"attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.0",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064

Use with transformers

Developed by: Tanwir
Language: Indonesia

Pastikan untuk memperbarui instalasi transformer Anda melalui pip install --upgrade transformer.

python

import torch
from transformers import pipeline

model_id = "kodetr/stunting-7B-Deepseek-R1"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "Jelaskan definisi 1000 hari pertama kehidupan."},
    {"role": "user", "content": "Apa itu 1000 hari pertama kehidupan?"},
]
outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])