Text Generation
ONNX
Safetensors
GGUF
English
Arabic
qwen2
conversational
small-language-model
edge-ai
raspberry-pi
arm
lora
Instructions to use srmortal/SilentVision-52M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use srmortal/SilentVision-52M 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 srmortal/SilentVision-52M:Q4_K_M # Run inference directly in the terminal: llama cli -hf srmortal/SilentVision-52M:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf srmortal/SilentVision-52M:Q4_K_M # Run inference directly in the terminal: llama cli -hf srmortal/SilentVision-52M:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf srmortal/SilentVision-52M:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf srmortal/SilentVision-52M:Q4_K_M
Use Docker
docker model run hf.co/srmortal/SilentVision-52M:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use srmortal/SilentVision-52M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "srmortal/SilentVision-52M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "srmortal/SilentVision-52M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/srmortal/SilentVision-52M:Q4_K_M
- Ollama
How to use srmortal/SilentVision-52M with Ollama:
ollama run hf.co/srmortal/SilentVision-52M:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use srmortal/SilentVision-52M with Docker Model Runner:
docker model run hf.co/srmortal/SilentVision-52M:Q4_K_M
- Lemonade
How to use srmortal/SilentVision-52M with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull srmortal/SilentVision-52M:Q4_K_M
Run and chat with the model
lemonade run user.SilentVision-52M-Q4_K_M
List all available models
lemonade list
- Atomic Chat
build task: GitHub CPU execution provenance
Browse files
ci/tasks/a3a5008bca4d8d0ddee638231863a8127849fc7c2502c2ff61cabdadcda01016.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_source": null,
|
| 3 |
+
"code_repository": "Srmortal/tiny-bilingual-llm",
|
| 4 |
+
"code_revision": "a916f1a38ecfbc61c91345dd59ad8fec3cb52714",
|
| 5 |
+
"code_snapshot": {
|
| 6 |
+
"path": "ci/build-code/c7142fdfaa7ffa5844371c2e7f86c9bb24adcc776d2a0ff35041a59faac839a9.tar.gz",
|
| 7 |
+
"repo": "srmortal/SilentVision-52M",
|
| 8 |
+
"sha256": "c7142fdfaa7ffa5844371c2e7f86c9bb24adcc776d2a0ff35041a59faac839a9"
|
| 9 |
+
},
|
| 10 |
+
"gguf_publish_prefix": "gguf/silentvision_general_unlearned_v1",
|
| 11 |
+
"identity": {
|
| 12 |
+
"content_sha256": "d17325f5ac11fbf805873a83d2ab51e6e9e1dbcd10dca45d18905e936727f077",
|
| 13 |
+
"links_sha256": "6cc89bfd94e57050af683183989c1688cca300a47bcb45d795be2d59fc5b45d9",
|
| 14 |
+
"recipe_sha256": "cf09ceb0c4015bc695d7c8ab67d59ee5ab8e36fa3bebdd1b35e24ea28773a580",
|
| 15 |
+
"selection_sha256": "24b3f0778071568ab53192aa115f4bcbaeac90a6bb599534aa7f2f09edd45a55",
|
| 16 |
+
"target_sha256": "a809cd62d7caa752fa7970505b871fb9dae4a4d8efa8926846a3ba3514ffc948"
|
| 17 |
+
},
|
| 18 |
+
"kind": "base",
|
| 19 |
+
"package_id": "base",
|
| 20 |
+
"recipe": {
|
| 21 |
+
"converter_hashes": {
|
| 22 |
+
"configs/model.yaml": "68fc868e3675b5a9c92e88af83a4911183962c82d8878a459124fba058c23ebe",
|
| 23 |
+
"configs/pi_target.yaml": "da46ce6253e9be10a494247196f42815e2cd74214b2b759d38f0162dec9e8986",
|
| 24 |
+
"scripts/export_gguf.py": "900735dcca92841bb622705b67fcc499e698a29d11d4d395fd8bf6dbb8c12a36",
|
| 25 |
+
"src/deployment/export_qwen_gguf.py": "708c55c8f73a8880bf2699d3176177951df2ccfd6263e6c76197fabc4a4866ea"
|
| 26 |
+
},
|
| 27 |
+
"execution": {
|
| 28 |
+
"backend": "github-actions-cpu",
|
| 29 |
+
"python": "3.11",
|
| 30 |
+
"runner": "ubuntu-latest",
|
| 31 |
+
"timeout_minutes": 35
|
| 32 |
+
},
|
| 33 |
+
"format": "Q4_K_M",
|
| 34 |
+
"kind": "base",
|
| 35 |
+
"quantizations": [
|
| 36 |
+
"F16",
|
| 37 |
+
"Q4_K_M",
|
| 38 |
+
"Q8_0"
|
| 39 |
+
],
|
| 40 |
+
"tool_revision": "master",
|
| 41 |
+
"worker_sha256": "d57bd80eed0976877d3b07e15d1227353441fa2d56f0372cf94abc002ce7aeac"
|
| 42 |
+
},
|
| 43 |
+
"repo": "srmortal/SilentVision-52M",
|
| 44 |
+
"source": {
|
| 45 |
+
"checkpoint_sha256": "d17325f5ac11fbf805873a83d2ab51e6e9e1dbcd10dca45d18905e936727f077",
|
| 46 |
+
"hf_folder": "candidates/d17325f5ac11fbf805873a83d2ab51e6e9e1dbcd10dca45d18905e936727f077",
|
| 47 |
+
"hf_repo": "srmortal/SilentVision-52M",
|
| 48 |
+
"hf_revision": "dd6048d6d055226d22bbbb847597f336241a01e0",
|
| 49 |
+
"llama_cpp_revision": "master",
|
| 50 |
+
"publish": false
|
| 51 |
+
}
|
| 52 |
+
}
|