Instructions to use namelessai/TrillionHelp-7.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use namelessai/TrillionHelp-7.5b with Transformers:

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

pipe = pipeline("text-generation", model="namelessai/TrillionHelp-7.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("namelessai/TrillionHelp-7.5b")
model = AutoModelForCausalLM.from_pretrained("namelessai/TrillionHelp-7.5b")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use namelessai/TrillionHelp-7.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "namelessai/TrillionHelp-7.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "namelessai/TrillionHelp-7.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/namelessai/TrillionHelp-7.5b

SGLang

How to use namelessai/TrillionHelp-7.5b 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 "namelessai/TrillionHelp-7.5b" \
    --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": "namelessai/TrillionHelp-7.5b",
		"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 "namelessai/TrillionHelp-7.5b" \
        --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": "namelessai/TrillionHelp-7.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use namelessai/TrillionHelp-7.5b with Docker Model Runner:
```
docker model run hf.co/namelessai/TrillionHelp-7.5b
```

Interesting Project

by junep89 - opened Mar 31, 2025

Discussion

junep89

Mar 31, 2025

Hi,

I'm jason from the trillionlabs team, you are officially the first one to have done something like this on huggingface using our model.

I'd love to know more about the project you're working on, is it an English-based project ?

Thank you,
Jason

namelessai

Owner Apr 1, 2025

•

edited Apr 2, 2025

@junep89 It is currently an english based project, but I hope to expand to more languages once I can translate my datasets. This project aims to create efficient LLMs to assist psychological clinicians in diagnosing, treating, and helping their patients. It also aims to be used to create new treatments. Right now I'm 15, and operating on a zero dollar budget (which is why there currently isn't a demo). I love what you guys have created, and the Trillion model series is insane performance for their size class. I'm hoping to take advantage of that for finetuning. Right now your tokenizer is only supported via PEFT, but I hope Axolotl will come to support it soon!

Cheers,
Alex Scott

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