Instructions to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF",
	filename="Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF.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 jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF
# Run inference directly in the terminal:
llama-cli -hf jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF
# Run inference directly in the terminal:
llama-cli -hf jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

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 jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF
# Run inference directly in the terminal:
./llama-cli -hf jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

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 jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

Use Docker

docker model run hf.co/jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

LM Studio
Jan

vLLM

How to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

Ollama
How to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with Ollama:
```
ollama run hf.co/jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF
```

Unsloth Studio

How to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-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 jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-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 jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF to start chatting

How to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

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": "jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

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 jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

Run Hermes

hermes

Docker Model Runner
How to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with Docker Model Runner:
```
docker model run hf.co/jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF
```

Lemonade

How to use jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

Run and chat with the model

lemonade run user.Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen2.5-Coder-1.5B-LF-FIM-Heavy

Finetuned from Qwen/Qwen2.5-Coder-1.5B.

HumanEval-Infilling (multi-line)

pass@1 = 53.23%
pass@10 = 62.62%
pass@20 = 64.35%

Since this evaluation script uses Qwen FIM tokens in prefix then suffix then middle order, this is PSM-style evaluation.

Benchmark

HumanEval-Infilling (single-line)
Tasks: 1033
Samples/task: 20
Metric: pass@k (functional correctness)

Results

pass@1: finetuned=85.48%, base=64.63%, delta=20.85%, 95% CI=[18.27%, 23.42%]
pass@10: finetuned=90.58%, base=74.48%, delta=16.11%, 95% CI=[13.59%, 18.75%]
pass@20: finetuned=91.58%, base=75.90%, delta=15.68%, 95% CI=[12.97%, 18.30%]

Setup for singleline

temperature=0.2, top_p=0.95, max_new_tokens=128
batched decoding (batch_size=16)
same evaluation harness/config for both models

Competitive multi-line performance vs larger open models.

Downloads last month: 83

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for jolovicdev/Qwen2.5-Coder-1.5B-LF-FIM-Heavy-GGUF

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Quantized

(41)

this model