Instructions to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF 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 peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S
# Run inference directly in the terminal:
llama cli -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S
# Run inference directly in the terminal:
llama cli -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

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 peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

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 peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

Use Docker

docker model run hf.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

LM Studio
Jan

vLLM

How to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "peculiar-ragdoll/Tiel-Coder-35B-A3B-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": "peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

Ollama
How to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S
```
Unsloth Desktop

How to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S
```

Lemonade

How to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

Run and chat with the model

lemonade run user.Tiel-Coder-35B-A3B-GGUF-UD-Q4_K_S

List all available models

lemonade list

Hermes Agent

How to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

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 peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S

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 "peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF:UD-Q4_K_S" \
  --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"

UD-Q4_K_XL blows UD-Q8_K_XL out of the water in my benchmarks - is UD-Q8_K_XL broken?

#19

by EmilPi - opened 14 days ago

Discussion

EmilPi

14 days ago

I think it really is. It can't be that in the case Q4_K_XL generates a fully working program Q8_K_XL generates a lot of syntax errors and still broken even after manually fixing those. Same for other than coding domains. Tested on my mix of private/public tasks benchmark.
Can you look into this?
I can add details and example prompts if needed.

brigar

14 days ago

I think it really is. It can't be that in the case Q4_K_XL generates a fully working program Q8_K_XL generates a lot of syntax errors and still broken even after manually fixing those. Same for other than coding domains. Tested on my mix of private/public tasks benchmark.
Can you look into this?
I can add details and example prompts if needed.

Have you tried using the same seed?

EmilPi

13 days ago

•

edited 13 days ago

I didn't but I evaluated it over >20 different tasks, and the results are consistent.
For the non-coding tasks the difference is small, but somewhat exists too.
The only peculiarity is that these tasks are one-shot (so far) . Do you think it is important / worth a try? I have to break my job queue to test that now.

brigar

13 days ago

I didn't but I evaluated it over >20 different tasks, and the results are consistent.
For the non-coding tasks the difference is small, but somewhat exists too.
The only peculiarity is that these tasks are one-shot (so far) . Do you think it is important / worth a try? I have to break my job queue to test that now.

Try these values
This is my template from the model run bash script
MAX_TOKENS and MAX_CTX - You can install your own

TEMP=0.60
TOP_P=0.95
TOP_K=20
MIN_P=0.0
PRESENCE_PENALTY=0.0
REPEAT_PENALTY=1.00
FREQUENCY_PENALTY=0.0
DRY_MULTIPLIER=0.5
DRY_PENALTY_LAST_N=2052
REPEAT_LAST_N=1024
MAX_TOKENS=32768
MAX_CTX=262144
SEED=42

Even with seed, the determinism can fluctuate, so after all the tests, try reducing the temperature to 0.30 or, if you're really bloodthirsty :), to 0.00
Share your tests, it's very interesting, let's try to figure it out.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment