Downloads · 30 days
24
44% of all-time downloads
ChatoyantAI/gemma-4-12b-it-lusy-sft-v4.0.1-step4300-lora
gemma-4-12b-it-lusy-sft-v4.0.1-step4300-lora is a text generation model from ChatoyantAI. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This is checkpoint-4300, epoch 1.27220948 (approximately 1.27 epochs) from the Lusy v4.0.1 training run. It is not the exact first-epoch checkpoint, not the completed two-epoch model, and not the older roleplay-only e…
Downloads · 30 days
24
44% of all-time downloads
All-time downloads
54
Public
Repo size
557 MB
Likes
0
Public
Click a slice to open those files.
.safetensors525 MB · 94%
From the Hugging Face model README
This is checkpoint-4300, epoch 1.27220948 (approximately 1.27 epochs)
from the Lusy v4.0.1 training run. It is not the exact first-epoch checkpoint,
not the completed two-epoch model, and not the older roleplay-only experiment.
These are adapter weights, not a standalone or merged model. The original
google/gemma-4-12B-it base is required.
Use a Transformers build supporting Gemma4UnifiedForConditionalGeneration
(training used Transformers5.10.2, PEFT0.18.1 and Unsloth2026.9.2).
import torch
from transformers import Gemma4UnifiedForConditionalGeneration, AutoTokenizer
from peft import PeftModel
adapter = "ChatoyantAI/gemma-4-12b-it-lusy-sft-v4.0.1-step4300-lora"
tokenizer = AutoTokenizer.from_pretrained(adapter)
base = Gemma4UnifiedForConditionalGeneration.from_pretrained(
"google/gemma-4-12B-it", dtype=torch.bfloat16, device_map="auto"
)
model = PeftModel.from_pretrained(base, adapter)
model.eval()
Use the included checkpoint chat template. When present, preserve the sequence
system -> assistant greeting -> user -> assistant history ... -> user.
65,536 is the training configuration, not a guarantee of long-context accuracy.
The adapter targets text; multimodal behavior has not been evaluated after SFT.
The dataset includes roleplay and mature themes. Outputs can be inaccurate, biased, inappropriate, or memorized and require review. No independent preference, safety, or general-capability benchmark improvement is claimed. Verification covers adapter tensor shape/finiteness, asset integrity and tokenizer-template loading; no new generation benchmark is included with this release.
release-manifest.json records hashes and provenance. Optimizer states, training
examples, credentials and raw logs are excluded. Apache2.0, following the base
model metadata; see LICENSE, NOTICE and BASE_MODEL_README.md. Not an official
Google release.