Instructions to use rfvasile/LinalgZero-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rfvasile/LinalgZero-SFT with Transformers:

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

pipe = pipeline("text-generation", model="rfvasile/LinalgZero-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rfvasile/LinalgZero-SFT")
model = AutoModelForCausalLM.from_pretrained("rfvasile/LinalgZero-SFT", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rfvasile/LinalgZero-SFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rfvasile/LinalgZero-SFT

SGLang

How to use rfvasile/LinalgZero-SFT 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 "rfvasile/LinalgZero-SFT" \
    --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": "rfvasile/LinalgZero-SFT",
		"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 "rfvasile/LinalgZero-SFT" \
        --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": "rfvasile/LinalgZero-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use rfvasile/LinalgZero-SFT with Docker Model Runner:
```
docker model run hf.co/rfvasile/LinalgZero-SFT
```

LinalgZero-SFT / README.md

Razvan Vasile

Update README.md

b5ebf3a verified 7 months ago

preview code

Raw

History Blame Contribute Delete

1.46 kB

metadata

datasets: atomwalk12/linalgzero-sft
library_name: transformers
model_name: atomwalk12/LinalgZero-SFT-LoRA
tags:
  - generated_from_trainer
  - linear-algebra
  - unsloth
  - linalg-zero
  - trl
  - tool-use
  - sft
licence: license

Model Card for LinalgZero-SFT

The training code is available on Github.

This model is a fine-tuned version of atomwalk12/LinalgZero-SFT-LoRA on the atomwalk12/linalgzero-sft dataset. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="atomwalk12/LinalgZero-SFT", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.20.0
Transformers: 4.56.2
Pytorch: 2.7.1
Datasets: 4.4.1
Tokenizers: 0.22.1