Instructions to use muhtasham/TowerInstruct-7B-v0.1-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use muhtasham/TowerInstruct-7B-v0.1-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="muhtasham/TowerInstruct-7B-v0.1-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("muhtasham/TowerInstruct-7B-v0.1-FP8")
model = AutoModelForCausalLM.from_pretrained("muhtasham/TowerInstruct-7B-v0.1-FP8")
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 muhtasham/TowerInstruct-7B-v0.1-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "muhtasham/TowerInstruct-7B-v0.1-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "muhtasham/TowerInstruct-7B-v0.1-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/muhtasham/TowerInstruct-7B-v0.1-FP8

SGLang

How to use muhtasham/TowerInstruct-7B-v0.1-FP8 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 "muhtasham/TowerInstruct-7B-v0.1-FP8" \
    --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": "muhtasham/TowerInstruct-7B-v0.1-FP8",
		"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 "muhtasham/TowerInstruct-7B-v0.1-FP8" \
        --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": "muhtasham/TowerInstruct-7B-v0.1-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use muhtasham/TowerInstruct-7B-v0.1-FP8 with Docker Model Runner:
```
docker model run hf.co/muhtasham/TowerInstruct-7B-v0.1-FP8
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

git clone https://github.com/neuralmagic/AutoFP8.git
pip install -e AutoFP8

from transformers import AutoTokenizer
from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
from datasets import load_dataset

pretrained_model_dir = "Unbabel/TowerInstruct-7B-v0.1"
quantized_model_dir = "TowerInstruct-7B-v0.1-FP8"

tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
tokenizer.pad_token = tokenizer.eos_token

ds = load_dataset("mgoin/ultrachat_2k", split="train_sft").select(range(512))
examples = [tokenizer.apply_chat_template(batch["messages"], tokenize=False) for batch in ds]
examples = tokenizer(examples, padding=True, truncation=True, return_tensors="pt").to("cuda")

quantize_config = BaseQuantizeConfig(quant_method="fp8", activation_scheme="static")


model = AutoFP8ForCausalLM.from_pretrained(
    pretrained_model_dir, quantize_config=quantize_config
)
model.quantize(examples)
model.save_quantized(quantized_model_dir)

Downloads last month: 15

Safetensors

Model size

7B params

Tensor type

F32

F8_E4M3

Collection including muhtasham/TowerInstruct-7B-v0.1-FP8

Tower Models

Collection

4 items • Updated Aug 27, 2024