Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen3.5-4b-zeta-gguf – AI Model by wasfox | AlphaNeural AI
You can deploy this model and start earning money today!
wasfox
/
qwen3.5-4b-zeta-gguf
like
0
gguf
code
unsloth
zed-industries/zeta
unsloth/Qwen3.5-4B
quantized
apache-2.0
endpoints_compatible
us
conversational
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen3.5-4B Zeta GGUF
Fine-tuned Qwen3.5-4B for inline code editing using the
Zeta dataset
.
SFT: 60 steps, rank 256, batch 8
DPO: 1 epoch, rank 32, batch 4
Notebooks used:
SFT
DPO
Base mode:
model-f16
-- raw fine-tuned 3.5-4B (~8.42GB)
Quantizations:
q8_0/
-- near-lossless (~4.48GB)
q4_k_m/
-- balanced quality/size (~2.71GB)
Credits to
Zeta
and
Zed Team
.
