134 lines
6.0 KiB
Markdown
134 lines
6.0 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)
|
|
|
|
|
|
TinyAlpaca-1.1B - GGUF
|
|
- Model creator: https://huggingface.co/luckychao/
|
|
- Original model: https://huggingface.co/luckychao/TinyAlpaca-1.1B/
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [TinyAlpaca-1.1B.Q2_K.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q2_K.gguf) | Q2_K | 0.4GB |
|
|
| [TinyAlpaca-1.1B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.IQ3_XS.gguf) | IQ3_XS | 0.44GB |
|
|
| [TinyAlpaca-1.1B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.IQ3_S.gguf) | IQ3_S | 0.47GB |
|
|
| [TinyAlpaca-1.1B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q3_K_S.gguf) | Q3_K_S | 0.47GB |
|
|
| [TinyAlpaca-1.1B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.IQ3_M.gguf) | IQ3_M | 0.48GB |
|
|
| [TinyAlpaca-1.1B.Q3_K.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q3_K.gguf) | Q3_K | 0.51GB |
|
|
| [TinyAlpaca-1.1B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q3_K_M.gguf) | Q3_K_M | 0.51GB |
|
|
| [TinyAlpaca-1.1B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q3_K_L.gguf) | Q3_K_L | 0.55GB |
|
|
| [TinyAlpaca-1.1B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.IQ4_XS.gguf) | IQ4_XS | 0.57GB |
|
|
| [TinyAlpaca-1.1B.Q4_0.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q4_0.gguf) | Q4_0 | 0.59GB |
|
|
| [TinyAlpaca-1.1B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.IQ4_NL.gguf) | IQ4_NL | 0.6GB |
|
|
| [TinyAlpaca-1.1B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q4_K_S.gguf) | Q4_K_S | 0.6GB |
|
|
| [TinyAlpaca-1.1B.Q4_K.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q4_K.gguf) | Q4_K | 0.62GB |
|
|
| [TinyAlpaca-1.1B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q4_K_M.gguf) | Q4_K_M | 0.62GB |
|
|
| [TinyAlpaca-1.1B.Q4_1.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q4_1.gguf) | Q4_1 | 0.65GB |
|
|
| [TinyAlpaca-1.1B.Q5_0.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q5_0.gguf) | Q5_0 | 0.71GB |
|
|
| [TinyAlpaca-1.1B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q5_K_S.gguf) | Q5_K_S | 0.71GB |
|
|
| [TinyAlpaca-1.1B.Q5_K.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q5_K.gguf) | Q5_K | 0.73GB |
|
|
| [TinyAlpaca-1.1B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q5_K_M.gguf) | Q5_K_M | 0.73GB |
|
|
| [TinyAlpaca-1.1B.Q5_1.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q5_1.gguf) | Q5_1 | 0.77GB |
|
|
| [TinyAlpaca-1.1B.Q6_K.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q6_K.gguf) | Q6_K | 0.84GB |
|
|
| [TinyAlpaca-1.1B.Q8_0.gguf](https://huggingface.co/RichardErkhov/luckychao_-_TinyAlpaca-1.1B-gguf/blob/main/TinyAlpaca-1.1B.Q8_0.gguf) | Q8_0 | 1.09GB |
|
|
|
|
|
|
|
|
|
|
Original model description:
|
|
---
|
|
language:
|
|
- en
|
|
datasets:
|
|
- tatsu-lab/alpaca
|
|
---
|
|
# Model Card for Model ID
|
|
|
|
This model checkpoint is the TinyLlama-1.1B fine-tuned on [alpaca dataset](https://huggingface.co/datasets/tatsu-lab/alpaca).
|
|
|
|
## Model Details
|
|
|
|
### Model Sources
|
|
|
|
<!-- Provide the basic links for the model. -->
|
|
|
|
- **Repository:** https://github.com/jzhang38/TinyLlama
|
|
- **Paper:** [https://arxiv.org/abs/2404.02406]
|
|
|
|
## Uses
|
|
|
|
|
|
The use of this model should comply with the restrictions from [TinyLlama-1.1b](https://github.com/jzhang38/TinyLlama) and
|
|
[Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca).
|
|
|
|
## How to Get Started with the Model
|
|
|
|
Use the code below to get started with the model.
|
|
|
|
```
|
|
# Load model directly
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("luckychao/TinyAlpaca-1.1B")
|
|
model = AutoModelForCausalLM.from_pretrained("luckychao/TinyAlpaca-1.1B")
|
|
|
|
```
|
|
|
|
## Training Details
|
|
|
|
### Training Data
|
|
|
|
We use the [alpaca dataset](https://huggingface.co/datasets/tatsu-lab/alpaca), which is created by researchers from Stanford University.
|
|
|
|
### Training Procedure
|
|
|
|
We follow the same training procedure and mostly same hyper-parameters to fine-tune the original Alpaca model on Llama. The procedure can be found in [stanford_alpaca project](https://huggingface.co/datasets/tatsu-lab/alpaca).
|
|
|
|
#### Training Hyperparameters
|
|
```
|
|
--num_train_epochs 3 \
|
|
--per_device_train_batch_size 2 \
|
|
--per_device_eval_batch_size 2 \
|
|
--gradient_accumulation_steps 4 \
|
|
--evaluation_strategy "no" \
|
|
--save_strategy "steps" \
|
|
--save_steps 1000 \
|
|
--save_total_limit 1 \
|
|
--learning_rate 2e-5 \
|
|
--weight_decay 0. \
|
|
--warmup_ratio 0.03 \
|
|
--lr_scheduler_type "cosine" \
|
|
--logging_steps 1 \
|
|
--bf16 True \
|
|
--fsdp "full_shard auto_wrap" \
|
|
--fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
|
|
--model_max_length 2048
|
|
|
|
```
|
|
|
|
|
|
## Citation
|
|
|
|
The model is mostly developed for the paper below. Please cite it if you find the repository helpful.
|
|
|
|
**BibTeX:**
|
|
```
|
|
@article{hao2024exploring,
|
|
title={Exploring Backdoor Vulnerabilities of Chat Models},
|
|
author={Hao, Yunzhuo and Yang, Wenkai and Lin, Yankai},
|
|
journal={arXiv preprint arXiv:2404.02406},
|
|
year={2024}
|
|
}
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
|