GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
fiel1986
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
fiel1986
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen2.5-3B-InstructQwen/Qwen2.5-0.5B-InstructL = α · KL(teacher || student) + (1-α) · CE(labels)| Métrica | 0.5B original | 3B (teacher) | Andromeda-0.5B-destilada |
|---|---|---|---|
| Peso en disco | 1.0 GB | 5.8 GB | 1.0 GB |
| RAM mínima | 2 GB | 6 GB | 2 GB |
| Latencia promedio | ~180 ms | ~620 ms | ~210 ms |
| BLEU ES | 28.4 | 38.7 | 34.2 |
| Exact Match | 52.1% | 68.9% | 61.4% |
| Fluidez (1-10) |
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "tu-usuario/Andromeda-0.5B-destilada"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") messages = [{"role": "user", "content": "Hola, ¿cómo estás?"}]inputs = tok.apply_chat_template(messages, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=128, do_sample=True, temperature=0.7)print(tok.decode(out[0], skip_special_tokens=True)) ⚙️ Detalles técnicosArquitectura: idéntica a Qwen2.5-0.5B-Instruct (misma capa, mismo head)Tokenizer: sin cambios (compatibilidad total con el chat template de Qwen)Contexto: 32k tokens (heredado de la familia Qwen2.5)Formato pesos: safetensors (fp16 / bf16) ⚠️ LimitacionesModelo pequeño: puede fallar en razonamiento multi-paso complejoConocimiento factual acotado al corte del dataset de entrenamiento baseNo reemplaza al 3B en tareas de alta precisión; es un trade-off velocidad/recursos| 6.2 |
| 8.1 |
| 7.3 |
| Coherencia | 58.3% | 74.5% | 67.8% |