GigaChat-20B-A3B-instruct-v1.5-bf16

281
6
2 languages
license:mit
by
ai-sage
Code Model
OTHER
20B params
New
281 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
45GB+ RAM
Mobile
Laptop
Server
Quick Summary

Диалоговая модель из семейства моделей GigaChat, основная на ai-sage/GigaChat-20B-A3B-instruct-v1.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
19GB+ RAM

Code Examples

Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=False)
print(result)
Пример использования через transformerspythontransformers
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ai-sage/GigaChat-20B-A3B-instruct-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
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))

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

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.