Downloads · 30 days
23
1% of all-time downloads
AtAndDev_-_ShortKing-1.4b-v0.1-gguf
RichardErkhov/AtAndDev_-_ShortKing-1.4b-v0.1-gguf
AtAndDev_-_ShortKing-1.4b-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
4.1K
Public
Repo size
16.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf19.4 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024
- SHA
- acede24d
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
ShortKing-1.4b-v0.1 - GGUF
- Model creator: https://huggingface.co/AtAndDev/
- Original model: https://huggingface.co/AtAndDev/ShortKing-1.4b-v0.1/
| Name | Quant method | Size |
|---|---|---|
| ShortKing-1.4b-v0.1.Q2_K.gguf | Q2_K | 0.53GB |
| ShortKing-1.4b-v0.1.IQ3_XS.gguf | IQ3_XS | 0.59GB |
| ShortKing-1.4b-v0.1.IQ3_S.gguf | IQ3_S | 0.61GB |
| ShortKing-1.4b-v0.1.Q3_K_S.gguf | Q3_K_S | 0.61GB |
| ShortKing-1.4b-v0.1.IQ3_M.gguf | IQ3_M | 0.66GB |
| ShortKing-1.4b-v0.1.Q3_K.gguf | Q3_K | 0.71GB |
| ShortKing-1.4b-v0.1.Q3_K_M.gguf | Q3_K_M | 0.71GB |
| ShortKing-1.4b-v0.1.Q3_K_L.gguf | Q3_K_L | 0.77GB |
| ShortKing-1.4b-v0.1.IQ4_XS.gguf | IQ4_XS | 0.74GB |
| ShortKing-1.4b-v0.1.Q4_0.gguf | Q4_0 | 0.77GB |
| ShortKing-1.4b-v0.1.IQ4_NL.gguf | IQ4_NL | 0.78GB |
| ShortKing-1.4b-v0.1.Q4_K_S.gguf | Q4_K_S | 0.78GB |
| ShortKing-1.4b-v0.1.Q4_K.gguf | Q4_K | 0.85GB |
| ShortKing-1.4b-v0.1.Q4_K_M.gguf | Q4_K_M | 0.85GB |
| ShortKing-1.4b-v0.1.Q4_1.gguf | Q4_1 | 0.85GB |
| ShortKing-1.4b-v0.1.Q5_0.gguf | Q5_0 | 0.92GB |
| ShortKing-1.4b-v0.1.Q5_K_S.gguf | Q5_K_S | 0.92GB |
| ShortKing-1.4b-v0.1.Q5_K.gguf | Q5_K | 0.98GB |
| ShortKing-1.4b-v0.1.Q5_K_M.gguf | Q5_K_M | 0.98GB |
| ShortKing-1.4b-v0.1.Q5_1.gguf | Q5_1 | 1.0GB |
| ShortKing-1.4b-v0.1.Q6_K.gguf | Q6_K | 1.08GB |
| ShortKing-1.4b-v0.1.Q8_0.gguf | Q8_0 | 1.4GB |
Original model description:
license: cc-by-nc-4.0 datasets:
- vicgalle/alpaca-gpt4 language:
- en
Model Overview
Model license: cc-by-nc-4.0<br> This model is trained based on EleutherAI/pythia-1.4b-deduped model that is LoRA finetuned on vicgalle/alpaca-gpt4 dataset.<br>
Prompt Template: Alpaca
<system_prompt>
### Instruction:
<user_message>
### Response:
<assistant_response>
Intended Use
THIS IS A TEST MODEL, IT IS NOT INTENDED FOR REAL APPLICATIONS BY ANY MEANS. HOWEVER, A NEW MODEL IS COMING IN THE SAME TOPIC.<br> This model series will be used for small but intense applications.
Training Details
This model took 2:31:23 to train in QLoRA on a single T4 GPU.<br>
- epochs:
1 - train batch size:
12 - eval batch size:
12 - gradient accumulation steps:
1 - maximum gradient normal:
0.3 - learning rate:
2e-4 - weight decay:
0.001 - optimizer:
paged_adamw_32bit - learning rate schedule:
cosine - warmup ratio (linear):
0.03
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024