Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bioreasoning-qwen3-32b-sft-20260228-ckpt-final – AI Model by abugoot-primeintellect | AlphaNeural AI
You can deploy this model and start earning money today!
abugoot-primeintellect
/
bioreasoning-qwen3-32b-sft-20260228-ckpt-final
like
0
peft
safetensors
bioreasoning
sft
lora
tinker
Qwen/Qwen3-32B
adapter
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
bioreasoning-qwen3-32b-sft-20260228-ckpt-final
LoRA adapter checkpoint from supervised fine-tuning on the
bioreasoning dataset
.
Training Details
Base model:
Qwen/Qwen3-32B
Method:
LoRA (rank 32)
Training platform:
Tinker
(ThinkingMachines)
Dataset:
abugoot-primeintellect/bioreasoning_v0211_prime_sft (~193k train examples)
Hyperparameters:
batch_size=128, lr=2e-5 (linear decay), weight_decay=0.01, seq_len=8192
Epochs:
3
Checkpoint:
step final (epoch 3, batch 1511)
Loss masking:
Last assistant message only
All Checkpoints
Step
Epoch
HF Repo
1500
~1
bioreasoning-qwen3-32b-sft-20260228-ckpt-1500
3000
~2
bioreasoning-qwen3-32b-sft-20260228-ckpt-3000
final
3
bioreasoning-qwen3-32b-sft-20260228-ckpt-final
