Instructions to use ailabykt/aLabAI-20B-A3B-instruct-1301-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ailabykt/aLabAI-20B-A3B-instruct-1301-bf16 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ailabykt/aLabAI-20B-A3B-instruct-1301-bf16", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ailabykt/aLabAI-20B-A3B-instruct-1301-bf16", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ailabykt/aLabAI-20B-A3B-instruct-1301-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ailabykt/aLabAI-20B-A3B-instruct-1301-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ailabykt/aLabAI-20B-A3B-instruct-1301-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ailabykt/aLabAI-20B-A3B-instruct-1301-bf16

SGLang

How to use ailabykt/aLabAI-20B-A3B-instruct-1301-bf16 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ailabykt/aLabAI-20B-A3B-instruct-1301-bf16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ailabykt/aLabAI-20B-A3B-instruct-1301-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ailabykt/aLabAI-20B-A3B-instruct-1301-bf16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ailabykt/aLabAI-20B-A3B-instruct-1301-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ailabykt/aLabAI-20B-A3B-instruct-1301-bf16 with Docker Model Runner:
```
docker model run hf.co/ailabykt/aLabAI-20B-A3B-instruct-1301-bf16
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

aLabAI-20B-A3B-instruct-1301-bf16

Диалоговая модель с поддержкой якутского языка, основанная на GigaChat-20B-A3B-instruct.

Requirements

transformers>=4.47

Пример использования через transformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "ailabykt/aLabAI-20B-A3B-instruct-1301-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)

messages = [
    {"role": "user", "content": "Саха сирин туһунан кэпсээ"}
]
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)

В aLabAI-20B-A3B-instruct-1301-bf16, как и в оригинальной модели, используется особый способ токенизации текста, поэтому не рекомендуется следующий сценарий

input_string = tokenizer.apply_chat_template(messages,tokenize=False, add_generation_prompt=True)
input_tensor = tokenizer(input_string, return_tensors="pt")

Downloads last month: -

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for ailabykt/aLabAI-20B-A3B-instruct-1301-bf16

Base model

ai-sage/GigaChat-20B-A3B-base

Finetuned

ai-sage/GigaChat-20B-A3B-instruct

Finetuned

(2)

this model

ailabykt
/

aLabAI-20B-A3B-instruct-1301-bf16

You need to agree to share your contact information to access this model

aLabAI-20B-A3B-instruct-1301-bf16

Requirements

Пример использования через transformers

Model tree for ailabykt/aLabAI-20B-A3B-instruct-1301-bf16

Datasets used to train ailabykt/aLabAI-20B-A3B-instruct-1301-bf16