Instructions to use stockmark/Stockmark-2-100B-Instruct-beta-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stockmark/Stockmark-2-100B-Instruct-beta-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="stockmark/Stockmark-2-100B-Instruct-beta-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stockmark/Stockmark-2-100B-Instruct-beta-AWQ")
model = AutoModelForCausalLM.from_pretrained("stockmark/Stockmark-2-100B-Instruct-beta-AWQ")
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 stockmark/Stockmark-2-100B-Instruct-beta-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stockmark/Stockmark-2-100B-Instruct-beta-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stockmark/Stockmark-2-100B-Instruct-beta-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stockmark/Stockmark-2-100B-Instruct-beta-AWQ

SGLang

How to use stockmark/Stockmark-2-100B-Instruct-beta-AWQ 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 "stockmark/Stockmark-2-100B-Instruct-beta-AWQ" \
    --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": "stockmark/Stockmark-2-100B-Instruct-beta-AWQ",
		"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 "stockmark/Stockmark-2-100B-Instruct-beta-AWQ" \
        --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": "stockmark/Stockmark-2-100B-Instruct-beta-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stockmark/Stockmark-2-100B-Instruct-beta-AWQ with Docker Model Runner:
```
docker model run hf.co/stockmark/Stockmark-2-100B-Instruct-beta-AWQ
```

Stockmark-2-100B-Instruct-beta-AWQ / scripts /quantize_autoawq.py

omitakahiro

Rename quantize_autoawq.py to scripts/quantize_autoawq.py

f952bd2 verified about 1 year ago

raw

history blame contribute delete

922 Bytes

	import random

	import pandas as pd
	from awq import AutoAWQForCausalLM
	from transformers import AutoTokenizer

	model_path = 'stockmark/Stockmark-2-100B-Instruct-beta'
	quant_path = 'Stockmark-2-100B-Instruct-beta-AWQ'

	quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }

	# Load model
	model = AutoAWQForCausalLM.from_pretrained(model_path)
	tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

	# load dataset
	ds = pd.read_json("caliblation.jsonl", lines=True).to_dict("records")
	ds = [ tokenizer.apply_chat_template(doc["messages"], tokenize=False) for doc in ds ]
	random.shuffle(ds)

	# Quantize
	model.quantize(
	tokenizer,
	quant_config=quant_config,
	calib_data=ds,
	n_parallel_calib_samples=64,
	max_calib_samples=128,
	max_calib_seq_len=1024
	)

	# Save quantized model
	model.save_quantized(quant_path)
	tokenizer.save_pretrained(quant_path)