Instructions to use josephl04/ece6514-p1-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use josephl04/ece6514-p1-random with Transformers:

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

pipe = pipeline("text-generation", model="josephl04/ece6514-p1-random")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("josephl04/ece6514-p1-random")
model = AutoModelForCausalLM.from_pretrained("josephl04/ece6514-p1-random", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use josephl04/ece6514-p1-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "josephl04/ece6514-p1-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "josephl04/ece6514-p1-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/josephl04/ece6514-p1-random

SGLang

How to use josephl04/ece6514-p1-random 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 "josephl04/ece6514-p1-random" \
    --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": "josephl04/ece6514-p1-random",
		"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 "josephl04/ece6514-p1-random" \
        --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": "josephl04/ece6514-p1-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use josephl04/ece6514-p1-random with Docker Model Runner:
```
docker model run hf.co/josephl04/ece6514-p1-random
```

josephl04/ece6514-p1-random

Qwen2.5-3B-Instruct, full-parameter SFT on josephl04/ece6514-p1-random-15k: 15K samples selected from redsgnaoh/acereason11_100k, for ECE 6514 Project 1. LLaMA-Factory, 3 epochs, lr 5e-6 cosine, global batch 8, cutoff_len 16384. Code, data selection and evaluation: https://github.com/kiarak425/TML-Group1

Evaluate with the system prompt "Please reason step by step, and put your final answer within \boxed{}."

Downloads last month: 20

Safetensors

Model size

242k params

Tensor type

BF16

Model tree for josephl04/ece6514-p1-random

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(1663)

this model

josephl04
/

ece6514-p1-random

josephl04/ece6514-p1-random

Model tree for josephl04/ece6514-p1-random

Dataset used to train josephl04/ece6514-p1-random