GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Yhyu13
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Yhyu13
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
| Item | Value |
|---|---|
| Base model | Qwen/Qwen3.5-4B |
| PEFT type | LoRA (rank 16, α 32, dropout 0.05) |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Task | CAUSAL_LM (tool-call text generation) |
| Training data | data/splits/train.jsonl of Yhyu13/UE5_Training_MCP (a small UE5 corpus bundled with the training repo; not published as a separate HF dataset) (108 examples) |
| Eval data | data/splits/val.jsonl (13 examples) |
| Max seq length | 512 |
| Epochs | 3 |
| Effective batch size | 8 (per_device 4 × grad_accum 2) |
| Learning rate | 3e-4 |
| Wall-clock training | 592.3s on 1×CUDA 12.1 |
| Train framework | PEFT 0.19.1 · Transformers 5.14.1 · TRL 0.26.2 · Torch 2.5.1+cu121 |
| Adapter size | 81.0 MB (adapter_model.safetensors) |
| Eval loss (val) | 0.5216 |
Requires peft + transformers. From the base model + adapter:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelBASE = "Qwen/Qwen3.5-4B"ADAPTER = "Yhyu13/Qwen3.5-4B-UE5-LoRA"tok = AutoTokenizer.from_pretrained(BASE, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)model = PeftModel.from_pretrained(model, ADAPTER)model.eval()# See Yhyu13/UE5_Training_MCP/eval/benchmark_questions.jsonl for prompt format.prompt = open("eval/example_prompt.txt").read()inputs = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=256, do_sample=False)print(tok.decode(out[0], skip_special_tokens=True))
Or, with the bundled chat template baked in:
python
ADAPTER = "Yhyu13/Qwen3.5-4B-UE5-LoRA"tok = AutoTokenizer.from_pretrained(ADAPTER, trust_remote_code=True)print(tok.chat_template[:200], "...") # matches the adapter's training chat template
Reproduce with the scripts in Yhyu13/UE5_Training_MCP:
bash
git clone https://huggingface.co/Yhyu13/UE5_Training_MCPcd UE5_Training_MCPpython -m venv .venv && . .venv/bin/activatepip install -r requirements.txtpython scripts/train_qwen35.py \--base_model Qwen/Qwen3.5-4B \--train data/splits/train.jsonl \--val data/splits/val.jsonl \--out outputs/models/qwen3.5-4b-ue5-lora
Hyperparameters come from train_meta.json (bundled in this repo).
final_eval.json records the validation loss after the third epoch. The full
side-by-side benchmark (base vs. fine-tuned, tool-call exact-match rate, JSON
schema conformance, and lm_eval results) lives in
Yhyu13/UE5_Training_MCP/outputs/results/.
cmd_*), Blueprint→Python
(py_*), and the introspection tools declared in the bundled
config/mcp_config.json.Apache-2.0 — same as the base Qwen3.5 model.