Gemma 9B Pretrained Translation Models
Collection
This is a collection of models that are fine-tuned for translation, based on the pretrained Gemma 9B model.
•
5 items
•
Updated
LoRA Adapters
This repository contains the LoRA adapters used for fine-tuning.
Details
- Base Model: Bronsn/gemma-9b-luganda-pretrained
- Contains LoRA adapter weights
- Compatible with PEFT library
Configuration
peft_config = LoraConfig(
r=128,
target_modules=["q_proj", "k_proj", "v_proj", "o_proj",
"gate_proj", "up_proj", "down_proj",
"embed_tokens", "lm_head"],
lora_alpha=32,
bias="none",
)
- Downloads last month
- 11
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 HF Inference API does not support translation models for peft library.
Model tree for Bronsn/luganda-english-translation-lora
Base model
google/gemma-2-9b
Quantized
unsloth/gemma-2-9b-bnb-4bit