | 2.24GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q4_K.gguf) | Q4_K | 2.4GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q4_K_M.gguf) | Q4_K_M | 2.4GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q4_1.gguf) | Q4_1 | 2.04GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q5_0.gguf) | Q5_0 | 2.23GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q5_K_S.gguf) | Q5_K_S | 2.42GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q5_K.gguf) | Q5_K | 2.57GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q5_K_M.gguf) | Q5_K_M | 2.57GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q5_1.gguf) | Q5_1 | 2.42GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q6_K.gguf) | Q6_K | 3.39GB |
|
||
|
|
| [TinyKAI-3B-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Keynote-Technology_-_TinyKAI-3B-v0.1-gguf/blob/main/TinyKAI-3B-v0.1.Q8_0.gguf) | Q8_0 | 3.39GB |
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
Original model description:
|
||
|
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
datasets:
|
||
|
|
- Keynote-Technology/PLANE-2K
|
||
|
|
- togethercomputer/RedPajama-Data-V2
|
||
|
|
tags:
|
||
|
|
- code
|
||
|
|
- chatbot
|
||
|
|
- safetensors
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
TinyKAI 3B is a fine-tuned LLM (Large Language Model) based off of [OpenLlama 3B v2](https://huggingface.co/openlm-research/open_llama_3b_v2).
|
||
|
|
The TinyKAI models are a series of lightweight LLMs under 5 Billion parameters, usually used for research.
|
||
|
|
|
||
|
|
## Direct Use
|
||
|
|
TinyKAI 3B is optimal for research on large language models, specifically the influence of web data on the properties of large language models (fairness, safety, limitations, capabilities, etc.).
|
||
|
|
|
||
|
|
## Training
|
||
|
|
This model was trained on a mixture of the [Falcon refined-web dataset](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), the [StarCoder dataset](https://huggingface.co/datasets/bigcode/starcoderdata) and the wikipedia, arxiv, book and stackexchange part of the [RedPajama dataset](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T).
|
||
|
|
|
||
|
|
## Banned Use
|
||
|
|
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful or insulting to anyone or any certain group.
|
||
|
|
TinyKAI-3B is governed by the [apache 2.0 liscense](https://choosealicense.com/licenses/apache-2.0/), and therefore means that whatever the license deems unacceptable shall not be allowed. We specificaly ban the use of [ANY AND ALL KAI MODELS](https://huggingface.co/collections/Keynote-Technology/kai-large-language-models) for hate speech towards a paricular thing, person, our particular group due to [legal](https://www.ftc.gov/news-events/news/press-releases/2022/06/ftc-report-warns-about-using-artificial-intelligence-combat-online-problems) and ethical issues.
|
||
|
|
|
||
|
|
## Limitations
|
||
|
|
TinyKAI 3B is trained on English data only, and will not generate appropriately reasonable content in other languages. Being trained on a representative of the web, it will carry the stereotypes and biases commonly encountered online.
|
||
|
|
|
||
|
|
## Recommendations
|
||
|
|
We recommend users of TinyKAI 3B to consider finetuning it for personal use, and for precautions to be taken for any commercial use.
|
||
|
|
|
||
|
|
## WARNING!
|
||
|
|
This model runs on an older version of transformers, v4.10.0, and therefore may be unstable.
|
||
|
|
|