Hugging Face's logo

radlab
/
pLLama-L31-adapters-MIX-SFT-DPO

Safetensors
llama
8-bit precision
bitsandbytes
Model card Files Community

Temp. description: https://radlab.dev/2024/12/08/pllama3-1-8b-czyli-srednio-duze-a-nawet-male-genai-dla-polskiego/

Downloads last month
11
Safetensors
Model size
8.03B params
Tensor type
F32
·
FP16
·
I8
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for radlab/pLLama-L31-adapters-MIX-SFT-DPO

Base model

meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct
Quantized
(370)
this model

Collection including radlab/pLLama-L31-adapters-MIX-SFT-DPO