Instructions to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF",
	filename="Ornstein3.6-35B-A3B-RYS-F16.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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

Use Docker

docker model run hf.co/GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

LM Studio
Jan

vLLM

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GestaltLabs/Ornstein3.6-35B-A3B-RYS-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": "GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

Ollama
How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF with Ollama:
```
ollama run hf.co/GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16
```

Unsloth Studio

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF 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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF 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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF to start chatting

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

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": "GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

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 "GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16" \
  --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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF with Docker Model Runner:
```
docker model run hf.co/GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16
```

Lemonade

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GestaltLabs/Ornstein3.6-35B-A3B-RYS-GGUF:F16

Run and chat with the model

lemonade run user.Ornstein3.6-35B-A3B-RYS-GGUF-F16

List all available models

lemonade list

Ornstein3.6-35B-A3B-RYS-Q6_K.gguf throws llama-cli error: "missing tensor 'blk.11.attn_q.weight'"

by SkyMind - opened Apr 24

Discussion

SkyMind

Apr 24

Attempting to run with llama-cli:

create_tensor: loading tensor blk.10.ffn_up_exps.weight
create_tensor: loading tensor blk.10.ffn_gate_inp_shexp.weight
create_tensor: loading tensor blk.10.ffn_gate_shexp.weight
create_tensor: loading tensor blk.10.ffn_up_shexp.weight
create_tensor: loading tensor blk.10.ffn_down_shexp.weight
create_tensor: loading tensor blk.11.attn_norm.weight
create_tensor: loading tensor blk.11.post_attention_norm.weight
llama_model_load: error loading model: missing tensor 'blk.11.attn_q.weight'
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model './Ornstein3.6-35B-A3B-RYS-Q6_K.gguf'
srv    load_model: failed to load model, './Ornstein3.6-35B-A3B-RYS-Q6_K.gguf'
 
Failed to load the model

~/code/llama.cpp/gguf-py/gguf/scripts/gguf_dump.py Ornstein3.6-35B-A3B-RYS-Q6_K.gguf | grep "attn_q.weight"

yields:

INFO:gguf-dump:* Loading: Ornstein3.6-35B-A3B-RYS-Q6_K.gguf
     65:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.3.attn_q.weight
    138:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.7.attn_q.weight
    230:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.12.attn_q.weight
    303:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.16.attn_q.weight
    376:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.20.attn_q.weight
    449:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.24.attn_q.weight
    522:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.28.attn_q.weight
    595:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.32.attn_q.weight
    668:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.36.attn_q.weight
    741:   16777216 |  2048,  8192,     1,     1 | Q6_K    | blk.40.attn_q.weight

SkyMind

Apr 24

I saw that other RYS models use a forked llama.cpp. Using that,

'''~/code/DJLougen/llama.cpp-rys-qwen35/build/bin/llama-cli -m ./Ornstein3.6-35B-A3B-RYS-Q6_K.gguf --min-p 0.01 --temp 1.0 --top-p 0.95 --top-k 20 -c 65536 -ngl 18```

still gives

Loading model... |llama_model_load: error loading model: missing tensor 'blk.11.attn_q.weight'
llama_model_load_from_file_impl: failed to load model

and the forked code gguf_dump.py output is unchanged.

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