Instructions to use Mike0021/Ling-3.0-tiny-GGUF 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 Mike0021/Ling-3.0-tiny-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 Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
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 Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
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 Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Mike0021/Ling-3.0-tiny-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Mike0021/Ling-3.0-tiny-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": "Mike0021/Ling-3.0-tiny-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
- Ollama
How to use Mike0021/Ling-3.0-tiny-GGUF with Ollama:
ollama run hf.co/Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
- Unsloth Studio
How to use Mike0021/Ling-3.0-tiny-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 Mike0021/Ling-3.0-tiny-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 Mike0021/Ling-3.0-tiny-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Mike0021/Ling-3.0-tiny-GGUF to start chatting
- Pi
How to use Mike0021/Ling-3.0-tiny-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
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": "Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- OpenClaw new
How to use Mike0021/Ling-3.0-tiny-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
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 "Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M" \ --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 Mike0021/Ling-3.0-tiny-GGUF with Docker Model Runner:
docker model run hf.co/Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
- Lemonade
How to use Mike0021/Ling-3.0-tiny-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Ling-3.0-tiny-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Mike0021/Ling-3.0-tiny-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 Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
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 Mike0021/Ling-3.0-tiny-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
| { | |
| "artifacts": [ | |
| { | |
| "bytes": 15803475232, | |
| "filename": "Ling-3.0-tiny-BF16.gguf", | |
| "hub_introduced_in_commit": "5181b83cba18aa36484eb4f385479ddc015f37ea", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": null, | |
| "metadata_count": 55, | |
| "quantization": "BF16", | |
| "role": "model", | |
| "sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "source_weights_manifest": "source-safetensors.sha256", | |
| "source_weights_manifest_sha256": "d8a7cf059fd4b4f2fd7f7d0b1118417be02f7b39a5c428461c027f5d71faff6d", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "BF16": 311, | |
| "F32": 215 | |
| }, | |
| "validation_reports": { | |
| "context": "validation/context-results.json", | |
| "generation": "validation/generation-BF16.json", | |
| "kld": "validation/kld-results.json", | |
| "multiple_choice": "validation/multiple-choice-results.json", | |
| "structure": "validation/structure-BF16.json" | |
| } | |
| }, | |
| { | |
| "bytes": 8408187744, | |
| "filename": "Ling-3.0-tiny-Q8_0.gguf", | |
| "hub_introduced_in_commit": "6ed6298b7b0b41c8db02d6773e6172e03745df55", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": null, | |
| "metadata_count": 55, | |
| "quantization": "Q8_0", | |
| "role": "model", | |
| "sha256": "326221bdef72525bd6178b072d3827cd5fb5248a55e8c44eb400417f401733bc", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "Q8_0": 311 | |
| }, | |
| "validation_reports": { | |
| "generation": "validation/generation-Q8_0.json", | |
| "kld": "validation/kld-results.json", | |
| "structure": "validation/structure-Q8_0.json" | |
| } | |
| }, | |
| { | |
| "bytes": 6499262560, | |
| "filename": "Ling-3.0-tiny-Q6_K.gguf", | |
| "hub_introduced_in_commit": "b0d10c82afeb64ea0528ec4550c5b15a071ed4e4", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "metadata_count": 59, | |
| "quantization": "Q6_K", | |
| "role": "model", | |
| "sha256": "480acd6ef2c664f026f1452548221a00954e9888393c6f49a425dd5567a3d77a", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "Q6_K": 305, | |
| "Q8_0": 6 | |
| }, | |
| "validation_reports": { | |
| "generation": "validation/generation-Q6_K.json", | |
| "kld": "validation/kld-results.json", | |
| "structure": "validation/structure-Q6_K.json" | |
| } | |
| }, | |
| { | |
| "bytes": 5635443808, | |
| "filename": "Ling-3.0-tiny-Q5_K_M.gguf", | |
| "hub_introduced_in_commit": "d50633f06287cb120a9f9bd3d06843b08ab38c69", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "metadata_count": 59, | |
| "quantization": "Q5_K_M", | |
| "role": "model", | |
| "sha256": "77d35bfd5ceaa03eff4d48af4438240f48ef4b6f5a70dff3cf25e78933b742ad", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "Q5_1": 6, | |
| "Q5_K": 272, | |
| "Q6_K": 33 | |
| }, | |
| "validation_reports": { | |
| "generation": "validation/generation-Q5_K_M.json", | |
| "kld": "validation/kld-results.json", | |
| "multiple_choice": "validation/multiple-choice-results.json", | |
| "structure": "validation/structure-Q5_K_M.json" | |
| } | |
| }, | |
| { | |
| "bytes": 4823895136, | |
| "filename": "Ling-3.0-tiny-Q4_K_M.gguf", | |
| "hub_introduced_in_commit": "4cb7775c71f0c269ced22d475118be72add13a5a", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "metadata_count": 59, | |
| "quantization": "Q4_K_M", | |
| "role": "model", | |
| "sha256": "40e2d1201acdb346f4faa4cd8c2ce39b69d5fc9820baa17430ecd87cbdda7db5", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "Q4_K": 272, | |
| "Q5_0": 6, | |
| "Q6_K": 33 | |
| }, | |
| "validation_reports": { | |
| "context": "validation/context-results.json", | |
| "generation": "validation/generation-Q4_K_M.json", | |
| "imatrix_ablation": "validation/kld-Q4_K_M-ab.json", | |
| "kld": "validation/kld-results.json", | |
| "multiple_choice": "validation/multiple-choice-results.json", | |
| "server": "validation/server-results.json", | |
| "structure": "validation/structure-Q4_K_M.json" | |
| } | |
| }, | |
| { | |
| "bytes": 4554886240, | |
| "filename": "Ling-3.0-tiny-Q4_K_S.gguf", | |
| "hub_introduced_in_commit": "e0f51a846c7791455feb461910485f54fb7af091", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "metadata_count": 59, | |
| "quantization": "Q4_K_S", | |
| "role": "model", | |
| "sha256": "b5688aee697a9129ee49616918d4411cdaca0b909c06820ba9300706cac22672", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "Q4_K": 295, | |
| "Q5_0": 6, | |
| "Q5_K": 9, | |
| "Q6_K": 1 | |
| }, | |
| "validation_reports": { | |
| "generation": "validation/generation-Q4_K_S.json", | |
| "kld": "validation/kld-results.json", | |
| "multiple_choice": "validation/multiple-choice-results.json", | |
| "structure": "validation/structure-Q4_K_S.json" | |
| } | |
| }, | |
| { | |
| "bytes": 4287511648, | |
| "filename": "Ling-3.0-tiny-IQ4_XS.gguf", | |
| "hub_introduced_in_commit": "a6fd141638d7aec1f3e06dc49e5efb64ee60d067", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "metadata_count": 59, | |
| "quantization": "IQ4_XS", | |
| "role": "model", | |
| "sha256": "b81d3cc7d096e5ab2768191ea1de5549a9cc1efc87f20fba571e39f91e7a6f29", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "IQ4_NL": 6, | |
| "IQ4_XS": 304, | |
| "Q6_K": 1 | |
| }, | |
| "validation_reports": { | |
| "generation": "validation/generation-IQ4_XS.json", | |
| "kld": "validation/kld-results.json", | |
| "multiple_choice": "validation/multiple-choice-results.json", | |
| "structure": "validation/structure-IQ4_XS.json" | |
| } | |
| }, | |
| { | |
| "bytes": 3841570912, | |
| "filename": "Ling-3.0-tiny-Q3_K_M.gguf", | |
| "hub_introduced_in_commit": "e5b631e5990870b3b676f2aa5ca18f7af43aee2c", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "metadata_count": 59, | |
| "quantization": "Q3_K_M", | |
| "role": "model", | |
| "sha256": "d32c6cbf24b736deb94c1d409dc4bf75f31aebf8822abb716772cb3352cd075f", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "Q3_K": 215, | |
| "Q4_0": 6, | |
| "Q4_K": 86, | |
| "Q5_K": 3, | |
| "Q6_K": 1 | |
| }, | |
| "validation_reports": { | |
| "generation": "validation/generation-Q3_K_M.json", | |
| "kld": "validation/kld-results.json", | |
| "multiple_choice": "validation/multiple-choice-results.json", | |
| "structure": "validation/structure-Q3_K_M.json" | |
| } | |
| }, | |
| { | |
| "bytes": 3556950112, | |
| "filename": "Ling-3.0-tiny-IQ3_M.gguf", | |
| "hub_introduced_in_commit": "c6cc27c2a5d176c30e7bf81b362e6310dc18a73d", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "metadata_count": 59, | |
| "quantization": "IQ3_M", | |
| "role": "model", | |
| "sha256": "644a42f6c7680e2afcdd58258b39561df1eb858e4b8be7128c3677b5ba089198", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "IQ3_S": 257, | |
| "IQ4_NL": 6, | |
| "Q4_K": 47, | |
| "Q6_K": 1 | |
| }, | |
| "validation_reports": { | |
| "generation": "validation/generation-IQ3_M.json", | |
| "kld": "validation/kld-results.json", | |
| "multiple_choice": "validation/multiple-choice-results.json", | |
| "structure": "validation/structure-IQ3_M.json" | |
| } | |
| }, | |
| { | |
| "bytes": 2704009312, | |
| "filename": "Ling-3.0-tiny-IQ2_M.gguf", | |
| "hub_introduced_in_commit": "1db5044f7d3374c6cac5a29a507702341c07b98f", | |
| "hub_lfs_matches_local": true, | |
| "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "metadata_count": 59, | |
| "quantization": "IQ2_M", | |
| "role": "model", | |
| "sha256": "7f1fba0f96faf67fee40e9083070f753b3f8e484caf541b1b6bb91f786e2ddeb", | |
| "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526, | |
| "tensor_type_counts": { | |
| "F32": 215, | |
| "IQ2_S": 258, | |
| "IQ3_S": 28, | |
| "IQ4_NL": 6, | |
| "Q4_K": 18, | |
| "Q5_K": 1 | |
| }, | |
| "validation_reports": { | |
| "context": "validation/context-results.json", | |
| "generation": "validation/generation-IQ2_M.json", | |
| "kld": "validation/kld-results.json", | |
| "multiple_choice": "validation/multiple-choice-results.json", | |
| "structure": "validation/structure-IQ2_M.json" | |
| } | |
| }, | |
| { | |
| "bytes": 44016768, | |
| "filename": "Ling-3.0-tiny-imatrix.gguf", | |
| "hub_introduced_in_commit": "92a3e7cc9566cbc5a66bcff32c0bad4fb3c4e9b5", | |
| "hub_lfs_matches_local": true, | |
| "matrix_entries": 332, | |
| "quantization": null, | |
| "role": "importance_matrix", | |
| "sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "tensor_count": 664, | |
| "validation_reports": { | |
| "inspection": "validation/imatrix.json" | |
| } | |
| } | |
| ], | |
| "conversion": { | |
| "bf16": { | |
| "bytes": 15803475232, | |
| "metadata_count": 55, | |
| "outtype": "bf16", | |
| "sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "tensor_count": 526 | |
| }, | |
| "byte_reproduction_constraints": { | |
| "embedded_imatrix_path": "/tmp/Ling-3.0-tiny-imatrix.gguf", | |
| "embedded_primary_dataset_path": "/workspace/ling3/calibration/bartowski-imatrix-v5-semantic.txt", | |
| "embedded_supplement_dataset_path": "/workspace/ling3/calibration/eaddario/combined_all_micro.txt", | |
| "note": "Different path spellings change GGUF metadata bytes and therefore artifact SHA-256, even when tensor data is equivalent.", | |
| "source_directory_basename": "Ling-3.0-tiny" | |
| }, | |
| "importance_matrix": { | |
| "collection": { | |
| "batch": 4096, | |
| "complete_chunks": 162, | |
| "context": 4096, | |
| "process_output": false, | |
| "tokens_processed": 663552, | |
| "trailing_tokens_excluded": 5338, | |
| "ubatch": 512 | |
| }, | |
| "embedded_metadata_limitation": "quantize.imatrix.dataset records only the first input; ordered_passes is authoritative.", | |
| "final": { | |
| "bytes": 44016768, | |
| "expert_slots": 8832, | |
| "expert_vectors": 69, | |
| "filename": "Ling-3.0-tiny-imatrix.gguf", | |
| "matrix_entries": 332, | |
| "sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0", | |
| "zero_expert_slots": 0 | |
| }, | |
| "format": "gguf", | |
| "ordered_passes": [ | |
| { | |
| "bytes": 1496006, | |
| "complete_chunks": 89, | |
| "file": "bartowski-imatrix-v5-semantic.txt", | |
| "index": 1, | |
| "repository": "lemon07r/bartowski-imatrix-v5-semantic", | |
| "revision": "a306f203ee4323e0afe846ae02c2daafe17384d9", | |
| "serialized_lines": 6318, | |
| "sha256": "ff879b5a748f822ef539e43c596a3f44ab922f0295ee209d4220d9f86e86a063", | |
| "tokens_processed": 364544, | |
| "trailing_tokens_excluded": 1920 | |
| }, | |
| { | |
| "complete_chunks": 73, | |
| "extracted_bytes": 1008653, | |
| "extracted_file": "combined_all_micro.txt", | |
| "extracted_sha256": "fdb2d41abf04a2fb207502741a561a5a9ab385eb0c44a450eae676c410955946", | |
| "index": 2, | |
| "repository": "eaddario/imatrix-calibration", | |
| "revision": "e87ed55dcba9d9c3a3e41539f3e728e981b1daa4", | |
| "serialized_lines": 3130, | |
| "source_file": "combined_all_micro.parquet", | |
| "source_sha256": "94389921e1f67b180a99de28c3090b41ce6f1960eb13abad21b7eba7cbe11b26", | |
| "tokens_processed": 299008, | |
| "trailing_tokens_excluded": 3418 | |
| } | |
| ], | |
| "primary_intermediate": { | |
| "bytes": 44016704, | |
| "sha256": "01e5d88e62b6654dacfe525908808911af103d06ec95a79ac2f78f36aa780dec" | |
| } | |
| }, | |
| "quantization": { | |
| "all_outputs_direct_from_bf16": true, | |
| "allow_requantize": false, | |
| "base_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e", | |
| "pure": false, | |
| "threads": 32 | |
| } | |
| }, | |
| "environment": { | |
| "compute_capability": "12.0", | |
| "container_image": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404", | |
| "container_platform_manifest_digest": "sha256:4d1721e62b56d345c83b4fd6090664be6daf9312caab5b2e76f23d8231941851", | |
| "gpu": "NVIDIA RTX PRO 4500 Blackwell", | |
| "gpu_memory_mib": 32623, | |
| "kernel": "Linux 6.8.0-101-generic x86_64", | |
| "nvidia_driver": "580.126.20", | |
| "os": "Ubuntu 24.04.3 LTS", | |
| "provider": "RunPod Secure Cloud", | |
| "python_environments": { | |
| "converter": { | |
| "gguf_import_note": "convert_hf_to_gguf.py imported the vendored llama.cpp/gguf-py from the pinned repository because NO_LOCAL_GGUF was not set; the installed gguf package supplied inspection tooling.", | |
| "packages": { | |
| "gguf": "0.19.0", | |
| "huggingface_hub": "0.36.2", | |
| "numpy": "1.26.4", | |
| "protobuf": "4.25.9", | |
| "safetensors": "0.8.0", | |
| "sentencepiece": "0.2.2", | |
| "tokenizers": "0.22.2", | |
| "torch": "2.8.0+cu128", | |
| "tqdm": "4.70.0", | |
| "transformers": "4.57.6" | |
| }, | |
| "purpose": "HF-to-GGUF conversion dependencies and GGUF inspection", | |
| "python": "3.12.3" | |
| }, | |
| "hf_reference": { | |
| "packages": { | |
| "accelerate": "1.10.1", | |
| "huggingface_hub": "0.36.2", | |
| "numpy": "2.1.2", | |
| "safetensors": "0.8.0", | |
| "tokenizers": "0.22.2", | |
| "torch": "2.8.0+cu128", | |
| "tqdm": "4.70.0", | |
| "transformers": "4.57.6" | |
| }, | |
| "purpose": "Transformers BF16 tokenizer and generation reference", | |
| "python": "3.12.3" | |
| }, | |
| "utility_upload": { | |
| "packages": { | |
| "duckdb": "1.3.2", | |
| "huggingface_hub": "1.27.0", | |
| "numpy": "2.5.2", | |
| "protobuf": "7.35.1", | |
| "sentencepiece": "0.2.2", | |
| "tqdm": "4.70.0" | |
| }, | |
| "purpose": "Calibration text extraction and Hub upload", | |
| "python": "3.12.3" | |
| } | |
| } | |
| }, | |
| "independent_cross_checks": [ | |
| { | |
| "exact_matches": [ | |
| { | |
| "filename": "Ling-3.0-tiny-BF16.gguf", | |
| "sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e" | |
| }, | |
| { | |
| "filename": "Ling-3.0-tiny-Q8_0.gguf", | |
| "sha256": "326221bdef72525bd6178b072d3827cd5fb5248a55e8c44eb400417f401733bc" | |
| } | |
| ], | |
| "relationship": "Post-hoc independent artifact comparison, not a weight source", | |
| "repository": "bloomer010/Ling-3.0-tiny-GGUF", | |
| "revision": "59820116411687d44e1333816609afca8c93aa0b" | |
| } | |
| ], | |
| "manifest_kind": "gguf_conversion", | |
| "release": { | |
| "date_utc": "2026-08-11", | |
| "license": "MIT", | |
| "publisher": "Mike0021", | |
| "repository": "Mike0021/Ling-3.0-tiny-GGUF", | |
| "repository_type": "model", | |
| "tag": "v1.0", | |
| "training_performed": false, | |
| "transformation": "BF16 GGUF conversion followed by direct post-training quantization" | |
| }, | |
| "schema_version": "1.0.0", | |
| "source": { | |
| "control_file_sha256": { | |
| "chat_template.jinja": "eb6226c94ae38058f875d159f86a206b3a165828c0e7d6bda664ae14667f798a", | |
| "config.json": "9750d847957913f665a13c0b5a6537199e33c6f3ec970d9fcb55a0e5076d4012", | |
| "configuration_bailing_moe_v3.py": "f2c048966aec8a2f042cfeb1351f74d51a28589b409c55baae7d24e841c1f6c4", | |
| "generation_config.json": "64752c5973a55faf4cfc02604c7587c38b090f00013f91191f52362dcc79a4a8", | |
| "model.safetensors.index.json": "84ef9fe8ef967eeb0545deb1d23c0ce54e86e6b18fa943a7903d7354a79f9cf9", | |
| "modeling_bailing_moe_v3.py": "c2509bf7ac580c262e2581d34d6403aa21682d2e10beb9ad85ad8820a7e33a40", | |
| "special_tokens_map.json": "69b63b9f81044ead642d16a5fdc01bcc737dc1183746485c8397ab14d3126614", | |
| "tokenizer.json": "40fb9d7d7795b8bd305aeff39ce9963f3f450915b9553f2938e009be9a1fed60", | |
| "tokenizer_config.json": "2456b0372956cd3e82f17e33372148b115a94970bfd4878ba5e7e60cd3204f74" | |
| }, | |
| "notes": [ | |
| "model.safetensors.index.json metadata.total_size is not used as physical file size; measured shard bytes are authoritative." | |
| ], | |
| "repository": "inclusionAI/Ling-3.0-tiny", | |
| "required_directory_basename": "Ling-3.0-tiny", | |
| "revision": "a2ee06c0f2de5b171701aee7f73f70a1da75483b", | |
| "weights": { | |
| "actual_bytes": 15787992416, | |
| "format": "safetensors", | |
| "sha256_manifest": "source-safetensors.sha256", | |
| "sha256_manifest_sha256": "d8a7cf059fd4b4f2fd7f7d0b1118417be02f7b39a5c428461c027f5d71faff6d", | |
| "shard_count": 32, | |
| "weight_map_entries": 9283 | |
| } | |
| }, | |
| "toolchain": { | |
| "binary_sha256": { | |
| "llama-cli": "aa52b6f0281d85c65a35b0fd3aac786a0deb8a0d28f14bcb90352f93fad2e52e", | |
| "llama-completion": "cd16edd3ef2cfbc4ff5ea2ac1acd73a7f0e0355c4ad3c268e40ba9f85d039fe3", | |
| "llama-imatrix": "16e3fe106cd1832e3dd4aa03e954521e79f2fc58cd03afaa0953960a9f390006", | |
| "llama-perplexity": "78f36a12b0a823d0f7b9454151effd6ecb67387d8e57b59325e18de0362c2cc4", | |
| "llama-quantize": "eb98052b77b529891537ace9e35fed0ad6f0a8692d187213c8dc7e3be1d6eeb3", | |
| "llama-server": "6cba678338c0e81a6cb01e79a9bdae55007a2f246041f8af77d824bbf455ae71", | |
| "llama-tokenize": "d548bc241ac43bd6f05cec4b9b84ad01f43c2783d02641ec159c326a6ce9508e" | |
| }, | |
| "build": { | |
| "build_type": "Release", | |
| "c_compiler": "GNU 13.3.0", | |
| "cmake": "3.28.3", | |
| "cuda_architectures_requested": "native", | |
| "cuda_architectures_resolved": [ | |
| "sm_120a" | |
| ], | |
| "cuda_compiler": "12.8 build 35583870_0", | |
| "cxx_compiler": "GNU 13.3.0", | |
| "generator": "Ninja", | |
| "ggml_cuda": true, | |
| "ggml_native": false | |
| }, | |
| "llama_cpp": { | |
| "build_number": 10372, | |
| "commit": "d8d862521e9ad842f2b47f3b392b039317782aa0", | |
| "convert_hf_to_gguf_sha256": "e38975e1c68d98ac1664dfd530616eb35c72294382a4dd873d4746b23f27779f", | |
| "repository": "https://github.com/aetherbird/llama.cpp.git", | |
| "required_ancestor_commits": [ | |
| "517b467544f732ddabb3f7727932f8d004ad9457", | |
| "0266ebca66bd95b7a85d37b8ca08ccf9812b85cc" | |
| ], | |
| "upstream_pr": 26608, | |
| "worktree_clean": true | |
| } | |
| }, | |
| "validation_inputs": { | |
| "kld": { | |
| "archive_sha256": "ef7edb566e3e2b2d31b29c1fdb0c89a4cc683597484c3dc2517919c615435a11", | |
| "batch": 512, | |
| "bf16_reference_bytes": 2565373716, | |
| "bf16_reference_sha256": "afa4dc9bd2d995dd85d8614494dc9cccec8e0e4bd6b2c24efc81d3bba96638f7", | |
| "chunks": 32, | |
| "context": 512, | |
| "repository": "ggml-org/ci", | |
| "revision": "927b3642933080f1b0e811e2f916e14c292992f9", | |
| "scored_tokens": 8160, | |
| "test_text_sha256": "173c87a53759e0201f33e0ccf978e510c2042d7f2cb78229d9a50d79b9e7dd08", | |
| "ubatch": 512 | |
| }, | |
| "multiple_choice": { | |
| "bytes": 762276, | |
| "file": "mmlu-validation.bin", | |
| "note": "The pinned tool log labels this path TruthfulQA; the input is MMLU validation.", | |
| "repository": "ikawrakow/validation-datasets-for-llama.cpp", | |
| "revision": "37884b81b4957f1950a53b6ff48d77c8dd5e430c", | |
| "seed": 1, | |
| "sha256": "470af3a74eccacfaf6f43b08aabf510f61e6c92fe20d17241ded934151e225fa", | |
| "tasks": 500 | |
| } | |
| } | |
| } | |