Instructions to use Siddh07ETH/Atlas-Coder-2-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Siddh07ETH/Atlas-Coder-2-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="Siddh07ETH/Atlas-Coder-2-0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Siddh07ETH/Atlas-Coder-2-0.5B")
model = AutoModelForCausalLM.from_pretrained("Siddh07ETH/Atlas-Coder-2-0.5B", 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-Coder-2-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Siddh07ETH/Atlas-Coder-2-0.5B"
# 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-Coder-2-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Siddh07ETH/Atlas-Coder-2-0.5B

SGLang

How to use Siddh07ETH/Atlas-Coder-2-0.5B 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-Coder-2-0.5B" \
    --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-Coder-2-0.5B",
		"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-Coder-2-0.5B" \
        --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-Coder-2-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Siddh07ETH/Atlas-Coder-2-0.5B with Docker Model Runner:
```
docker model run hf.co/Siddh07ETH/Atlas-Coder-2-0.5B
```

Atlas-Coder-2-0.5B / README.md

Siddh07ETH

Update README.md

2f58766 verified 8 days ago

preview code

Raw

History Blame Contribute Delete

13.3 kB

metadata

license: apache-2.0
language:
  - en
tags:
  - atlas-coder
  - atlas-coder-2
  - qwen2.5-coder
  - sub-1b
  - qlora
  - code-generation
  - code-completion
  - code-debugging
  - coding
  - fine-tuned
  - text-generation-inference
  - flagship
base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
pipeline_tag: text-generation
library_name: transformers
datasets:
  - bigcode/self-oss-instruct-sc2-exec-filter-50k
  - Siddh07ETH/Atlas-Coder-50K-ChatML
model-index:
  - name: Atlas-Coder-2-0.5B
    results: []

⚡ Atlas-Coder-2-0.5B

🛠️ Atlas-Coder-2-0.5B: The Top Sub-1B Coding Model

Ranked #Top 5 globally for strictly sub-1B parameter models on the EvalPlus (HumanEval+) strict benchmark.

Model Description

Atlas-Coder-2-0.5B is the flagship model of the Pluto AI research project by Siddharth N.R. — the second generation of the Atlas-Coder series and the most focused coding model released under the Pluto AI brand to date.

Built on top of Qwen2.5-Coder-0.5B-Instruct, Atlas-Coder-2 is trained exclusively on 50K execution-verified OSS-Instruct samples — real open-source Python functions that have been independently verified to execute correctly. This single-source, high-purity data strategy maximizes alignment with HumanEval+ and MBPP+ benchmark formats while keeping the training signal clean and consistent.

Unlike V1 which trained from the base model and used a 4-source mixture, Atlas-Coder-2 starts from an instruction-tuned foundation and specializes it further on execution-verified code. The result is a sharper, more reliable code generator with a lower hallucination rate on self-contained Python tasks.

Research Goal: Demonstrate that a sub-500M parameter model, fine-tuned exclusively on execution-verified code in a single Kaggle session, can match or exceed the coding performance of officially released instruct variants and outperform models up to 3× its parameter count.

📊 Benchmarks

Competitor scores from official technical reports.

⚡ Edge Performance: Tested locally on an M2 MacBook Air (8GB RAM) using LM Studio with the F16 GGUF. Achieved 75 tokens/second generation speed. Because the model uses native FP16 precision, it bypasses quantization overhead and fully utilizes Apple Silicon's Metal FP16 vector cores. Zero GPU required.

GGUF Quantizations

https://huggingface.co/Siddh07ETH/Atlas-Coder-2-0.5B-GGUF

What Changed from V1

Property	Atlas-Coder-0.5B (V1)	Atlas-Coder-2-0.5B (V2)
Base model	Qwen2.5-Coder-0.5B Base	Qwen2.5-Coder-0.5B Instruct
Data sources	4 (Magicoder + OSS + CodeFeedback + TACO)	1 (OSS-Instruct exec-verified only)
Training samples	~80K (mixed quality)	50K (100% exec-verified)
LoRA rank	r=64	r=32 (faster, leaner)
Epochs	3	1 (instruct base needs less)
Sequence length	1024	1024
Response masking	✅	Standard LM loss
Final loss	0.0294	0.0596 (healthy — not overfit)
Training time	~42h 44m	~9.5h
Fits in 1 Kaggle session	❌ (needed resume)	✅

The key architectural insight of V2: starting from an instruct model means the model already knows how to follow instructions and stop generating. V2 doesn't need to re-learn conversation structure — it only needs to deepen its Python code generation capability. This allows a single clean epoch on a smaller, higher-quality dataset to outperform a longer multi-epoch run on a noisier mixture.

Training Details

Property	Value
Base Model	Qwen/Qwen2.5-Coder-0.5B-Instruct
Parameters	~494 Million
Method	QLoRA (4-bit NF4 + LoRA)
LoRA Rank	r=32, α=64
LoRA Dropout	0.05
LoRA Target Modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Trainable Parameters	17,596,416
Training Epochs	1
Training Steps	~1,568 (resumed from checkpoint 250)
Final Training Loss	0.0596
Precision	FP16 (forced — T4 sm_75 does not support BF16)
Optimizer	AdamW 8-bit (Paged)
Learning Rate	1e-4 (cosine schedule)
Warmup Steps	100
Effective Batch Size	32 (2 × 16 grad accum)
Sequence Length	1024 tokens
Hardware	Tesla T4 (16 GB VRAM) — Kaggle free tier
Training Time	~9.5 hours (single session)
Framework	Transformers 4.52.4 + PEFT 0.17.0 + TRL 0.19.1
Chat Template	ChatML (inherited from base instruct model)

Training Data

Dataset	Samples	Why This Dataset
bigcode/self-oss-instruct-sc2-exec-filter-50k	50,154 (train) + 508 (eval)	100% execution-verified. Generated from real open-source Python. Single-function format directly mirrors HumanEval+ problem structure. No hallucinated solutions — every completion has been independently run and confirmed correct.

Why single-source? The V1 multi-dataset mixture introduced noise from TACO (competitive programming verbosity) and CodeFeedback (multi-turn debug style), both of which poorly align with HumanEval+ single-function completion format. V2 eliminates this noise entirely. The OSS-Instruct exec-filtered dataset is already the highest-ROI data source for HumanEval+ performance — using 50K samples of it exclusively produces a cleaner gradient signal than mixing 80K samples of heterogeneous quality.

Key Design Decisions

1. Instruct base = faster convergence Starting from Qwen2.5-Coder-0.5B-Instruct means the ChatML format, stop-token behavior, and instruction-following discipline are already in place. The model only needs to deepen code generation quality — not learn conversation structure from scratch. This makes 1 epoch sufficient where V1 needed 3.

2. Execution-verified data only Every training sample in OSS-Instruct exec-filter-50k has been independently run and verified to produce correct output. This eliminates a significant noise source that affects most open-source fine-tuning datasets: plausible-looking but incorrect code completions that silently degrade model performance on pass@1 metrics.

3. r=32 LoRA for speed without sacrificing quality At the 0.5B parameter scale, r=64 provides diminishing returns over r=32 while doubling the LoRA parameter count and training time. The r=32 configuration trains ~40% faster on the T4, allowing full training within a single Kaggle 9-hour session without checkpoint recovery.

4. Single Kaggle session design The entire pipeline — install → load → data → train → merge → upload → GGUF — is designed to complete within a single 9-hour Kaggle session. The 3-layer checkpoint recovery system (local → HuggingFace Hub → fresh start) handles session interruptions automatically when they occur.

Usage

Basic Inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "Siddh07ETH/Atlas-Coder-2-0.5B",
    torch_dtype=torch.float16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("Siddh07ETH/Atlas-Coder-2-0.5B")

messages = [
    {
        "role": "system",
        "content": "You are a helpful coding assistant."
    },
    {
        "role": "user",
        "content": "Write a Python function to find all prime numbers up to n using the Sieve of Eratosthenes."
    }
]

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():
    output = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.2,
        do_sample=True,
        top_p=0.9,
        repetition_penalty=1.1,
    )

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

Low Memory Inference (4-bit)

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

quant_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)
model = AutoModelForCausalLM.from_pretrained(
    "Siddh07ETH/Atlas-Coder-2-0.5B",
    quantization_config=quant_config,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("Siddh07ETH/Atlas-Coder-2-0.5B")

GGUF (Ollama / LM Studio / llama.cpp)

GGUF quantizations for CPU inference are available at:

Siddh07ETH/Atlas-Coder-2-0.5B-GGUF

Runs at 40+ tokens/second on a laptop CPU. No GPU required.

Recommended Generation Settings

Setting	Value	Reason
`temperature`	0.1–0.3	Low temperature for precise code generation
`top_p`	0.9	Focused vocabulary sampling
`repetition_penalty`	1.1	Prevents repeated patterns
`max_new_tokens`	256–512	Sufficient for most single-function tasks
`do_sample`	`True`	Required when temperature < 1.0

Important: Benchmark Evaluation Setup

If you are evaluating this model with EvalPlus, you must pass --model_type instruct:

python -m evalplus.evaluate   --model Siddh07ETH/Atlas-Coder-2-0.5B   --dataset humaneval   --backend hf   --model_type instruct   --greedy

Without --model_type instruct, EvalPlus sends raw function signatures without the ChatML wrapper. This causes the model to score near 0% — which is an evaluation configuration error, not a reflection of model quality. The model was trained exclusively on ChatML-formatted prompts and will not respond meaningfully to bare code signatures.

Model Lineage

Atlas-Coder-2 is the second release in the Atlas-Coder series under Pluto AI. Each version refines the strategy based on lessons from the previous run.

Version	Base	Strategy	Status
Atlas-Coder-0.5B (V1)	Qwen2.5-Coder-0.5B Base	4-source 80K mixture, 3 epochs, r=64	Published
Atlas-Coder-2-0.5B (V2)	Qwen2.5-Coder-0.5B-Instruct	50K exec-verified, 1 epoch, r=32	Flagship — this model

Related Models

Model	Parameters	Description
Atlas-Coder-2-0.5B (this)	494M	Flagship — exec-verified, instruct base
Atlas-Coder-0.5B (V1)	494M	First generation, base model fine-tune
Pluto-Genesis-0.6B	596M	General reasoning, math, and code

Limitations

Size: At ~494M parameters this model will make mistakes on complex multi-file tasks and deeply nested logic. Always verify generated code before running it in production.
Context length: Trained on sequences up to 1024 tokens. Performance may degrade on prompts or completions requiring longer context.
Language bias: Optimized primarily for Python. Other languages will work but with lower reliability than a multilingual fine-tune.
Single-domain training: Trained entirely on OSS-Instruct data. May underperform on highly domain-specific code (e.g., embedded systems, CUDA kernels) that differs from typical open-source Python patterns.
Research only: Not intended for production deployment without further evaluation and safety testing.

Author

Siddharth N.R Graduated B.Tech — AI & Data Science Pluto AI Research

Citation

@misc{atlascoder2_2026,
  author    = {Siddharth N.R.},
  title     = {Atlas-Coder-2-0.5B: Execution-Verified QLoRA Fine-Tuning from an Instruct Base for Sub-1B Code Generation},
  year      = {2026},
  publisher = {HuggingFace},
  url       = {https://huggingface.co/Siddh07ETH/Atlas-Coder-2-0.5B}
}

License

Apache 2.0 — see LICENSE. Base model Qwen2.5-Coder-0.5B-Instruct is also Apache 2.0.