Instructions to use Siddh07ETH/Atlas-Frontier-Distill-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Siddh07ETH/Atlas-Frontier-Distill-3B with Transformers:

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

pipe = pipeline("text-generation", model="Siddh07ETH/Atlas-Frontier-Distill-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Siddh07ETH/Atlas-Frontier-Distill-3B")
model = AutoModelForCausalLM.from_pretrained("Siddh07ETH/Atlas-Frontier-Distill-3B", 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 Siddh07ETH/Atlas-Frontier-Distill-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Siddh07ETH/Atlas-Frontier-Distill-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Siddh07ETH/Atlas-Frontier-Distill-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Siddh07ETH/Atlas-Frontier-Distill-3B

SGLang

How to use Siddh07ETH/Atlas-Frontier-Distill-3B 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 "Siddh07ETH/Atlas-Frontier-Distill-3B" \
    --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": "Siddh07ETH/Atlas-Frontier-Distill-3B",
		"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 "Siddh07ETH/Atlas-Frontier-Distill-3B" \
        --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": "Siddh07ETH/Atlas-Frontier-Distill-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Siddh07ETH/Atlas-Frontier-Distill-3B with Docker Model Runner:
```
docker model run hf.co/Siddh07ETH/Atlas-Frontier-Distill-3B
```

🧬 Atlas-Frontier-Distill-3B

An experimental 3B coding model distilled from frontier model traces (Kimi-K3, GPT-5.6, Fable-5).

Model Description

Atlas-Frontier-Distill-3B is a specialized coding assistant built on top of Qwen2.5-Coder-3B-Instruct. The project explores whether the coding and debugging capabilities of large frontier models can be transferred into an efficient 3B parameter model suitable for local and edge deployment.

The model was trained using QLoRA on 15,746 carefully curated coding conversations extracted from multiple frontier teacher models. Rather than imitating every response, the dataset was aggressively filtered to preserve only successful reasoning traces and high-quality coding solutions.

Distillation Experiment

This model is part of an empirical research project by Pluto AI Research Lab investigating knowledge distillation through curated execution traces.

During dataset construction, raw frontier model outputs contained a significant amount of unusable samples including:

Empty tool calls
Failed API responses
Placeholder outputs
"Needs human" responses
Abandoned reasoning chains

Over 20,375 low-quality conversations were removed, leaving 15,746 high-quality coding traces for training.

The objective was to ensure the student model learns productive coding behavior instead of failure patterns.

🔬 Behavioral Delta (via llm-diff)

Behavioral regression analysis comparing the base model against Atlas-Frontier-Distill-3B using Pluto AI's open-source llm-diff behavioral evaluation tool.

llm-diff ollama/qwen2.5-coder:3b ollama/atlas-frontier-distill-3b --backend ollama

Metric	Result	Observation
🎯 Instruction Fidelity	1.00	Maintained at 1.00. The distillation traces did not break the model's ability to follow strict formatting constraints.
⚡ Response Style	Improved	Total word count remained stable, but GPT-4 style filler preamble words were reduced to 0. The frontier traces taught the model to output pure code immediately without conversational bloat
🧠 Reasoning Consistency	1.00	Maintained at 1.00. The model successfully retained its logical consistency across reframed syllogisms.

Key Takeaway

Want to audit your own model upgrades? Install llm-diff today: pip install pluto-llm-diff

Dataset Processing

The training corpus underwent a dedicated preprocessing pipeline:

✅ Schema unification from multiple chat formats into ChatML
✅ Automatic extraction of user/assistant conversations
✅ Removal of invalid tool outputs
✅ Deduplication
✅ Conversation validation
✅ Coding-only filtering
✅ High-quality reasoning preservation

Final training corpus:

15,746 conversations
~36 MB cleaned dataset
100% coding & debugging focused

Dataset:

Siddh07ETH/Atlas-Frontier-Model-Traces

Training Details

Property	Value
Base Model	Qwen/Qwen2.5-Coder-3B-Instruct
Parameters	3.09B
Training Method	QLoRA (NF4 4-bit)
LoRA Rank	r=32
LoRA Alpha	64
LoRA Dropout	0.05
Target Modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Optimizer	Paged AdamW 8-bit
Learning Rate	1e-4
Scheduler	Cosine
Sequence Length	1024
Epochs	1
Training Steps	493
Final Training Loss	1.7056
Hardware	Kaggle Tesla T4 (16 GB)
Framework	Transformers + PEFT + TRL

Evaluation

🧪 Benchmark Results (HumanEval Pass@1)

Evaluated on a random subset of 20 complex HumanEval problems using greedy decoding (temperature=0.0) to test pure reasoning capabilities.

Model	Pass@1 Accuracy
Base Model (Qwen2.5-Coder-3B-Instruct)	60.0%
Atlas-Frontier-Distill-3B	65.0%

Key Takeaway: The fine-tuning process successfully improved the model's ability to solve complex edge-case logic problems (such as Problem #10 in our evaluation subset) while maintaining zero regression on tasks the base model already solved correctly. This validates the distillation of high-quality frontier reasoning traces into the 3B parameter space.

Intended Use

Atlas-Frontier-Distill-3B is intended for:

Local coding assistants
IDE integration
Autonomous debugging agents
Python code generation
GGUF deployment
Ollama deployment
Edge inference
Software engineering research

Limitations

Optimized specifically for coding and debugging tasks.
May perform worse than the base model on open-domain conversation.
Not trained for creative writing or general-purpose chat.
Distillation quality depends entirely on the quality of teacher traces.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "Siddh07ETH/Atlas-Frontier-Distill-3B",
    torch_dtype=torch.float16,
    device_map="auto",
)

tokenizer = AutoTokenizer.from_pretrained(
    "Siddh07ETH/Atlas-Frontier-Distill-3B"
)

messages = [
    {
        "role": "user",
        "content": "Write a Python function to connect to a PostgreSQL database."
    }
]

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=256,
        temperature=0.2,
        do_sample=True,
    )

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

Citation

If you use this model or the accompanying dataset in your research, please cite:

@misc{atlasfrontierdistill3b,
  author    = {Siddharth N.R.},
  title     = {Atlas-Frontier-Distill-3B: Distilling Frontier Model Traces into Edge-Deployable LLMs},
  year      = {2026},
  publisher = {Hugging Face},
  url       = {https://huggingface.co/Siddh07ETH/Atlas-Frontier-Distill-3B}
}

Author

Siddharth N.R.

Pluto AI Research Lab

License

Apache-2.0

Downloads last month: 10

Safetensors

Model size

3B params

Tensor type

F16

Model tree for Siddh07ETH/Atlas-Frontier-Distill-3B

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

Qwen/Qwen2.5-Coder-3B-Instruct

Finetuned

(129)

this model

Siddh07ETH
/

Atlas-Frontier-Distill-3B

🧬 Atlas-Frontier-Distill-3B

Model Description

Distillation Experiment

🔬 Behavioral Delta (via llm-diff)

Dataset Processing

Training Details

Evaluation

🧪 Benchmark Results (HumanEval Pass@1)

Intended Use

Limitations

Usage

Citation

Author

License

Model tree for Siddh07ETH/Atlas-Frontier-Distill-3B

Dataset used to train Siddh07ETH/Atlas-Frontier-Distill-3B