L3-8B-Helium3-GGUF / README.md
Reiterate3680's picture
Create README.md
2a0c804 verified
|
raw
history blame
397 Bytes
metadata
base_model: inflatebot/L3-8B-Helium3
language:
  - en
license: other
pipeline_tag: text-generation
quantized_by: Reiterate3680

Original Model: https://huggingface.co/inflatebot/L3-8B-Helium3

made with https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script

Models Q2_K_L, Q4_K_L, Q5_K_L, Q6_K_L, are using Q_8 output tensors and token embeddings

using bartowski's imatrix dataset