Instructions to use singularity-layer/Singularity-xMESH-0.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use singularity-layer/Singularity-xMESH-0.8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="singularity-layer/Singularity-xMESH-0.8B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("singularity-layer/Singularity-xMESH-0.8B")
model = AutoModelForMultimodalLM.from_pretrained("singularity-layer/Singularity-xMESH-0.8B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use singularity-layer/Singularity-xMESH-0.8B 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 singularity-layer/Singularity-xMESH-0.8B:BF16
# Run inference directly in the terminal:
llama cli -hf singularity-layer/Singularity-xMESH-0.8B:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf singularity-layer/Singularity-xMESH-0.8B:BF16
# Run inference directly in the terminal:
llama cli -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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 singularity-layer/Singularity-xMESH-0.8B:BF16
# Run inference directly in the terminal:
./llama-cli -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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 singularity-layer/Singularity-xMESH-0.8B:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf singularity-layer/Singularity-xMESH-0.8B:BF16

Use Docker

docker model run hf.co/singularity-layer/Singularity-xMESH-0.8B:BF16

LM Studio
Jan

vLLM

How to use singularity-layer/Singularity-xMESH-0.8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "singularity-layer/Singularity-xMESH-0.8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "singularity-layer/Singularity-xMESH-0.8B",
		"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/singularity-layer/Singularity-xMESH-0.8B:BF16

SGLang

How to use singularity-layer/Singularity-xMESH-0.8B 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 "singularity-layer/Singularity-xMESH-0.8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "singularity-layer/Singularity-xMESH-0.8B",
		"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 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 "singularity-layer/Singularity-xMESH-0.8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "singularity-layer/Singularity-xMESH-0.8B",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use singularity-layer/Singularity-xMESH-0.8B with Ollama:
```
ollama run hf.co/singularity-layer/Singularity-xMESH-0.8B:BF16
```
Unsloth Desktop

How to use singularity-layer/Singularity-xMESH-0.8B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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": "singularity-layer/Singularity-xMESH-0.8B:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use singularity-layer/Singularity-xMESH-0.8B with Docker Model Runner:
```
docker model run hf.co/singularity-layer/Singularity-xMESH-0.8B:BF16
```

Lemonade

How to use singularity-layer/Singularity-xMESH-0.8B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull singularity-layer/Singularity-xMESH-0.8B:BF16

Run and chat with the model

lemonade run user.Singularity-xMESH-0.8B-BF16

List all available models

lemonade list

Hermes Agent

How to use singularity-layer/Singularity-xMESH-0.8B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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 singularity-layer/Singularity-xMESH-0.8B:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use singularity-layer/Singularity-xMESH-0.8B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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 "singularity-layer/Singularity-xMESH-0.8B:BF16" \
  --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"

ivaavi commited on 5 days ago

Commit

6bb813a

verified ·

1 Parent(s): d9b6f1a

Bind portability claims to the proven release path

Browse files

Record the production Vulkan distributions running at zero GPU layers on Windows and Linux, publish the 8 GB memory floor, and preserve mixed upstream dataset attribution in the release package.

Files changed (6) hide show

ATTRIBUTION.md +1 -1
MANIFEST.json +11 -11
PLATFORM_CANARIES.json +12 -6
PORTABILITY.md +5 -3
README.md +2 -2
THIRD_PARTY_NOTICES.md +9 -0

ATTRIBUTION.md CHANGED Viewed

@@ -1,3 +1,3 @@
 # Attribution
-Singularity xMESH 0.8B was trained and evaluated with Singularity Training Lab. It derives from the Apache-2.0 Qwen3.5 0.8B model and uses the Apache-2.0 Cloudflare Clef joint-schema architecture for typed decisions. Singularity Layer supplies the x402 specialization, calibrated weights, evaluation, deterministic policy, packaging, and runtime integration.


1	# Attribution
2
3	+ Singularity xMESH 0.8B was trained and evaluated with Singularity Training Lab. It derives from the Apache-2.0 Qwen3.5 0.8B model and uses the Apache-2.0 Cloudflare Clef joint-schema architecture for typed decisions. General decision warm-up used `MaziyarPanahi/AgentToolDecisions-180K`, which retains mixed CC BY 4.0, Apache-2.0, and MIT source terms per row. Singularity Layer supplies the x402 specialization, calibrated weights, evaluation, deterministic policy, packaging, and runtime integration.

MANIFEST.json CHANGED Viewed

@@ -3,7 +3,7 @@
   "algorithm": "sha256",
   "base_model": "Qwen/Qwen3.5-0.8B@2fc06364715b967f1860aea9cf38778875588b17",
   "file_count": 46,
-  "total_bytes": 4246356881,
   "files": [
     {
       "path": ".gitignore",
@@ -12,8 +12,8 @@
     },
     {
       "path": "ATTRIBUTION.md",
-      "bytes": 374,
-      "sha256": "b09fec7297b4a73910af21fcddc05def7ed79da15585bf927704d38b4b976d94"
     },
     {
       "path": "FINAL_EVALUATION.json",
@@ -52,18 +52,18 @@
     },
     {
       "path": "PLATFORM_CANARIES.json",
-      "bytes": 2085,
-      "sha256": "27adb372505a4afeac44492b5a9024a11ffbb94278876547246814ff2a8ab531"
     },
     {
       "path": "PORTABILITY.md",
-      "bytes": 2469,
-      "sha256": "3c54df61bcd2894aa52b1cbb0de4d0e5f82107153df548b06ebe27dc84bafd4d"
     },
     {
       "path": "README.md",
-      "bytes": 7518,
-      "sha256": "98d40ad5260f48a3bf1e2c93dec543f0a01295e8fa53e8a75d5b3752f7c4dab1"
     },
     {
       "path": "Singularity-xMESH-0.8B-BF16.gguf",
@@ -77,8 +77,8 @@
     },
     {
       "path": "THIRD_PARTY_NOTICES.md",
-      "bytes": 389,
-      "sha256": "cd3c4d8a155112145b1dbf132931cf493b087c24063209a6c07284d9c3808a1d"
     },
     {
       "path": "VALIDATION.md",

   "algorithm": "sha256",
   "base_model": "Qwen/Qwen3.5-0.8B@2fc06364715b967f1860aea9cf38778875588b17",
   "file_count": 46,
+  "total_bytes": 4246358346,
   "files": [
     {
       "path": ".gitignore",
     },
     {
       "path": "ATTRIBUTION.md",
+      "bytes": 518,
+      "sha256": "2277a70986ac418718256b0b5dc604a0d60e97ec9084e81b546c9d04f47536ec"
     },
     {
       "path": "FINAL_EVALUATION.json",
     },
     {
       "path": "PLATFORM_CANARIES.json",
+      "bytes": 2516,
+      "sha256": "c7e1035e539162534bf852d2eb4c094460a35f062cd06f414face3067b54864e"
     },
     {
       "path": "PORTABILITY.md",
+      "bytes": 2672,
+      "sha256": "9e8b1ff94a3c5ab96ae094332d62d93f9d7890f8a0fca38884b1b530be9ee3d1"
     },
     {
       "path": "README.md",
+      "bytes": 7667,
+      "sha256": "862414dd044146022e8cbcd0bdea6ff9cf16e3cce18d980cd35dff65acee1e4c"
     },
     {
       "path": "Singularity-xMESH-0.8B-BF16.gguf",
     },
     {
       "path": "THIRD_PARTY_NOTICES.md",
+      "bytes": 927,
+      "sha256": "bbf4dec8f637ab3af8e196f74e723ad3852f5b2852d4207bfab200191c280498"
     },
     {
       "path": "VALIDATION.md",

PLATFORM_CANARIES.json CHANGED Viewed

@@ -35,21 +35,27 @@
     },
     "linux_x64_cpu": {
       "status": "passed",
-      "environment": "GitHub Actions ubuntu-24.04 x64, libgomp1",
-      "workflow_run": "Singularity-Layer/sgl-network-node/actions/runs/39157338563",
       "fixture_input_tokens": 1012,
       "expected_decisions": 9,
       "matching_decisions": 9,
-      "latency_ms": 17260.950348000002
     },
     "windows_x64_cpu": {
       "status": "passed",
-      "environment": "GitHub Actions windows-2025-vs2026 x64",
-      "workflow_run": "Singularity-Layer/sgl-network-node/actions/runs/39157338563",
       "fixture_input_tokens": 1012,
       "expected_decisions": 9,
       "matching_decisions": 9,
-      "latency_ms": 10923.7665
     }
   }
 }

     },
     "linux_x64_cpu": {
       "status": "passed",
+      "environment": "GitHub Actions ubuntu-24.04 x64, Vulkan distribution with -ngl 0, libgomp1 and libvulkan1",
+      "workflow_run": "Singularity-Layer/sgl-network-node/actions/runs/39158899243",
+      "archive": "llama-b11719-bin-ubuntu-vulkan-x64.tar.gz",
+      "archive_sha256": "9a09cce245acf8823feb99fb7ba8ddd3e878e3827564888131e0185044aa4429",
+      "gpu_layers": 0,
       "fixture_input_tokens": 1012,
       "expected_decisions": 9,
       "matching_decisions": 9,
+      "latency_ms": 17155.671278
     },
     "windows_x64_cpu": {
       "status": "passed",
+      "environment": "GitHub Actions windows-2025-vs2026 x64, Vulkan distribution with -ngl 0",
+      "workflow_run": "Singularity-Layer/sgl-network-node/actions/runs/39158899243",
+      "archive": "llama-b11719-bin-win-vulkan-x64.zip",
+      "archive_sha256": "08dde7f4133443ac629431c35f0435e267ca73251fc002cb95e10625424e2963",
+      "gpu_layers": 0,
       "fixture_input_tokens": 1012,
       "expected_decisions": 9,
       "matching_decisions": 9,
+      "latency_ms": 10955.597100000006
     }
   }
 }

PORTABILITY.md CHANGED Viewed

@@ -8,6 +8,8 @@ Singularity Node must serve xMESH through the same `/v1/systemone` request and r
 - Context: 2,048 tokens per request.
 - Physical batch: 2,048 tokens. The llama.cpp default of 512 rejects normal multi-field requests.
 - Default concurrency: one slot. Higher concurrency requires a platform-specific canary.
 ## Artifacts
@@ -23,9 +25,9 @@ Q8 passes the full Metal decision-parity suite but crashes in llama.cpp `b11719`
 | Surface | Target | Artifact | Status |
 | --- | --- | --- | --- |
 | Desktop | macOS Apple silicon | BF16 | Local CPU and Metal canaries passed; packaged-app canary pending |
-| Desktop / Node | Windows x64 CPU | BF16 | Native Windows 2025 x64 canary passed 9/9 decisions |
-| Node CLI | Linux x64 CPU/Vulkan | BF16 | Native Ubuntu 24.04 x64 canary passed 9/9 decisions |
-| Node CLI | Linux ARM64 CPU/Vulkan | BF16 | CPU load and real decision canary passed in Ubuntu 24.04 ARM64 |
 The desktop release workflow does not currently publish Linux or Intel Mac packages. The Node CLI covers Linux; Intel Mac desktop support requires a separate release target.

 - Context: 2,048 tokens per request.
 - Physical batch: 2,048 tokens. The llama.cpp default of 512 rejects normal multi-field requests.
 - Default concurrency: one slot. Higher concurrency requires a platform-specific canary.
+- Portable Node execution: CPU (`-ngl 0`). GPU offload remains disabled until accelerator-specific decision parity passes.
+- System memory: 8 GB minimum; 16 GB recommended.
 ## Artifacts
 | Surface | Target | Artifact | Status |
 | --- | --- | --- | --- |
 | Desktop | macOS Apple silicon | BF16 | Local CPU and Metal canaries passed; packaged-app canary pending |
+| Desktop / Node | Windows x64 CPU | BF16 | Production Vulkan distribution with `-ngl 0` passed 9/9 decisions |
+| Node CLI | Linux x64 CPU | BF16 | Production Vulkan distribution with `-ngl 0` passed 9/9 decisions on Ubuntu 24.04 |
+| Node CLI | Linux ARM64 CPU | BF16 | CPU load and real decision canary passed in Ubuntu 24.04 ARM64 |
 The desktop release workflow does not currently publish Linux or Intel Mac packages. The Node CLI covers Linux; Intel Mac desktop support requires a separate release target.

README.md CHANGED Viewed

@@ -47,7 +47,7 @@ Output: candidate selection or abstention, calibrated confidence, approval requi
 ## Training data
-The general decision warm-up used licensed rows from [`MaziyarPanahi/AgentToolDecisions-180K`](https://huggingface.co/datasets/MaziyarPanahi/AgentToolDecisions-180K). Singularity-curated x402 rows supplied the routing specialization. Frozen evaluation cases and resources were excluded from training.
 ## Hardware compatibility
@@ -57,7 +57,7 @@ The general decision warm-up used licensed rows from [`MaziyarPanahi/AgentToolDe
 | CPU | **Verified**; portable but slower |
 | llama.cpp Metal | **Verified** with the Q8 GGUF on an Apple M4 |
 | llama.cpp Windows/Linux x64 CPU | **Verified**; native canaries passed 9/9 expected decisions on both platforms |
-| NVIDIA CUDA | Supported by the PyTorch runtime; standalone CUDA canary pending |
 | AMD ROCm | Not verified |
 The checkpoint contains 873M BF16 parameters. An 8 GB system is the practical minimum; 16 GB is recommended for comfortable local loading and inference.

 ## Training data
+The general decision warm-up used licensed rows from [`MaziyarPanahi/AgentToolDecisions-180K`](https://huggingface.co/datasets/MaziyarPanahi/AgentToolDecisions-180K). That dataset retains mixed CC BY 4.0, Apache-2.0, and MIT source terms per row; see `THIRD_PARTY_NOTICES.md`. Singularity-curated x402 rows supplied the routing specialization. Frozen evaluation cases and resources were excluded from training.
 ## Hardware compatibility
 | CPU | **Verified**; portable but slower |
 | llama.cpp Metal | **Verified** with the Q8 GGUF on an Apple M4 |
 | llama.cpp Windows/Linux x64 CPU | **Verified**; native canaries passed 9/9 expected decisions on both platforms |
+| NVIDIA CUDA | PyTorch runtime support only; Singularity Node GPU offload is disabled pending decision-parity canaries |
 | AMD ROCm | Not verified |
 The checkpoint contains 873M BF16 parameters. An 8 GB system is the practical minimum; 16 GB is recommended for comfortable local loading and inference.

THIRD_PARTY_NOTICES.md CHANGED Viewed

@@ -12,3 +12,12 @@
 - Pinned revision: `0b331204bb13fbd2ca93a64df1956f5b55478ce5`
 - License: Apache-2.0
 - The complete notice and license are included with this repository.

 - Pinned revision: `0b331204bb13fbd2ca93a64df1956f5b55478ce5`
 - License: Apache-2.0
 - The complete notice and license are included with this repository.
+## Agent Tool Decisions 180K
+- Upstream: `MaziyarPanahi/AgentToolDecisions-180K`
+- Use: general typed-decision warm-up rows
+- License: mixed upstream terms recorded per row
+- Sources: pinned revisions of `nvidia/Nemotron-SFT-Agentic-v2` and `nvidia/When2Call`
+- Terms: When2Call is CC BY 4.0. The Nemotron source card lists CC BY 4.0, Apache-2.0, and MIT terms across its components.
+- Attribution and source-license metadata are retained in the upstream dataset. Review the linked source cards before redistributing the training rows.