Instructions to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 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 kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0
# Run inference directly in the terminal:
llama cli -hf kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0
# Run inference directly in the terminal:
llama cli -hf kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2: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 kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2: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 kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

Use Docker

docker model run hf.co/kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

LM Studio
Jan

vLLM

How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

Ollama
How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with Ollama:
```
ollama run hf.co/kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0
```
Unsloth Desktop

How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with Docker Model Runner:
```
docker model run hf.co/kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0
```

Lemonade

How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

Run and chat with the model

lemonade run user.dendriva-qwen2.5-coder-3b-storyline-code-v2-Q8_0

List all available models

lemonade list

Hermes Agent

How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

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 kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0

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 "kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2:Q8_0" \
  --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"

Dendriva Qwen2.5-Coder-3B Storyline-Code v2

Private Dendriva model artifacts produced by completion-only SFT of Qwen/Qwen2.5-Coder-3B-Instruct for long-context storyline and Manim code generation.

Artifacts

qwen2.5-coder-3b-instruct.Q8_0.gguf: LoRA merged into the base model and quantized to Q8_0. This is the recommended artifact for LM Studio, llama.cpp, Ollama, and local GGUF inference.
adapter/: final PEFT LoRA adapter and tokenizer files for Transformers or reproducible re-merging with the exact base model.
training/: training configuration, observed metrics, and checksums.

The proprietary training and evaluation records are not included in this model repository.

Training summary

Objective: generation SFT with completion-only loss
Context length: 32,768 tokens
Train/eval records: 184 / 20
Precision: BF16 LoRA
LoRA: rank 32, alpha 64, RSLoRA enabled
Effective batch size: 8 (batch 1, gradient accumulation 8)
Optimizer: AdamW 8-bit
Learning rate: 5e-5 with cosine schedule and 3 warmup steps
Training duration: 46 optimizer steps, approximately 2 epochs
Final training loss: 0.331966
Best observed evaluation loss: 0.323377 at step 45

Training completed successfully on a single NVIDIA H100 80 GB. Training loss and evaluation loss do not by themselves prove downstream Manim quality; base-versus-adapter compile, render, visual, and pedagogical evaluation remains required.

Private download

Authenticate with an account that has access to this repository, then download the GGUF file:

hf auth login
hf download kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2 \
  qwen2.5-coder-3b-instruct.Q8_0.gguf \
  --local-dir ./dendriva-qwen2.5-coder-3b-storyline-code-v2

LM Studio

Download the Q8_0 GGUF with hf download, then import the local GGUF file into LM Studio. Set the context length to 32,768. On a 16 GB Apple Silicon Mac, close other memory-heavy applications before using the full context window.

Ollama

The included Modelfile expects the GGUF file to be in the same directory:

ollama create dendriva-storyline-code-v2 -f ./Modelfile
ollama run dendriva-storyline-code-v2

Adapter usage

The adapter must be loaded with the exact base model Qwen/Qwen2.5-Coder-3B-Instruct. Using a different base checkpoint can produce invalid or erratic results. For macOS inference, the merged GGUF is recommended over loading the PEFT adapter directly.

Limitations

This is a narrow domain adaptation trained on a small, curated Dendriva corpus. It may regress on unrelated coding tasks and can still produce Python or Manim code that does not compile or render. Validate outputs in a sandbox before use.

Downloads last month: 29

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

8-bit

Model tree for kangsyahrul/dendriva-qwen2.5-coder-3b-storyline-code-v2

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

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

Adapter

(76)

this model