Instructions to use HawkonLi/Hunyuan-A52B-Instruct-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HawkonLi/Hunyuan-A52B-Instruct-2bit with Transformers:

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

pipe = pipeline("text-generation", model="HawkonLi/Hunyuan-A52B-Instruct-2bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HawkonLi/Hunyuan-A52B-Instruct-2bit", trust_remote_code=True, dtype="auto")

MLX

How to use HawkonLi/Hunyuan-A52B-Instruct-2bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("HawkonLi/Hunyuan-A52B-Instruct-2bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use HawkonLi/Hunyuan-A52B-Instruct-2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HawkonLi/Hunyuan-A52B-Instruct-2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HawkonLi/Hunyuan-A52B-Instruct-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HawkonLi/Hunyuan-A52B-Instruct-2bit

SGLang

How to use HawkonLi/Hunyuan-A52B-Instruct-2bit 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 "HawkonLi/Hunyuan-A52B-Instruct-2bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HawkonLi/Hunyuan-A52B-Instruct-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "HawkonLi/Hunyuan-A52B-Instruct-2bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HawkonLi/Hunyuan-A52B-Instruct-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

MLX LM

How to use HawkonLi/Hunyuan-A52B-Instruct-2bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "HawkonLi/Hunyuan-A52B-Instruct-2bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "HawkonLi/Hunyuan-A52B-Instruct-2bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "HawkonLi/Hunyuan-A52B-Instruct-2bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use HawkonLi/Hunyuan-A52B-Instruct-2bit with Docker Model Runner:
```
docker model run hf.co/HawkonLi/Hunyuan-A52B-Instruct-2bit
```

Hunyuan-A52B-Instruct-2bit / test4consistent.py

HawkonLi

Add files using upload-large-folder tool

0a69ebf verified over 1 year ago

raw

history blame contribute delete

1.31 kB

	# Copyright (C) 2024 THL A29 Limited, a Tencent company. All rights reserved.
	#
	# Licensed under the TENCENT HUNYUAN COMMUNITY LICENSE AGREEMENT (the "License");
	# you may not use this file except in compliance with the License.
	# You may obtain a copy of the License at
	#
	# https://github.com/Tencent/Tencent-Hunyuan-Large/blob/main/License.docx
	#
	# Unless required by applicable law or agreed to in writing, software
	# distributed under the License is distributed on an "AS IS" BASIS,
	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
	# See the License for the specific language governing permissions and
	# limitations under the License.
	# test tokenizer encode & decode consistency
	from transformers import AutoTokenizer
	tokenizer = AutoTokenizer.from_pretrained('/tokenizer_exp/other_tokenizer_vocab/hy', local_files_only=True, trust_remote_code=True)

	test_data = [line.strip() for line in open('/tokenizer_exp/data/test.txt', 'r').readlines()]

	num_origi_len = 0
	num_token_len = 0

	for d in test_data:
	a = tokenizer.encode(d)
	num_origi_len += len(d)
	num_token_len += len(a)
	b = tokenizer.decode(a)
	assert b == d, f"encode & decode not consistent: {d} vs {b}"

	print(f" original length: {num_origi_len}")
	print(f" token length: {num_token_len}")