Instructions to use tensense/code_repo_finetuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensense/code_repo_finetuning with Transformers:

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

pipe = pipeline("text-generation", model="tensense/code_repo_finetuning")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensense/code_repo_finetuning", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tensense/code_repo_finetuning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensense/code_repo_finetuning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensense/code_repo_finetuning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensense/code_repo_finetuning

SGLang

How to use tensense/code_repo_finetuning 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 "tensense/code_repo_finetuning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensense/code_repo_finetuning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "tensense/code_repo_finetuning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensense/code_repo_finetuning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tensense/code_repo_finetuning with Docker Model Runner:
```
docker model run hf.co/tensense/code_repo_finetuning
```

code_repo_finetuning / repos /Laddr /docs /cli.md

tensense

Upload folder using huggingface_hub

4e909c7 verified 12 months ago

preview code

Raw History Blame Contribute Delete

3.7 kB

`laddr`

Usage:

$ laddr [OPTIONS] COMMAND [ARGS]...

Options:

--help: Show this message and exit.

Commands:

init: Initialize a new laddr project
add agent: Add a new agent to your project
add tool: Add a new tool to an existing agent
run: Run an agent or coordinator locally
check: Validate project structure and configuration
infra up: Start infrastructure services
infra down: Stop infrastructure services
worker: Start a worker process for an agent
prompt view: View an agent’s system prompt
prompt edit: Edit an agent’s system prompt

`laddr init`

Initialize a new laddr project.

Usage:

$ laddr init my-project
$ cd my-project

Creates:

laddr.yml – Main config
.env – Environment variables (Redis, Postgres, MinIO)
agents/ – Agent folders
workers/ – Worker modules

Options:

Project is created in a subdirectory with the given name.

`laddr add agent`

Add a new agent to your project.

Usage:

$ laddr add agent researcher

Creates:

agents/researcher/handler.py – Agent handler with tools
agents/researcher/prompt.md – System prompt

Options:

Agent name must be lowercase, snake_case.

`laddr add tool`

Add a new tool to an existing agent.

Usage:

$ laddr add tool researcher

Creates: Tool files inside the specified agent directory and updates handler.py.

Options:

Tool name must be lowercase, snake_case.

`laddr run`

Run an agent or coordinator locally (without Redis/Postgres).

Usage:

$ laddr run researcher "Search for latest AI news"

Options:

--trace – Enable tracing output
--trace-mask <tool1,tool2> – Mask specific tools from traces

Environment:

Uses in-memory implementations (no Redis/Postgres required)
Loads .env for LLM credentials.

`laddr check`

Validate project structure and configuration.

Usage:

$ laddr check

Verifies:

All agents have handler.py and prompt.md
All tools are valid Python modules
Environment variables are set correctly
laddr.yml structure is valid.

`laddr infra up`

Start infrastructure services (Redis, Postgres, MinIO) via Docker Compose.

Usage:

$ laddr infra up

Options:

-d, --detach – Run in background.

`laddr infra down`

Stop infrastructure services.

Usage:

$ laddr infra down

`laddr worker`

Start a worker process for an agent.

Usage:

$ laddr worker researcher

Options:

Connects to Redis queue specified in laddr.yml
Loads agent from agents/researcher/handler.py
Processes tasks from the coordinator.

`laddr prompt view`

View an agent’s system prompt.

Usage:

$ laddr prompt view researcher

`laddr prompt edit`

Edit an agent’s system prompt.

Usage:

$ laddr prompt edit researcher

Behavior:

Opens prompt.md in your default editor.

Edge Cases

Running without infrastructure

For local testing without Redis/Postgres:

$ laddr run researcher "test query"

Uses in-memory implementations and does not require laddr infra up.

Tracing specific agents

Enable tracing for debugging:

$ laddr run researcher "query" --trace

Mask noisy tools:

$ laddr run researcher "query" --trace --trace-mask web_search,file_read

Custom environment file

Use a custom .env file:

$ export LADDR_ENV_FILE=.env.production
$ laddr check