yqnis/llama3-8b-quaero-gguf

LLaMA 3 8B fine-tuned on Quaero for Named Entity Recognition (Generative)

This is a Quantized version (Q5_K_M) of yqnis/llama3-8b-quaero, a model fine-tuned on the Quaero French medical dataset using a generative approach to Named Entity Recognition (NER).

Other formats

This model is also available in the following formats:

• 16-bit
  → yqnis/llama3-8b-quaero

• LoRA Q8_0
  → yqnis/llama3-8b-quaero-lora

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