metadata
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
- Dataset: OpenAssistant/oasst_top1_2023-08-25
Recommended Prompt Format
<|im_start|>user
{message}<|im_end|>
<|im_start|>assistant
How it was trained
%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"