Instructions to use likhithv/meta-sdk-baseline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use likhithv/meta-sdk-baseline with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B")
model = PeftModel.from_pretrained(base_model, "likhithv/meta-sdk-baseline")

Transformers

How to use likhithv/meta-sdk-baseline with Transformers:

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

pipe = pipeline("text-generation", model="likhithv/meta-sdk-baseline")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("likhithv/meta-sdk-baseline", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use likhithv/meta-sdk-baseline with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/likhithv/meta-sdk-baseline

SGLang

How to use likhithv/meta-sdk-baseline 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 "likhithv/meta-sdk-baseline" \
    --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": "likhithv/meta-sdk-baseline",
		"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 "likhithv/meta-sdk-baseline" \
        --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": "likhithv/meta-sdk-baseline",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use likhithv/meta-sdk-baseline with Docker Model Runner:
```
docker model run hf.co/likhithv/meta-sdk-baseline
```

Meta SDK Baseline — LoRA Adapter

LoRA adapter for Qwen/Qwen3.5-4B fine-tuned on 1,209 chunk-based training samples generated by Meta's Synthetic Data Kit from the same financial and medical source documents.

This is the Meta SDK baseline model from the paper "Knowledge Graph-Guided Fine-Tuning Data Generation: A Rigorous Benchmark" — the industry-standard chunk-based approach used as the comparison point against KnowledgeMesh.

Benchmark Results

Evaluated by Gemini 2.5 Flash pointwise judge (1–5 scale, 4 dimensions):

Eval Set	Base	This Model	KM Full	Delta (KM − this)
Primary (n=473, KM-generated)	1.79	1.93	2.47	+0.54
Independent (n=955, Gemini-generated)	1.96	2.17	2.90	+0.72

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base_model_id = "Qwen/Qwen3.5-4B"
adapter_id = "likhithv/meta-sdk-baseline"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)

messages = [{"role": "user", "content": "What were Apple's total net sales in 2023?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs.to(model.device), max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))

Training Details

Parameter	Value
Base model	Qwen/Qwen3.5-4B (4-bit quantized via bitsandbytes)
Fine-tuning method	LoRA (rank=16, alpha=16)
Training samples	1,209 (chunk-based QA, Meta Synthetic Data Kit)
Epochs	3
Learning rate	2e-4
Effective batch size	8
Hardware	Kaggle T4 GPU (16 GB)
Domains	Financial (Apple 10-K 2023), Medical (PubMed abstracts)

Eval Datasets

likhithv/knowledgemesh-benchmark-eval

Compared Models

likhithv/km-full-model — KnowledgeMesh, 4,361 KG-guided samples (+0.72 on independent eval)

Citation

@misc{knowledgemesh2026,
  title={Knowledge Graph-Guided Fine-Tuning Data Generation: A Rigorous Benchmark},
  author={Likhith V},
  year={2026},
  howpublished={https://huggingface.co/likhithv/meta-sdk-baseline}
}

Downloads last month: 3

Model tree for likhithv/meta-sdk-baseline

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Adapter

(185)

this model

likhithv
/

meta-sdk-baseline