File size: 2,284 Bytes
85723f7 51573d6 85723f7 51573d6 b01aa48 3cfecd1 85723f7 51573d6 85723f7 51573d6 85723f7 51573d6 85723f7 51573d6 0a82167 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
---
license: apache-2.0
tags:
- autotrain
- text-generation
base_model: Locutusque/TinyMistral-248M
datasets:
- OpenAssistant/oasst_top1_2023-08-25
widget:
- text: |-
<|im_start|>user
Write the specs of a game about trolls and warriors in a fantasy world.<|im_end|>
<|im_start|>assistant
The game is an adventure game that takes place on a planet, where players must explore their unique abilities to survive. Players can use different strategies such as collecting items or trading them for gold or silver coins, but they also need to learn how to deal with obstacles and find new ways to escape.<|im_end|>
<|im_start|>user
Could you tell me something curious about the Earth?<|im_end|>
<|im_start|>assistant
The planet is a large, rocky world with an atmosphere of 10 billion years old and a surface area around 25 million miles (36 million kilometers) wide.<|im_end|>
<|im_start|>user
What are some potential applications for quantum computing?<|im_end|>
<|im_start|>assistant
inference:
parameters:
max_new_tokens: 64
repetition_penalty: 1.18
---
# Locutusque's TinyMistral-248M trained on OpenAssistant TOP-1 Conversation Threads
- Base model: [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M/blob/90b89d18fdf27937dc04ab8a9b543c5af2991c7f/README.md)
- Dataset: [OpenAssistant/oasst_top1_2023-08-25](https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25)
## Recommended Prompt Format
```
<|im_start|>user
{message}<|im_end|>
<|im_start|>assistant
```
## How it was trained
```ipython
%pip install autotrain-advanced
!autotrain setup
!autotrain llm \
--train \
--trainer "sft" \
--model './TinyMistral-248M/' \
--model_max_length 4096 \
--block-size 1024 \
--project-name 'trained-model' \
--data-path "OpenAssistant/oasst_top1_2023-08-25" \
--train_split "train" \
--valid_split "test" \
--text-column "text" \
--lr 1e-5 \
--train_batch_size 2 \
--epochs 5 \
--evaluation_strategy "steps" \
--save-strategy "steps" \
--save-total-limit 2 \
--warmup-ratio 0.05 \
--weight-decay 0.0 \
--gradient-accumulation 8 \
--logging-steps 10 \
--scheduler "constant"
``` |