Instructions to use theprint/SoCode-v1-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theprint/SoCode-v1-2B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("theprint/SoCode-v1-2B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use theprint/SoCode-v1-2B-GGUF 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 theprint/SoCode-v1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf theprint/SoCode-v1-2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf theprint/SoCode-v1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf theprint/SoCode-v1-2B-GGUF:Q4_K_M

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 theprint/SoCode-v1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf theprint/SoCode-v1-2B-GGUF:Q4_K_M

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 theprint/SoCode-v1-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theprint/SoCode-v1-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/theprint/SoCode-v1-2B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use theprint/SoCode-v1-2B-GGUF with Ollama:
```
ollama run hf.co/theprint/SoCode-v1-2B-GGUF:Q4_K_M
```

Unsloth Studio

How to use theprint/SoCode-v1-2B-GGUF 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 theprint/SoCode-v1-2B-GGUF 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 theprint/SoCode-v1-2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theprint/SoCode-v1-2B-GGUF to start chatting

How to use theprint/SoCode-v1-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theprint/SoCode-v1-2B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "theprint/SoCode-v1-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use theprint/SoCode-v1-2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theprint/SoCode-v1-2B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default theprint/SoCode-v1-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use theprint/SoCode-v1-2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theprint/SoCode-v1-2B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "theprint/SoCode-v1-2B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use theprint/SoCode-v1-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/theprint/SoCode-v1-2B-GGUF:Q4_K_M
```

Lemonade

How to use theprint/SoCode-v1-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theprint/SoCode-v1-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SoCode-v1-2B-GGUF-Q4_K_M

List all available models

lemonade list

SoCode-v1-2B-GGUF / README.md

theprint

Upload README.md with huggingface_hub

fe1634f verified 13 days ago

preview code

Raw

History Blame Contribute Delete

2.29 kB

	---
	base_model: unsloth/Qwen3.5-2B
	datasets:
	- OpceanAI/sota-coding
	tags:
	- fine-tuned
	- lora
	- sft
	- auto-sft
	language:
	- en
	library_name: transformers
	---

	# SoCode-v1-2B (GGUF)

	A fine-tuned version of [`unsloth/Qwen3.5-2B`](https://huggingface.co/unsloth/Qwen3.5-2B) trained on OpceanAI sota coding data using Auto-SFT — an automated hyperparameter search and supervised fine-tuning pipeline.

	The base model was adapted to follow the style and content of the `OpceanAI sota coding` dataset. Expect improved performance on tasks similar to those represented in the training data.

	## Model Details

	\| Property \| Value \|
	\|---\|---\|
	\| Base model \| `unsloth/Qwen3.5-2B` \|
	\| Training data \| `OpceanAI/sota-coding` \|
	\| Fine-tuning epochs \| 1 \|
	\| Fine-tuning date \| 2026-07-21 \|
	\| Fine-tuning method \| LoRA (merged to full 16-bit) \|

	## Training Hyperparameters

	### LoRA

	\| Parameter \| Value \|
	\|---\|---\|
	\| `r` \| `64` \|
	\| `alpha` \| `256` \|
	\| `dropout` \| `0.07` \|
	\| `target_modules` \| `['q_proj', 'v_proj']` \|

	### Training

	\| Parameter \| Value \|
	\|---\|---\|
	\| `learning_rate` \| `0.0002` \|
	\| `batch_size` \| `1` \|
	\| `gradient_accumulation_steps` \| `8` \|
	\| `warmup_ratio` \| `0.1` \|
	\| `max_seq_length` \| `512` \|
	\| `quantization` \| `none` \|

	## GGUF Files

	These quantized GGUF files can be used directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://ollama.com/), [LM Studio](https://lmstudio.ai/), and other compatible runtimes.

	\| File \| Description \|
	\|---\|---\|
	\| `SoCode-v1-2B-GGUF-BF16.gguf` \| BF16 \|
	\| `SoCode-v1-2B-GGUF-Q8_0.gguf` \| 8-bit — near-lossless, larger file \|
	\| `SoCode-v1-2B-GGUF-Q6_K.gguf` \| 6-bit — high quality \|
	\| `SoCode-v1-2B-GGUF-Q5_K_M.gguf` \| 5-bit medium — good quality/size balance \|
	\| `SoCode-v1-2B-GGUF-Q5_K_S.gguf` \| Q5_K_S \|
	\| `SoCode-v1-2B-GGUF-Q4_K_M.gguf` \| 4-bit medium — recommended for most use cases \|
	\| `SoCode-v1-2B-GGUF-Q4_K_S.gguf` \| Q4_K_S \|
	\| `SoCode-v1-2B-GGUF-Q3_K_L.gguf` \| Q3_K_L \|
	\| `SoCode-v1-2B-GGUF-Q3_K_M.gguf` \| Q3_K_M \|
	\| `SoCode-v1-2B-GGUF-Q3_K_S.gguf` \| Q3_K_S \|
	\| `SoCode-v1-2B-GGUF-Q2_K.gguf` \| 2-bit — smallest size, lowest quality \|
	\| `SoCode-v1-2B-GGUF-IQ4_XS.gguf` \| IQ4_XS \|
	\| `SoCode-v1-2B-GGUF-IQ4_NL.gguf` \| IQ4_NL \|
	\| `SoCode-v1-2B-GGUF-TQ2_0.gguf` \| TQ2_0 \|

	---
	Generated by Auto-SFT

	---
	base_model: unsloth/Qwen3.5-2B
	datasets:
	- OpceanAI/sota-coding
	tags:
	- fine-tuned
	- lora
	- sft
	- auto-sft
	language:
	- en
	library_name: transformers
	---

	# SoCode-v1-2B (GGUF)

	A fine-tuned version of [`unsloth/Qwen3.5-2B`](https://huggingface.co/unsloth/Qwen3.5-2B) trained on OpceanAI sota coding data using Auto-SFT — an automated hyperparameter search and supervised fine-tuning pipeline.

	The base model was adapted to follow the style and content of the `OpceanAI sota coding` dataset. Expect improved performance on tasks similar to those represented in the training data.

	## Model Details

	\| Property \| Value \|
	\|---\|---\|
	\| Base model \| `unsloth/Qwen3.5-2B` \|
	\| Training data \| `OpceanAI/sota-coding` \|
	\| Fine-tuning epochs \| 1 \|
	\| Fine-tuning date \| 2026-07-21 \|
	\| Fine-tuning method \| LoRA (merged to full 16-bit) \|

	## Training Hyperparameters

	### LoRA

	\| Parameter \| Value \|
	\|---\|---\|
	\| `r` \| `64` \|
	\| `alpha` \| `256` \|
	\| `dropout` \| `0.07` \|
	\| `target_modules` \| `['q_proj', 'v_proj']` \|

	### Training

	\| Parameter \| Value \|
	\|---\|---\|
	\| `learning_rate` \| `0.0002` \|
	\| `batch_size` \| `1` \|
	\| `gradient_accumulation_steps` \| `8` \|
	\| `warmup_ratio` \| `0.1` \|
	\| `max_seq_length` \| `512` \|
	\| `quantization` \| `none` \|

	## GGUF Files

	These quantized GGUF files can be used directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://ollama.com/), [LM Studio](https://lmstudio.ai/), and other compatible runtimes.

	\| File \| Description \|
	\|---\|---\|
	\| `SoCode-v1-2B-GGUF-BF16.gguf` \| BF16 \|
	\| `SoCode-v1-2B-GGUF-Q8_0.gguf` \| 8-bit — near-lossless, larger file \|
	\| `SoCode-v1-2B-GGUF-Q6_K.gguf` \| 6-bit — high quality \|
	\| `SoCode-v1-2B-GGUF-Q5_K_M.gguf` \| 5-bit medium — good quality/size balance \|
	\| `SoCode-v1-2B-GGUF-Q5_K_S.gguf` \| Q5_K_S \|
	\| `SoCode-v1-2B-GGUF-Q4_K_M.gguf` \| 4-bit medium — recommended for most use cases \|
	\| `SoCode-v1-2B-GGUF-Q4_K_S.gguf` \| Q4_K_S \|
	\| `SoCode-v1-2B-GGUF-Q3_K_L.gguf` \| Q3_K_L \|
	\| `SoCode-v1-2B-GGUF-Q3_K_M.gguf` \| Q3_K_M \|
	\| `SoCode-v1-2B-GGUF-Q3_K_S.gguf` \| Q3_K_S \|
	\| `SoCode-v1-2B-GGUF-Q2_K.gguf` \| 2-bit — smallest size, lowest quality \|
	\| `SoCode-v1-2B-GGUF-IQ4_XS.gguf` \| IQ4_XS \|
	\| `SoCode-v1-2B-GGUF-IQ4_NL.gguf` \| IQ4_NL \|
	\| `SoCode-v1-2B-GGUF-TQ2_0.gguf` \| TQ2_0 \|

	---
	Generated by Auto-SFT