GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
balaguhanesh
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
balaguhanesh
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Base vs. this adapter on 300 held-out examples (greedy decoding, strict exact-match grader):
| Metric | Base | Fine-tuned | Δ |
|---|---|---|---|
| JSON-valid rate | 51.7% | 100.0% | +48.3 |
| Function-name accuracy | 1.0% | 100.0% | +99.0 |
| Argument match (exact) | 0.3% | 95.0% | +94.7 |
The grader is strict: unparseable output fails all three axes, function name is
exact/case-sensitive, and arguments require exact dict equality ("5" != 5, any
extra/missing key fails the row). Fine-tuning here teaches format compliance and
schema discipline, not reasoning.
bitsandbytes), LoRA via peft
(r=16, α=32, all attention + MLP projections; ~30M trainable params, 0.96%)trl.SFTTrainer (supervised fine-tuning)glaiveai/glaive-function-calling-v2 → 2000 train / 300 evalpython
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "Qwen/Qwen2.5-3B-Instruct"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")model = PeftModel.from_pretrained(model, "Balaguhanesh/tool-call-ft")messages = [{"role": "system", "content": "You are a helpful assistant with access to the following functions. Use them if required -\n{...function schema...}"},{"role": "user", "content": "What's the weather in Paris?"},]inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)out = model.generate(**inputs, max_new_tokens=128, do_sample=False)print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))