metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: BEE-spoke-data/tFINE-900m-e16-d32-flan
tags:
  - instruct
  - code
datasets:
  - pszemraj/infinity-instruct-7m-T2T_en
pipeline_tag: text2text-generation

tFINE-900m-e16-d32-instruct

Model description

This model is a fine-tuned version of BEE-spoke-data/tFINE-900m-e16-d32-flan on the pszemraj/infinity-instruct-7m-T2T_en dataset. It achieves the following results on the evaluation set:

Loss: 1.3588
Num Input Tokens Seen: 810173896

Usage Example

You can also run inference with turboT5 on ampere+ GPUs for better performance. See example on Colab.

from transformers import pipeline

pipe = pipeline(
  "text2text-generation",
  model="BEE-spoke-data/tFINE-900m-e16-d32-instruct",
  # device_map="auto", # uncomment if have GPU/accelerate
)
prompt = "Write me a python script that demonstrates an advanced sorting algorithm"
res = pipe(
    prompt,
    max_new_tokens=384,
    num_beams=4,
    early_stopping=True,
    no_repeat_ngram_size=6,
)
print(res[0]["generated_text"])

evals

open-llm-leaderboard 2

Model	Average ⬆️	IFEval	BBH	MATH Lvl 5	GPQA	MUSR	MMLU-PRO
🔶 BEE-spoke-data/tFINE-900m-e16-d32-instruct	5.82	13.21	4.74	0	0.56	13.81	2.63
🔶 BEE-spoke-data/tFINE-900m-e16-d32-flan	4.43	15.06	4.41	0	0	3.72	3.41