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

Libraries

How to use devaloper/codeas with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="devaloper/codeas",
	filename="codeas-model-Q6_K.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 devaloper/codeas 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 devaloper/codeas:Q6_K
# Run inference directly in the terminal:
llama cli -hf devaloper/codeas:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf devaloper/codeas:Q6_K
# Run inference directly in the terminal:
llama cli -hf devaloper/codeas:Q6_K

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 devaloper/codeas:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf devaloper/codeas:Q6_K

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 devaloper/codeas:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf devaloper/codeas:Q6_K

Use Docker

docker model run hf.co/devaloper/codeas:Q6_K

LM Studio
Jan

vLLM

How to use devaloper/codeas with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/devaloper/codeas:Q6_K

Ollama
How to use devaloper/codeas with Ollama:
```
ollama run hf.co/devaloper/codeas:Q6_K
```

Unsloth Studio

How to use devaloper/codeas 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 devaloper/codeas 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 devaloper/codeas to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for devaloper/codeas to start chatting

How to use devaloper/codeas with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devaloper/codeas:Q6_K

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": "devaloper/codeas:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use devaloper/codeas with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devaloper/codeas:Q6_K

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 devaloper/codeas:Q6_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use devaloper/codeas with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devaloper/codeas:Q6_K

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 "devaloper/codeas:Q6_K" \
  --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"

Docker Model Runner
How to use devaloper/codeas with Docker Model Runner:
```
docker model run hf.co/devaloper/codeas:Q6_K
```

Lemonade

How to use devaloper/codeas with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull devaloper/codeas:Q6_K

Run and chat with the model

lemonade run user.codeas-Q6_K

List all available models

lemonade list

codeas / README.md

devaloper

Update README.md

64a3d35 verified 4 months ago

preview code

Raw

History Blame Contribute Delete

2.42 kB

	---
	license: apache-2.0
	library_name: gguf
	base_model: Qwen/Qwen3-14B
	tags:
	- code
	- qwen3
	- gguf
	- fine-tuned
	- conversational
	model-index:
	- name: Codeas Model
	results: []
	pipeline_tag: text-generation
	language:
	- en
	---

	# Codeas Model

	A fine-tuned Qwen3-14B model optimized for code generation and reasoning tasks. Available in GGUF Q6_K format for efficient local inference.

	## Model Details

	\| \| \|
	\|---\|---\|
	\| Base Model \| Qwen3-14B \|
	\| Parameters \| ~15B \|
	\| Architecture \| Qwen3 (GQA, RoPE) \|
	\| Context Length \| 40,960 tokens \|
	\| Precision \| BF16 (original), Q6_K (GGUF) \|
	\| License \| Apache 2.0 \|

	## Architecture

	- 40 transformer blocks
	- 40 attention heads, 8 KV heads (Grouped Query Attention)
	- 5,120 hidden size / 17,408 FFN size
	- RoPE with 1M frequency base
	- SiLU activation
	- 151,936 vocab size (GPT-2 tokenizer, Qwen2 pre-tokenizer)

	## Capabilities

	- Chain-of-thought reasoning via `<think>` blocks
	- Tool/function calling via `<tool_call>` format
	- Thinking mode can be toggled on/off per request

	## GGUF Quantizations

	\| File \| Quant \| Size \| Quality \|
	\|------\|-------\|------\|---------\|
	\| `codeas-model-Q6_K.gguf` \| Q6_K \| 12.1 GB \| Near-lossless \|

	## Usage

	### llama.cpp

	```bash
	./llama-cli -m codeas-model-Q6_K.gguf -p "Write a Python function to merge two sorted lists" -n 512
	```

	### Ollama

	Create a `Modelfile` with the following content:

	```dockerfile
	FROM ./codeas-model-Q6_K.gguf

	PARAMETER temperature 0.6
	PARAMETER top_p 0.95
	PARAMETER top_k 20

	TEMPLATE """{{- if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	{{ end }}<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>
	<\|im_start\|>assistant
	"""

	SYSTEM "You are Codeas, a helpful coding assistant."
	```

	Then run:

	```bash
	ollama create codeas -f Modelfile
	ollama run codeas
	```

	## Hardware Requirements

	\| Format \| VRAM / RAM \|
	\|--------\|-----------\|
	\| Q6_K GGUF \| ~14 GB \|

	## Training

	\| \| \|
	\|---\|---\|
	\| Method \| Full fine-tune (no LoRA) \|
	\| Framework \| Axolotl 0.13.0 + Transformers 4.55.4 \|
	\| Hardware \| 8x GPU (FSDP) \|
	\| Optimizer \| AdamW (fused) \|
	\| LR Schedule \| Cosine, 1e-5 peak \|
	\| Sequence Length \| 8,192 \|
	\| Batch Size \| 24 (3 per device) \|
	\| Epochs \| 3 \|
	\| Precision \| BF16 + TF32 \|
	\| Techniques \| Flash Attention, Sample Packing, Gradient Checkpointing, Activation Offloading \|

	## Sampling Defaults

	```
	temperature: 0.6
	top_p: 0.95
	top_k: 20
	```