Hugging Face's logo

shuyuej
/
c4ai-command-r-plus-08-2024-GPTQ

Safetensors
cohere
4-bit precision
gptq
Model card Files Community
Edit model card

The Quantized c4ai-command-r-plus-08-2024 Model

Original Base Model: CohereForAI/c4ai-command-r-plus-08-2024.
Link: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024

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
3
Safetensors
Model size
19.8B params
Tensor type
BF16
·
I32
·
FP16
·
Inference API
Unable to determine this model's library. Check the docs .

Collection including shuyuej/c4ai-command-r-plus-08-2024-GPTQ