Hugging Face's logo

shuyuej
/
bge-multilingual-gemma2-GPTQ

Feature Extraction
Transformers
Safetensors
gemma2
text-generation-inference
Inference Endpoints
4-bit precision
gptq
Model card Files Community

The Quantized FlagEmbedding (BGE-Multilingual-Gemma2) Model

Original Base Embedding Model: BAAI/bge-multilingual-gemma2.
Link: https://huggingface.co/BAAI/bge-multilingual-gemma2

Quantization Configurations 

"quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "damp_percent": 0.01,
    "desc_act": true,
    "group_size": 128,
    "model_file_base_name": null,
    "model_name_or_path": null,
    "quant_method": "gptq",
    "static_groups": false,
    "sym": true,
    "true_sequential": true
  },

Source Codes

Source Codes: https://github.com/vkola-lab/medpodgpt/tree/main/quantization.

Downloads last month
9
Safetensors
Model size
2.95B params
Tensor type
I32
·
FP16
·
Inference Examples
Feature Extraction
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including shuyuej/bge-multilingual-gemma2-GPTQ