metadata

base_model: Felladrin/TinyMistral-248M-SFT-v3
datasets:
  - OpenAssistant/oasst_top1_2023-08-25
inference: false
license: apache-2.0
model_creator: Felladrin
model_name: TinyMistral-248M-SFT-v3
pipeline_tag: text-generation
quantized_by: afrideva
tags:
  - autotrain
  - text-generation
  - gguf
  - ggml
  - quantized
  - q2_k
  - q3_k_m
  - q4_k_m
  - q5_k_m
  - q6_k
  - q8_0
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

Felladrin/TinyMistral-248M-SFT-v3-GGUF

Quantized GGUF model files for TinyMistral-248M-SFT-v3 from Felladrin

Name	Quant method	Size
tinymistral-248m-sft-v3.fp16.gguf	fp16	497.75 MB
tinymistral-248m-sft-v3.q2_k.gguf	q2_k	116.20 MB
tinymistral-248m-sft-v3.q3_k_m.gguf	q3_k_m	131.01 MB
tinymistral-248m-sft-v3.q4_k_m.gguf	q4_k_m	156.60 MB
tinymistral-248m-sft-v3.q5_k_m.gguf	q5_k_m	180.16 MB
tinymistral-248m-sft-v3.q6_k.gguf	q6_k	205.20 MB
tinymistral-248m-sft-v3.q8_0.gguf	q8_0	265.26 MB

Original Model Card:

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"