GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
issdandavis
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
issdandavis
Model Tree
Qwen/Qwen2.5-0.5B
Input Modalities
Output Modalities
Supported Functionality
q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj)Qwen/Qwen2.5-0.5Bissdandavis/polly-training-dataTrained on Kaggle for 435 steps (3 epochs, effective batch size 16) with cosine LR schedule peaking at 2e-4. Run took ~185 minutes.
| Metric | Start | End | Delta |
|---|---|---|---|
| Loss | 3.826 | 1.823 | -2.003 |
| Token accuracy | 36.82% | 67.05% | +30.23pp |
| Entropy | 3.65 | 1.76 | -1.89 |
| Grad norm (max over run) | — | 1.672 | stable |
Loss dropped smoothly without spikes. Gradients stayed under 1.7 throughout — no instability. Final learning rate landed at ~1e-7, meaning the cosine schedule completed cleanly. Entropy dropped alongside loss, which means the model became confidently trained rather than collapsing to a single mode.
Full training report: artifacts/training_reports/polly-1_2026-04-21.json in the SCBE-AETHERMOORE repo.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerimport torchbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B",torch_dtype=torch.bfloat16,device_map="auto",)model = PeftModel.from_pretrained(base, "issdandavis/polly-1")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B")messages = [{"role": "user", "content": "Explain Sacred Tongues in one sentence."}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)out = model.generate(inputs, max_new_tokens=160, do_sample=True, temperature=0.7)print(tokenizer.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
yaml
base_model: Qwen/Qwen2.5-0.5Bpeft: LoRA (r=16, alpha=32, dropout=0.05, bias=none)target_modules: [q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj]num_train_epochs: 3per_device_train_batch_size: 4gradient_accumulation_steps: 4effective_batch_size: 16learning_rate: 2e-4lr_scheduler: cosinewarmup_ratio: 0.03max_length: 1024bf16: trueseed: 42
polly-1 is the 0.5B-scale companion adapter in the SCBE-AETHERMOORE project — an AI safety and governance framework built on hyperbolic geometry (Poincare ball model) with a 14-layer security pipeline and six Sacred Tongues (KO, AV, RU, CA, UM, DR) weighted by the golden ratio. See the main repository for architectural details.
Larger siblings in the same family (7B variants, fleet adapters) are separate repos under issdandavis/*.
Apache-2.0. Base model license (Qwen2.5-0.5B) applies to merged weights.
bibtex
@software{davis2026polly1,title = {polly-1: Sacred Tongues LoRA on Qwen2.5-0.5B},author = {Davis, Issac Izreal},year = {2026},url = {https://huggingface.co/issdandavis/polly-1}}