Instructions to use sarimahsan101/Qwen2.5-0.5B-HiddenDistilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sarimahsan101/Qwen2.5-0.5B-HiddenDistilled with Transformers:

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

pipe = pipeline("text-generation", model="sarimahsan101/Qwen2.5-0.5B-HiddenDistilled")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sarimahsan101/Qwen2.5-0.5B-HiddenDistilled")
model = AutoModelForCausalLM.from_pretrained("sarimahsan101/Qwen2.5-0.5B-HiddenDistilled")
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 sarimahsan101/Qwen2.5-0.5B-HiddenDistilled with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sarimahsan101/Qwen2.5-0.5B-HiddenDistilled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sarimahsan101/Qwen2.5-0.5B-HiddenDistilled",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sarimahsan101/Qwen2.5-0.5B-HiddenDistilled

SGLang

How to use sarimahsan101/Qwen2.5-0.5B-HiddenDistilled 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 "sarimahsan101/Qwen2.5-0.5B-HiddenDistilled" \
    --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": "sarimahsan101/Qwen2.5-0.5B-HiddenDistilled",
		"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 "sarimahsan101/Qwen2.5-0.5B-HiddenDistilled" \
        --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": "sarimahsan101/Qwen2.5-0.5B-HiddenDistilled",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sarimahsan101/Qwen2.5-0.5B-HiddenDistilled with Docker Model Runner:
```
docker model run hf.co/sarimahsan101/Qwen2.5-0.5B-HiddenDistilled
```

Qwen2.5-0.5B-HiddenDistilled

This repository contains the fully merged base + adapter weights for Qwen2.5-0.5B-Instruct distilled from the teacher model Qwen2.5-3B-Instruct. The distillation pipeline optimizes a composite objective combining supervised learning cross-entropy, logit-level KL divergence, and MSE alignment of projected hidden states.

Base Student Model: Qwen/Qwen2.5-0.5B-Instruct
Teacher Model: Qwen/Qwen2.5-3B-Instruct
LoRA Adapter Repo: sarimahsan101/Qwen2.5-0.5B-HiddenDistilled-LoRA
Training Code (GitHub): sarimahsan101/distillation-hiddenstates

📊 Trial Run Evaluation Metrics

Evaluation metrics compiled on a single NVIDIA Tesla T4 (16GB) GPU for 1 epoch on a subset of Dolly, Alpaca SFT, and Ultrachat:

Metric	Before Distillation	After Distillation	Change	Status
Validation Perplexity	5.0924	5.2620	+0.1696	✗
Teacher-Student KL Divergence	2.7913	1.9637	-0.8276	✓
Hidden State Cosine Similarity	0.0075	0.0054	-0.0021	✗

🚀 How to Use (Merged Model)

You can load this model directly using standard Hugging Face Transformers:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "sarimahsan101/Qwen2.5-0.5B-HiddenDistilled"

# Load tokenizer and merged model
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
model.eval()

# Inference example
messages = [{"role": "user", "content": "Explain gravity in one sentence."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=50)

print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

🛠️ Training Configurations & Details

Framework: PyTorch & Hugging Face Transformers / Trainer
Quantization: 4-bit NF4 double quantization (bitsandbytes) for training, adapter weights were merged with FP16 base student.
Loss Weights: Cross-Entropy: 0.3, KL Divergence: 0.4, Hidden MSE: 0.3

Downloads last month: 255

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for sarimahsan101/Qwen2.5-0.5B-HiddenDistilled

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(884)

this model