GigaChat3-10B-A1.8B-bf16

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat3-10B-A1.8B-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)

messages = [
    {"role": "user", "content": "Докажи теорему о неподвижной точке"}
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_tensor.to(model.device), max_new_tokens=1000)

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ai-sage/GigaChat3-10B-A1.8B-bf16",
    "messages": [
      {
        "role": "user",
        "content": "Докажи теорему о неподвижной точке"
      }
    ],
    "max_tokens": 400,
    "temperature": 0
  }'

curl http://localhost:30000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ai-sage/GigaChat3-10B-A1.8B-bf16",
    "messages": [
      {
        "role": "user",
        "content": "Докажи теорему о неподвижной точке"
      }
    ],
    "max_tokens": 1000,
    "temperature": 0
  }'