Downloads · 30 days
3
16% of all-time downloads
gemma3-4b-content-ft-merged-8bit
rbarohit/gemma3-4b-content-ft-merged-8bit
gemma3-4b-content-ft-merged-8bit is a machine learning model from rbarohit. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Format: Transformers (PyTorch) merged 8-bit - Source: Fine-tuned with Unsloth; LoRA merged back into base - Intended use: Inference with transformers + bitsandbytes
All-time downloads
19
Public
Parameters
4.3B
8.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.6 GB · 100%
Parameter types
How the weights are stored.
F164.3B · 100%
Model card
From the Hugging Face model README
Gemma 3 4B — Content FT (Merged 8-bit)
- Format: Transformers (PyTorch) merged 8-bit
- Source: Fine-tuned with Unsloth; LoRA merged back into base
- Intended use: Inference with
transformers+bitsandbytes
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "rbarohit/gemma3-4b-content-ft-merged-8bit"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo,
device_map="auto",
torch_dtype=torch.float16,
load_in_8bit=True,
)
- Type
- gemma3
- Created
- Aug 25, 2025
- Updated
- Aug 25, 2025