Hugging Face's logo

vinhnx90
/
vt-qwen-3b-GRPO-merged-16bit-bnb-4bit

Feature Extraction
Transformers
Safetensors
English
qwen2
bnb-my-repo
text-generation-inference
unsloth
trl
grpo
text-embeddings-inference
4-bit precision
bitsandbytes
Model card Files
xet
 Community

vinhnx90/vt-qwen-3b-GRPO-merged-16bit (Quantized)

Description

This model is a quantized version of the original model vinhnx90/vt-qwen-3b-GRPO-merged-16bit.

It's quantized using the BitsAndBytes library to 4-bit using the bnb-my-repo space.

Quantization Details

  • Quantization Type: int4
  • bnb_4bit_quant_type: fp4
  • bnb_4bit_use_double_quant: True
  • bnb_4bit_compute_dtype: bfloat16
  • bnb_4bit_quant_storage: bfloat16

📄 Original Model Information

Uploaded model

  • Developed by: vinhnx90
  • License: apache-2.0
  • Finetuned from model : unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
2
Safetensors
Model size
1B params
Tensor type
F32
·
BF16
·
F16
·
U8
·
Inference Providers NEW
Feature Extraction
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for vinhnx90/vt-qwen-3b-GRPO-merged-16bit-bnb-4bit

Base model

vinhnx90/vt-qwen-3b-GRPO-merged-16bit
Quantized
(3)
this model

Collection including vinhnx90/vt-qwen-3b-GRPO-merged-16bit-bnb-4bit