Instructions to use abacusai/TheProfessor-155b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacusai/TheProfessor-155b with Transformers:

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

pipe = pipeline("text-generation", model="abacusai/TheProfessor-155b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abacusai/TheProfessor-155b")
model = AutoModelForCausalLM.from_pretrained("abacusai/TheProfessor-155b")
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

vLLM

How to use abacusai/TheProfessor-155b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abacusai/TheProfessor-155b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacusai/TheProfessor-155b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abacusai/TheProfessor-155b

SGLang

How to use abacusai/TheProfessor-155b 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 "abacusai/TheProfessor-155b" \
    --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": "abacusai/TheProfessor-155b",
		"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 "abacusai/TheProfessor-155b" \
        --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": "abacusai/TheProfessor-155b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abacusai/TheProfessor-155b with Docker Model Runner:
```
docker model run hf.co/abacusai/TheProfessor-155b
```

Quantized versions for mare mortals?

by LeaveNhA - opened Feb 11, 2024

Discussion

LeaveNhA

Feb 11, 2024

@TheBloke I know you are bussy, but this would be very nice.

Thanks.

MaziyarPanahi

Feb 12, 2024

•

edited Feb 12, 2024

I started the AWQ, maybe then GPTQ. Not sure if my 4 A100 is enough, ~~but I am interested into doing a GGUF~~ (it's already here: abacusai/TheProfessor-155b-gguf)

ehartford

Feb 12, 2024

https://huggingface.co/abacusai/TheProfessor-155b-gguf

ek826

Feb 13, 2024

exl2 quant here, https://huggingface.co/ek826/TheProfessor-155b-2.4bpw-exl2

ehartford

Feb 13, 2024

exl2 quant here, https://huggingface.co/ek826/TheProfessor-155b-2.4bpw-exl2

Any possible to get it under 48gb? Would love to get it into dual-3090

ek826

Feb 13, 2024

Sure will do a 2.2 or 2.0 bpw and test on a dual 24gb vram setup

ek826

Feb 14, 2024

2.21 bpw exl2 quants, exactly fits in a dual-4090 setup w/4k context, runs at 17.96 tokens/sec
https://huggingface.co/ek826/TheProfessor-155b-2.21bpw-exl2

ehartford

Feb 14, 2024

Awesome thank you!!

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