julienp79/ occitan-gemma-4-e2b-it-lora-sfttrainer

40 3 months ago

Gemma 4 2B fine-tuned on Occitan via standard LoRA (r=16) with SFTTrainer. Q2_K, Q4_K_M, Q5_K_M, Q8_0, f16 quants available.

6 models

occitan-gemma-4-e2b-it-lora-sfttrainer:latest
07f0dc958bec • 3.4GB • 128K context window •
Text input • 3 months ago
occitan-gemma-4-e2b-it-lora-sfttrainer:Q2_K
b4b5d9261ab6 • 3.0GB • 128K context window •
Text input • 3 months ago
occitan-gemma-4-e2b-it-lora-sfttrainer:Q4_K_M
449cf35f4b20 • 3.4GB • 128K context window •
Text input • 3 months ago
occitan-gemma-4-e2b-it-lora-sfttrainer:Q5_K_M
466ab79f7052 • 3.6GB • 128K context window •
Text input • 3 months ago
occitan-gemma-4-e2b-it-lora-sfttrainer:Q8_0
7c70e4b15b6a • 5.0GB • 128K context window •
Text input • 3 months ago
occitan-gemma-4-e2b-it-lora-sfttrainer:f16
db8c7dffc5dd • 9.3GB • 128K context window •
Text input • 3 months ago