Instructions to use piotrjanik/ocm-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use piotrjanik/ocm-coder with MLX:

# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir ocm-coder piotrjanik/ocm-coder

llama-cpp-python

How to use piotrjanik/ocm-coder with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="piotrjanik/ocm-coder",
	filename="ocm-coder-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use piotrjanik/ocm-coder with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf piotrjanik/ocm-coder:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf piotrjanik/ocm-coder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf piotrjanik/ocm-coder:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf piotrjanik/ocm-coder: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 piotrjanik/ocm-coder:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf piotrjanik/ocm-coder: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 piotrjanik/ocm-coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf piotrjanik/ocm-coder:Q4_K_M

Use Docker

docker model run hf.co/piotrjanik/ocm-coder:Q4_K_M

LM Studio
Jan
Ollama
How to use piotrjanik/ocm-coder with Ollama:
```
ollama run hf.co/piotrjanik/ocm-coder:Q4_K_M
```

Unsloth Studio new

How to use piotrjanik/ocm-coder 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 piotrjanik/ocm-coder 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 piotrjanik/ocm-coder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for piotrjanik/ocm-coder to start chatting

Pi new

How to use piotrjanik/ocm-coder with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "piotrjanik/ocm-coder"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "piotrjanik/ocm-coder"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use piotrjanik/ocm-coder with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "piotrjanik/ocm-coder"

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 piotrjanik/ocm-coder

Run Hermes

hermes

Docker Model Runner
How to use piotrjanik/ocm-coder with Docker Model Runner:
```
docker model run hf.co/piotrjanik/ocm-coder:Q4_K_M
```

Lemonade

How to use piotrjanik/ocm-coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull piotrjanik/ocm-coder:Q4_K_M

Run and chat with the model

lemonade run user.ocm-coder-Q4_K_M

List all available models

lemonade list

piotrjanik commited on Mar 10

Commit

459a98a

verified ·

1 Parent(s): 17893e6

Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

0000200_adapters.safetensors +3 -0
0000400_adapters.safetensors +3 -0
0000600_adapters.safetensors +3 -0
0000800_adapters.safetensors +3 -0
0001000_adapters.safetensors +3 -0
README.md +22 -0
adapter_config.json +40 -0
adapters.safetensors +3 -0

0000200_adapters.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:54344b95471da867774e2667b5f058750fd4213dd9f056ce13171e01c37d71ac
+size 46161566

0000400_adapters.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:65e15679fae571bdc480bf0a99d91b74ea0fe17f484886fc9882ab16ff8c03e3
+size 46161566

0000600_adapters.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e66f568b437464e6c0690b5870aeef4591c19318230b1767241568afe535179f
+size 46161566

0000800_adapters.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f51c73e4c85f71e6ff46610aee62b248fdae7c272dc5bce08d9b2e600c6f9c6f
+size 46161566

0001000_adapters.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f33565f4f7926e9f58963de97e0bc08f58ed33283b3db2e5b8b919157be80ea
+size 46161566

README.md ADDED Viewed

	@@ -0,0 +1,22 @@

+---
+base_model: mlx-community/Qwen2.5-Coder-32B-Instruct-4bit
+library_name: mlx
+tags: [mlx, lora, ocm, oci, go]
+---
+# ocm-coder
+LoRA adapters fine-tuned on the Open Component Model (OCM) and OCI specification ecosystem.
+**Base model:** [mlx-community/Qwen2.5-Coder-32B-Instruct-4bit](https://huggingface.co/mlx-community/Qwen2.5-Coder-32B-Instruct-4bit)
+## Usage
+```python
+from mlx_lm import load, generate
+model, tokenizer = load(
+    "mlx-community/Qwen2.5-Coder-32B-Instruct-4bit",
+    adapter_path="piotrjanik/ocm-coder",
+)
+```

adapter_config.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+    "adapter_path": "output/adapters",
+    "batch_size": 4,
+    "config": "output/lora_train_config.yaml",
+    "data": "output/mlx_data",
+    "fine_tune_type": "lora",
+    "grad_accumulation_steps": 1,
+    "grad_checkpoint": false,
+    "iters": 1000,
+    "learning_rate": 1e-05,
+    "lora_parameters": {
+        "dropout": 0.0,
+        "rank": 8,
+        "scale": 10.0
+    },
+    "lr_schedule": null,
+    "mask_prompt": false,
+    "max_seq_length": 4096,
+    "model": "mlx-community/Qwen2.5-Coder-7B-Instruct-4bit",
+    "num_layers": 16,
+    "optimizer": "adam",
+    "optimizer_config": {
+        "adam": {},
+        "adamw": {},
+        "muon": {},
+        "sgd": {},
+        "adafactor": {}
+    },
+    "project_name": null,
+    "report_to": null,
+    "resume_adapter_file": null,
+    "save_every": 200,
+    "seed": 42,
+    "steps_per_eval": 200,
+    "steps_per_report": 10,
+    "test": false,
+    "test_batches": 500,
+    "train": true,
+    "val_batches": 25
+}

adapters.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f33565f4f7926e9f58963de97e0bc08f58ed33283b3db2e5b8b919157be80ea
+size 46161566