Downloads · 30 days
10
7% of all-time downloads
EnergyAI/qwen3.5-27b-agrpo-nothink-lr3e-6-checkpoint400
qwen3.5-27b-agrpo-nothink-lr3e-6-checkpoint400 is a machine learning model from EnergyAI. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Qwen3.5-27B fine-tuned with Async GRPO (no thinking, nothink mode) — checkpoint at step 400
Downloads · 30 days
10
7% of all-time downloads
All-time downloads
137
Public
Parameters
26.9B
53.8 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors53.8 GB · 100%
From the Hugging Face model README
Qwen3.5-27B fine-tuned with Async GRPO (no thinking, nothink mode) — checkpoint at step 400
Fill-in-the-middle multiple-choice questions (MCQ) for energy domain verification.
The model outputs its answer inside \boxed{N} where N is the option number.
\boxed{N} matches ground truth)\boxed{N} exists but wrong answer)\boxed{} found)| Parameter | Value |
|---|---|
| base_model | Qwen/Qwen3.5-27B |
| algorithm | Async GRPO (TRL AsyncGRPOTrainer) |
| thinking | disabled (nothink) |
| learning_rate | 3e-6 |
| lr_scheduler | cosine |
| warmup_steps | 30 |
| max_steps | 2000 |
| global_step_saved | 400 |
| per_device_train_batch_size | 2 |
| gradient_accumulation_steps | 32 |
| num_train_processes | 8 |
| effective_batch_size | 512 prompts/step |
| num_generations | 5 |
| max_completion_length | 512 |
| temperature | 1.0 |
| epsilon | 0.2 |
| epsilon_high | 0.2 |
| max_staleness | 4 |
| weight_sync_steps | 3 |
| max_grad_norm | 1.0 |
| precision | bf16 |
| parallelism | FSDP2 (8 GPUs training, 1 node) + vLLM TP=8 (8 GPUs inference, 1 node) — 2 nodes total |
| final_reward | ~0.52 (at step 400) |
| final_mean_completion_length | ~190 tokens |
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("EnergyAI/qwen3.5-27b-agrpo-nothink-lr3e-6-checkpoint400", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("EnergyAI/qwen3.5-27b-agrpo-nothink-lr3e-6-checkpoint400")