Edit model card

Model Card for haesleinhuepf/gemma-2b-it-bia-proof-of-concept2

This is a proof-of-concept model. It is not properly trained. Do not use it for anything.

Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms

Model Details

Model Description

  • Developed by: Robert Haase
  • License: gemma license
  • Finetuned from model [optional]: google/gemma-2b-it

How to Get Started with the Model

Use the code below to get started with the model.

def prompt_hf(request, model="haesleinhuepf/gemma-2b-it-bia-proof-of-concept2"):
    global prompt_hf
    import transformers
    import torch
    
    if prompt_hf._pipeline is None:    
        prompt_hf._pipeline = transformers.pipeline(
            "text-generation", model=model, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
        )
    
    return prompt_hf._pipeline(request)[0]['generated_text']
prompt_hf._pipeline = None

prompt_hf("What is the capital of France?")

Training Details

Training Data

https://huggingface.co/datasets/haesleinhuepf/bio-image-analysis-qa

Model Card Contact

robert dot haase at uni minus leipzig dot de

Downloads last month
965
Safetensors
Model size
2.51B params
Tensor type
FP16
·
Inference Examples
Inference API (serverless) is not available, repository is disabled.

Dataset used to train haesleinhuepf/gemma-2b-it-bia-proof-of-concept2

Space using haesleinhuepf/gemma-2b-it-bia-proof-of-concept2 1