Hugging Face's logo

Agnuxo
/
Tinytron-Qwen-0.5B-Instruct_CODE_Python-Spanish_English_GGUF_4bit

Adapters
Safetensors
NeMo
English
Spanish
gemma
llama
minillama
tinyllama
tiny
mini
minitron
tinytron
ollama
Model card Files Community
Tinytron-Qwen-0.5B-Instruct_CODE_Python-Spanish_English_GGUF_4bit / README.md
Agnuxo's picture
Agnuxo
Create README.md
584ade5 verified
preview code
|
raw
history blame contribute delete
No virus
1.39 kB
metadata
model_size: 494034560
required_memory: 1.84
accuracy: 0.5080275229357798
metrics:
  - GLUE_SST-2
license: apache-2.0
datasets:
  - jtatman/python-code-dataset-500k
  - Vezora/Tested-143k-Python-Alpaca
language:
  - en
  - es
base_model: Qwen/Qwen2-0.5B
library_name: adapter-transformers
tags:
  - llama
  - minillama
  - tinyllama
  - tiny
  - mini
  - nemo
  - minitron
  - tinytron
  - ollama

Uploaded model

  • Developed by: Agnuxo
  • License: apache-2.0
  • Finetuned from model: Agnuxo/Tinytron-Qwen2-0.5B

This model was fine-tuned using Unsloth and Huggingface's TRL library.

Benchmark Results

This model has been fine-tuned for various tasks and evaluated on the following benchmarks:

GLUE_SST-2

Accuracy: 0.5080

GLUE_SST-2 Metrics

Model Size: 494,034,560 parameters Required Memory: 1.84 GB

For more details, visit my GitHub.

Thanks for your interest in this model!