Instructions to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with Transformers:

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

pipe = pipeline("text-generation", model="yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator", dtype="auto", device_map="auto")

llama-cpp-python

How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator",
	filename="smollm2_1_7b_instruct_merged-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0
# Run inference directly in the terminal:
llama cli -hf yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0
# Run inference directly in the terminal:
llama cli -hf yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0

Use Docker

docker model run hf.co/yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0

LM Studio
Jan

vLLM

How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0

SGLang

How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator 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 "yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator" \
    --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": "yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator",
		"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 "yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator" \
        --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": "yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with Ollama:
```
ollama run hf.co/yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0
```

Unsloth Studio

How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator to start chatting

Atomic Chat new
Docker Model Runner
How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with Docker Model Runner:
```
docker model run hf.co/yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0
```

Lemonade

How to use yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator:Q8_0

Run and chat with the model

lemonade run user.SmolLM2-1.7B-Instruct-DocstringGenerator-Q8_0

List all available models

lemonade list

SmolLM2-1.7B-Instruct · DocstringGenerator

A fine-tuned SmolLM2-1.7B-Instruct specialised in writing concise, high-level Python docstrings for functions, methods and classes. This model is the backbone of the PyDoctor CLI — a fully local, LLM-powered tool that automatically writes and manages docstrings in your Python codebase.

Intended Use

The model generates summary-style docstrings — single-paragraph, plain-English descriptions of a Python code block's purpose and architectural role. It does not produce Args:, Returns:, or Raises: sections by design.

Suitable for:

Automated docstring generation in CI/CD pipelines
Interactive IDE plugins
Local, privacy-preserving documentation workflows via llama.cpp / GGUF

Not suitable for:

General-purpose code generation
Generating full NumPy/Google-style docstrings with parameter tables (explicitly omitted)
Non-Python languages

Quick Start

With llama.cpp (GGUF · recommended for local use)

# Download the Q8_0 GGUF
huggingface-cli download \
  yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator \
  smollm2_1_7b_instruct_merged-q8_0.gguf \
  --local-dir ./models

# Run inference
llama-cli \
  -m ./models/smollm2_1_7b_instruct_merged-q8_0.gguf \
  --chat-template chatml \
  -p "..."

Tip: The PyDoctor CLI handles prompt construction, parsing, and atomic file rewrites out of the box.

Prompt Format (ChatML)

The model uses the ChatML template native to SmolLM2-Instruct:

<|im_start|>system
{SYSTEM_PROMPT}<|im_end|>
<|im_start|>user
CONTEXT
{context_code}

TARGET CODE
{target_code}<|im_end|>
<|im_start|>assistant

The model then generates only the raw docstring text, terminated by <|im_end|>.

Context definition:

function target -> context = "Independent code block"
method target → context = __init__ signature of its enclosing class
class target → context = signatures of its methods

Training Pipeline

Stage 1 — Code Extraction

Raw Python source files were streamed from codeparrot/codeparrot-clean (~200 k samples). Each file passed a quality filter that rejected:

Filter	Threshold
Too few lines	< 3 non-empty lines
Minified code	avg line length > 150 chars
Low alphabetic ratio	< 15 % (binary / machine-generated)
Repetitive boilerplate	unique line ratio < 10 %
Oversized files	> 50 000 characters

Surviving files were parsed with LibCST producing (target, context) pairs.

Stage 2 — Synthetic Docstring Generation

(target, context) pairs were labelled in parallel using DeepSeek V4 Flash (via OpenRouter):

The teacher-model system prompt enforced:

Describe semantic purpose and architectural role, not implementation details
Use context to disambiguate class membership

Stage 3 — Instruct Data Preparation & Tokenisation

Synthetic batches were assembled into ChatML prompt/completion pairs:

prompt = (
    f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n"
    f"<|im_start|>user\nCONTEXT\n{context}\n\nTARGET CODE\n{target}<|im_end|>\n"
    f"<|im_start|>assistant\n"
)
completion = f"{docstring}<|im_end|>"

Labels were constructed so that only completion tokens are trained on — prompt tokens are masked from cross-entropy loss.

Stage 4 — QLoRA Fine-tuning

Fine-tuning was performed on Kaggle kernels (instruct_finetune.py):

Hyperparameter	Value
Quantisation	4-bit NF4, double quant, fp16 compute
LoRA rank `r`	32
LoRA alpha `α`	64
LoRA dropout	0.2
LoRA bias	none
Target modules	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
Optimizer	AdamW 8-bit (bitsandbytes)
Learning rate	2e-4
LR schedule	Cosine with 5 % warmup
Weight decay	0.01
Batch size	8 per device
Gradient accumulation	8 steps → effective batch 64
Epochs	1
Max sequence length	1 024 tokens (95th-pct filter)
Validation split	1 % held-out, evaluated each epoch
Seed	1337

Loss = next-token cross-entropy, prompt tokens ignored via label mask.

Stage 5 — LoRA Merge & GGUF Export

After training, LoRA adapters were merged back into the base model weights and converted to Q8_0 GGUF using llama.cpp:

LoRA adapter (epoch 1, safetensors)
        │
        ▼  merge_and_unload()
        │
merged fp16 safetensors
        │
        ▼  llama.cpp convert_hf_to_gguf.py --outtype q8_0
        ▼
smollm2_1_7b_instruct_merged-q8_0.gguf

Files

File	Description
`smollm2_1_7b_instruct_merged-q8_0.gguf`	Q8_0 GGUF for llama.cpp — recommended for local use
`safetensors/model.safetensors`	Merged fp16 weights
`safetensors/config.json`	HuggingFace model configuration
`safetensors/tokenizer.json` / `safetensors/tokenizer_config.json`	SmolLM2-1.7B-Instruct tokenizer

Limitations & Bias

Summary-only style: the model is trained to output a single-paragraph summary. It will not produce Args: / Returns: sections.
Python only: trained exclusively on Python source code from codeparrot-clean.
Context dependency: quality improves when the correct context string is provided. Passing an empty context for class methods may reduce coherence.
Teacher model bias: docstring style reflects DeepSeek V4 Flash's preferences filtered through the strict prompt rules. Unusual code idioms may yield generic descriptions.
Not a general assistant: the model is heavily specialised and will likely perform poorly on tasks other than docstring generation.

Citation

@misc{pydoctor2026,
  author       = {yezdata},
  title        = {PyDoctor: Local LLM-powered Python Docstring Generator},
  year         = {2026},
  howpublished = {\url{https://github.com/yezdata/pydoctor}},
  note         = {Fine-tuned SmolLM2-1.7B-Instruct model available at
                  \url{https://huggingface.co/yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator}}
}

License

This model is released under the Apache 2.0 license, matching the base SmolLM2-1.7B-Instruct model.
Training data originates from codeparrot/codeparrot-clean (MIT)

Downloads last month: 67

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

8-bit

Model tree for yezdata/SmolLM2-1.7B-Instruct-DocstringGenerator

Base model

HuggingFaceTB/SmolLM2-1.7B

Quantized

HuggingFaceTB/SmolLM2-1.7B-Instruct

Adapter

(57)

this model

yezdata
/

SmolLM2-1.7B-Instruct-DocstringGenerator