GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
nelsondiasandre
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
nelsondiasandre
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from peft import AutoPeftModelForCausalLMfrom transformers import AutoTokenizermodel = AutoPeftModelForCausalLM.from_pretrained("nelsondiasandre/qwen25-1.5b-pt-qa-lora")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")def perguntar(pergunta: str) -> str:prompt = f"<|im_start|>user\n{pergunta}<|im_end|>\n<|im_start|>assistant\n"inputs = tokenizer(prompt, return_tensors="pt")outputs = model.generate(**inputs,max_new_tokens=100,do_sample=True,temperature=0.7,repetition_penalty=1.3,pad_token_id=tokenizer.eos_token_id,)resposta = tokenizer.decode(outputs[0], skip_special_tokens=False)resposta = resposta.split("<|im_start|>assistant\n")[-1].split("<|im_end|>")[0].strip()return respostaprint(perguntar("Qual e a capital de Portugal?"))
This model uses the Qwen ChatML format:
markdown
<|im_start|>user{pergunta}<|im_end|><|im_start|>assistant{resposta}<|im_end|>
Do not use Qwen's native apply_chat_template() — it produces a slightly different format than what this adapter was trained on. Use the prompt string directly as shown above.
| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen2.5-1.5B-Instruct |
| LoRA rank (r) | 8 |
| LoRA alpha | 16 |
| LoRA dropout | 0.05 |
| Target modules | q_proj, k_proj, v_proj, o_proj |
| Epochs | 20 |
| Learning rate | 2e-4 |
| LR scheduler | cosine |
| Warmup ratio | 0.1 |
| Batch size | 2 (effective 8 with grad accum 4) |
| Max sequence length | 512 tokens |
| Training hardware | CPU |
| Training dataset | 500 PT-PT instruction pairs (400 train / 100 eval) |
500 Portuguese (PT-PT) question-answer pairs across 20+ categories:
See the dataset card for details.
| Metric | Value |
|---|---|
| Eval loss (final epoch) | 0.6199 |
| Perplexity (eval set) | 1.86 |
Apache 2.0 (inherited from Qwen2.5-1.5B-Instruct base model).