Instructions to use build-small-hackathon/codeflow-qwen-3-finetuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use build-small-hackathon/codeflow-qwen-3-finetuning 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 build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L # Run inference directly in the terminal: llama cli -hf build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L # Run inference directly in the terminal: llama cli -hf build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L # Run inference directly in the terminal: ./build/bin/llama cli -hf build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
Use Docker
docker model run hf.co/build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
- Llama new
- LM Studio
- Jan
- Ollama
How to use build-small-hackathon/codeflow-qwen-3-finetuning with Ollama:
ollama run hf.co/build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
- Unsloth Desktop
- Pi
How to use build-small-hackathon/codeflow-qwen-3-finetuning with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use build-small-hackathon/codeflow-qwen-3-finetuning with Docker Model Runner:
docker model run hf.co/build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
- Lemonade
How to use build-small-hackathon/codeflow-qwen-3-finetuning with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
Run and chat with the model
lemonade run user.codeflow-qwen-3-finetuning-Q3_K_L
List all available models
lemonade list
- Hermes Agent
How to use build-small-hackathon/codeflow-qwen-3-finetuning with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
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://127.0.0.1:9931/v1 hermes config set model.default build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use build-small-hackathon/codeflow-qwen-3-finetuning with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L
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://127.0.0.1:9931/v1 \ --custom-model-id "build-small-hackathon/codeflow-qwen-3-finetuning:Q3_K_L" \ --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"
Download data/preview.md from build-small-hackathon/codeflow-qwen-3-finetuning: direct link, hf CLI and curl.
- Browser
- Download file 4.86 kB
-
https://huggingface.co/build-small-hackathon/codeflow-qwen-3-finetuning/resolve/main/data/preview.md
- Command line
-
hf download hf://build-small-hackathon/codeflow-qwen-3-finetuning/data/preview.md
-
curl -L -o preview.md https://huggingface.co/build-small-hackathon/codeflow-qwen-3-finetuning/resolve/main/data/preview.md
Dataset preview
Random sample of 6 examples (system prompt omitted for brevity).
Example 1 — switch_match (c), 6 nodes
User (input):
1| const char* trim_value(int kind) {
2| switch (kind) {
3| case 0:
4| return "first";
5| case 1:
6| return "second";
7| case 2:
8| return "third";
9| default:
10| return "other";
11| }
12| }
Assistant (target):
<thinking>
1. Control structures: 1 decision point, 4 terminal branches.
2. Execution nodes in order: A Start: trim_value, B Which case applies?, C Return first label, D Return second label, E Return third label, F Return default label.
3. Source lines: A maps to line 1, B maps to line 2, C maps to line 4, D maps to line 6, E maps to line 8, F maps to line 10.
</thinking>
graph TD
A[Start: trim_value]
B{Which case applies?}
C[Return first label]
D[Return second label]
E[Return third label]
F[Return default label]
A --> B
B -- First case --> C
B -- Second case --> D
B -- Third case --> E
B -- Default --> F
<linemap>
A: 1
B: 2
C: 4
D: 6
E: 8
F: 10
</linemap>
Example 2 — guard_return (c), 4 nodes
User (input):
1| int aggregate(int found) {
2| if (found) {
3| return 0;
4| }
5| return 1;
6| }
Assistant (target):
<thinking>
1. Structural parse: 1 decision point, 2 terminal branches.
2. Execution nodes in order: A Start: aggregate, B Flag is set?, C Return false, D Return true.
3. Source lines: A maps to line 1, B maps to line 2, C maps to line 3, D maps to line 5.
</thinking>
graph TD
A[Start: aggregate]
B{Flag is set?}
C[Return false]
D[Return true]
A --> B
B -- True --> C
B -- False --> D
<linemap>
A: 1
B: 2
C: 3
D: 5
</linemap>
Example 3 — dict_lookup (javascript), 4 nodes
User (input):
1| function searchList(registry, field) {
2| if (field in registry) {
3| return registry[field];
4| }
5| return null;
6| }
Assistant (target):
<thinking>
1. Structural parse: 1 decision point, 2 terminal branches.
2. Nodes mapped chronologically: A Start: searchList, B Key exists in map?, C Return the mapped value, D Return nothing.
3. Source lines: A maps to line 1, B maps to line 2, C maps to line 3, D maps to line 5.
</thinking>
graph TD
A[Start: searchList]
B{Key exists in map?}
C[Return the mapped value]
D[Return nothing]
A --> B
B -- Found --> C
B -- Missing --> D
<linemap>
A: 1
B: 2
C: 3
D: 5
</linemap>
Example 4 — try_except (javascript), 4 nodes
User (input):
1| function formatName(line) {
2| try {
3| return parseInt(line);
4| } catch (err) {
5| return 0;
6| }
7| }
Assistant (target):
<thinking>
1. Control structures: 1 decision point, 2 terminal branches.
2. Node sequence: A Start: formatName, B Conversion succeeds?, C Return the value, D Return zero.
3. Source lines: A maps to line 1, B maps to line 2, C maps to line 3, D maps to line 5.
</thinking>
graph TD
A[Start: formatName]
B{Conversion succeeds?}
C[Return the value]
D[Return zero]
A --> B
B -- Success --> C
B -- Failure --> D
<linemap>
A: 1
B: 2
C: 3
D: 5
</linemap>
Example 5 — for_search (javascript), 5 nodes
User (input):
1| function lookup(results, wanted) {
2| for (let i = 0; i < results.length; i++) {
3| if (results[i] === wanted) {
4| return i;
5| }
6| }
7| return -1;
8| }
Assistant (target):
<thinking>
1. Structural parse: 1 decision point, 1 loop, 2 terminal branches.
2. Execution nodes in order: A Start: lookup, B Iterate over collection, C Item matches target?, D Return the index, E Return not found.
3. Source lines: A is line 1, B is line 2, C is line 3, D is line 4, E is line 7.
</thinking>
graph TD
A[Start: lookup]
B[Iterate over collection]
C{Item matches target?}
D[Return the index]
E[Return not found]
A --> B
B -- For each --> C
B -- No more items --> E
C -- Match --> D
C -- No match --> B
<linemap>
A: 1
B: 2
C: 3
D: 4
E: 7
</linemap>
Example 6 — dict_lookup (python), 4 nodes
User (input):
1| def lookup(mapping, user_id):
2| if user_id in mapping:
3| return mapping[user_id]
4| return None
Assistant (target):
<thinking>
1. Structural parse: 1 decision point, 2 terminal branches.
2. Node sequence: A Start: lookup, B Key exists in map?, C Return the mapped value, D Return nothing.
3. Source lines: A maps to line 1, B maps to line 2, C maps to line 3, D maps to line 4.
</thinking>
graph TD
A[Start: lookup]
B{Key exists in map?}
C[Return the mapped value]
D[Return nothing]
A --> B
B -- Found --> C
B -- Missing --> D
<linemap>
A: 1
B: 2
C: 3
D: 4
</linemap>