Downloads · 30 days
77
4% of all-time downloads
Keynote-Technology_-_TinyKAI-0.7B-v0.1-gguf
RichardErkhov/Keynote-Technology_-_TinyKAI-0.7B-v0.1-gguf
Keynote-Technology_-_TinyKAI-0.7B-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
2K
Public
Repo size
2.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.4 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 15, 2024
- Updated
- Oct 16, 2024
- SHA
- 3b44ab47
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
TinyKAI-0.7B-v0.1 - GGUF
- Model creator: https://huggingface.co/Keynote-Technology/
- Original model: https://huggingface.co/Keynote-Technology/TinyKAI-0.7B-v0.1/
| Name | Quant method | Size |
|---|---|---|
| TinyKAI-0.7B-v0.1.Q2_K.gguf | Q2_K | 0.08GB |
| TinyKAI-0.7B-v0.1.IQ3_XS.gguf | IQ3_XS | 0.08GB |
| TinyKAI-0.7B-v0.1.IQ3_S.gguf | IQ3_S | 0.08GB |
| TinyKAI-0.7B-v0.1.Q3_K_S.gguf | Q3_K_S | 0.08GB |
| TinyKAI-0.7B-v0.1.IQ3_M.gguf | IQ3_M | 0.09GB |
| TinyKAI-0.7B-v0.1.Q3_K.gguf | Q3_K | 0.09GB |
| TinyKAI-0.7B-v0.1.Q3_K_M.gguf | Q3_K_M | 0.09GB |
| TinyKAI-0.7B-v0.1.Q3_K_L.gguf | Q3_K_L | 0.1GB |
| TinyKAI-0.7B-v0.1.IQ4_XS.gguf | IQ4_XS | 0.1GB |
| TinyKAI-0.7B-v0.1.Q4_0.gguf | Q4_0 | 0.1GB |
| TinyKAI-0.7B-v0.1.IQ4_NL.gguf | IQ4_NL | 0.1GB |
| TinyKAI-0.7B-v0.1.Q4_K_S.gguf | Q4_K_S | 0.1GB |
| TinyKAI-0.7B-v0.1.Q4_K.gguf | Q4_K | 0.11GB |
| TinyKAI-0.7B-v0.1.Q4_K_M.gguf | Q4_K_M | 0.11GB |
| TinyKAI-0.7B-v0.1.Q4_1.gguf | Q4_1 | 0.11GB |
| TinyKAI-0.7B-v0.1.Q5_0.gguf | Q5_0 | 0.11GB |
| TinyKAI-0.7B-v0.1.Q5_K_S.gguf | Q5_K_S | 0.11GB |
| TinyKAI-0.7B-v0.1.Q5_K.gguf | Q5_K | 0.12GB |
| TinyKAI-0.7B-v0.1.Q5_K_M.gguf | Q5_K_M | 0.12GB |
| TinyKAI-0.7B-v0.1.Q5_1.gguf | Q5_1 | 0.12GB |
| TinyKAI-0.7B-v0.1.Q6_K.gguf | Q6_K | 0.13GB |
| TinyKAI-0.7B-v0.1.Q8_0.gguf | Q8_0 | 0.17GB |
Original model description:
license: apache-2.0 tags:
- code
- safetensors
- chatbot
- 0.7B
- text-generation datasets:
- Keynote-Technology/PLANE-2K
- togethercomputer/RedPajama-Data-V2 pipeline_tag: text-generation
TinyKAI 0.7B
Model Details
TinyKAI-0.7B is one of the world's SMALLEST "large" language models EVER! We acheived such a feat by essentially compressing GPT2 and squeezing it to fit into one sub-GB pytorch.bin file!
Uses
Due to being one of the tiniest "large" language models on huggingface, many corners had to be cut. TinyKAI-0.7B has a max output of only 150 characters per computation (without repeating itself). Therefore, TinyKAI is only intended for research purposes.
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->Banned Use
TinyKAI-1B is governed by the apache 2.0 liscense, and therefore means that whatever the license deems unacceptable shall not be allowed. We specificaly ban the use of ANY AND ALL KAI MODELS for hate speech towards a paricular thing, person, our particular group due to legal and ethical issues.
Limitations
2K characters max output length, English only, and extremely tiny (1GB).
Recommendations
TinyKAI-0.7B is a very small model, and is good for AI research especially.
- Created
- Oct 15, 2024
- Updated
- Oct 16, 2024