Instructions to use aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens with Transformers:

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

pipe = pipeline("text-generation", model="aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens")
model = AutoModelForCausalLM.from_pretrained("aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens

SGLang

How to use aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens 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 "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens" \
    --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": "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens",
		"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 "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens" \
        --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": "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens with Docker Model Runner:
```
docker model run hf.co/aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens
```

Qwen2.5-Coder-7B KernelBook SFT (equal tokens)

Supervised Fine-Tuning (SFT) checkpoint of Qwen/Qwen2.5-Coder-7B-Instruct, post-trained on the KernelBook Triton kernel dataset.

This repo is the equal-exposure SFT checkpoint (checkpoint-350, ~1.06 epochs) selected to match SDFT's one-epoch training for fair comparison.

Method

This model was trained with SFT using TRL's SFTTrainer: standard next-token prediction on chat-formatted prompt → Triton completion pairs, with completion-only loss (prompt tokens masked). Training used DeepSpeed ZeRO-3 and bf16 on Modal.

Dataset

KernelBook — PyTorch module prompts paired with reference Triton kernels
Deduplicated, filtered to completions ≤4096 tokens, repo-stratified 80/10/10 split
Stopped at checkpoint-350 (~1.06 epochs) for parity with the SDFT run

Intended use

Generate Triton GPU kernels from PyTorch-style module descriptions. Best for KernelBook-style conversion prompts; not evaluated as a general-purpose chat or reasoning model.

Quick start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True
)

messages = [
    {
        "role": "user",
        "content": "Convert the following PyTorch code to an equivalent Triton kernel...",
    }
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=1200, do_sample=False)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1] :], skip_special_tokens=True))

Training summary

Setting	Value
Base model	Qwen2.5-Coder-7B-Instruct
Method	SFT (TRL `SFTTrainer`, completion-only NLL)
Checkpoint	`checkpoint-350` (~1.06 epochs)
Hardware	4× H100 (Modal)
Parallelism	DeepSpeed ZeRO-3, bf16

Limitations

Specialized for KernelBook Triton codegen. May show reduced performance on general coding, math, and knowledge benchmarks compared to the base instruct model.

Downloads last month: 121

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Finetuned

(387)

this model