Instructions to use a-m-team/AM-Thinking-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use a-m-team/AM-Thinking-v1 with Transformers:

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

pipe = pipeline("text-generation", model="a-m-team/AM-Thinking-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("a-m-team/AM-Thinking-v1")
model = AutoModelForCausalLM.from_pretrained("a-m-team/AM-Thinking-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Local Apps Settings

vLLM

How to use a-m-team/AM-Thinking-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/a-m-team/AM-Thinking-v1

SGLang

How to use a-m-team/AM-Thinking-v1 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 "a-m-team/AM-Thinking-v1" \
    --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": "a-m-team/AM-Thinking-v1",
		"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 "a-m-team/AM-Thinking-v1" \
        --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": "a-m-team/AM-Thinking-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use a-m-team/AM-Thinking-v1 with Docker Model Runner:
```
docker model run hf.co/a-m-team/AM-Thinking-v1
```

Please add this model to HuggingChat

by devopsML - opened May 19, 2025

Discussion

devopsML

May 19, 2025

Hi there!

Would you mind adding this model to huggingchat, since we really want to try it but the openrouter version of it of this model tries to charge us a dime after using a limited free number of prompts ?

We would like to hear from your response!

BTW, if you mind adding this model to huggingchat, feel free to add it to the official github repository: https://github.com/huggingface/chat-ui

barius

am team org May 19, 2025

Glad to here you like the model :)
Currently we are planning to host a model API (e.g. by using a HF Space) in the future.
Or you could try the quantized model with ollama or llama.cpp, the Q4_K_M version runs on most devices with low memory footprint and moderate speed :)

devopsML

May 20, 2025

Hi there!

Would you mind adding this model to huggingchat, since we really want to try it but the openrouter version of it of this model tries to charge us a dime after using a limited free number of prompts ?

We would like to hear from your response!

BTW, if you mind adding this model to huggingchat, feel free to add it to the official github repository: https://github.com/huggingface/chat-ui

but since all of us want a unified space for all open-source LLMs in huggingchat, would you mind adding this model to huggingchat, since we don't have to download it locally (due to hardware requirements especially with computers with low-end hardware) or run on openrouter (requires a subscription to use unlimited prompts)? By adding to huggingchat you can save us a lot of time, resources and effort by just running it online, since most other LLMs in huggingchat already have community tools. Adding this model to huggingchat will grant your model access to all community tools on huggingchat.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment