Instructions to use mehta/CooperLM-354M-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mehta/CooperLM-354M-4bit with Transformers:

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

pipe = pipeline("text-generation", model="mehta/CooperLM-354M-4bit")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mehta/CooperLM-354M-4bit")
model = AutoModelForCausalLM.from_pretrained("mehta/CooperLM-354M-4bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mehta/CooperLM-354M-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mehta/CooperLM-354M-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mehta/CooperLM-354M-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mehta/CooperLM-354M-4bit

SGLang

How to use mehta/CooperLM-354M-4bit 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 "mehta/CooperLM-354M-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mehta/CooperLM-354M-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "mehta/CooperLM-354M-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mehta/CooperLM-354M-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mehta/CooperLM-354M-4bit with Docker Model Runner:
```
docker model run hf.co/mehta/CooperLM-354M-4bit
```

🧠 CooperLM-354M (4-bit Quantized)

This is a 4-bit quantized version of CooperLM-354M, a 354M parameter GPT-2 style language model trained from scratch on a subset of Wikipedia, BookCorpus, and OpenWebText.

The quantized model is intended for faster inference and smaller memory footprint, especially useful for CPU or limited-GPU setups.

📌 Model Details

Base Model: mehta/CooperLM-354M
Architecture: GPT-2 (24 layers, 16 heads, 1024 hidden size)
Quantization: 4-bit integer weights via AutoGPTQ (safetensors)
Precision: INT4

🛠️ How to Use

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("mehta/CooperLM-354M-4bit")
model = AutoModelForCausalLM.from_pretrained("mehta/CooperLM-354M-4bit")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

prompt = "In the distant future,"
inputs = tokenizer(prompt, return_tensors="pt").to(device)

outputs = model.generate(
    **inputs,
    max_length=100,
    temperature=0.8,
    top_p=0.95,
    do_sample=True
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 10

Safetensors

Model size

0.4B params

Tensor type

F32

F16

Model tree for mehta/CooperLM-354M-4bit

Base model

openai-community/gpt2

Finetuned

mehta/CooperLM-354M

Quantized

(2)

this model