Instructions to use Mike0021/pulpie-orange-small-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/pulpie-orange-small-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/pulpie-orange-small-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mike0021/pulpie-orange-small-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/pulpie-orange-small-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mike0021/pulpie-orange-small-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/pulpie-orange-small-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Mike0021/pulpie-orange-small-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/pulpie-orange-small-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Mike0021/pulpie-orange-small-gguf:Q4_K_M
Use Docker
docker model run hf.co/Mike0021/pulpie-orange-small-gguf:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Mike0021/pulpie-orange-small-gguf with Ollama:
ollama run hf.co/Mike0021/pulpie-orange-small-gguf:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Mike0021/pulpie-orange-small-gguf with Docker Model Runner:
docker model run hf.co/Mike0021/pulpie-orange-small-gguf:Q4_K_M
- Lemonade
How to use Mike0021/pulpie-orange-small-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mike0021/pulpie-orange-small-gguf:Q4_K_M
Run and chat with the model
lemonade run user.pulpie-orange-small-gguf-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download verification_report.json from Mike0021/pulpie-orange-small-gguf: direct link, hf CLI and curl.
- Browser
- Download file 8.89 kB
-
https://huggingface.co/Mike0021/pulpie-orange-small-gguf/resolve/main/verification_report.json
- Command line
-
hf download hf://Mike0021/pulpie-orange-small-gguf/verification_report.json
-
curl -L -o verification_report.json https://huggingface.co/Mike0021/pulpie-orange-small-gguf/resolve/main/verification_report.json
8.89 kB
| { | |
| "created_at_utc": "2026-07-07T10:29:44Z", | |
| "source_model": "feyninc/pulpie-orange-small", | |
| "llama_cpp_note": "EuroBertForTokenClassification patch exposes per-token classifier logits via llama-embedding --pooling none.", | |
| "environment": { | |
| "python": "Python 3.11.10", | |
| "torch": "2.4.1+cu124", | |
| "device": "cpu", | |
| "device_note": "PyTorch CUDA fallback to CPU: RuntimeError: CUDA error: no kernel image is available for execution on the device\nCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\nFor debugging consider passing CUDA_LAUNCH_BLOCKING=1\nCompile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.\n", | |
| "cuda_available": true | |
| }, | |
| "files": [ | |
| { | |
| "file": "pulpie-orange-small-F16.gguf", | |
| "size_bytes": 431400864, | |
| "size_mb": 431.4 | |
| }, | |
| { | |
| "file": "pulpie-orange-small-Q2_K.gguf", | |
| "size_bytes": 130177056, | |
| "size_mb": 130.18 | |
| }, | |
| { | |
| "file": "pulpie-orange-small-Q3_K_M.gguf", | |
| "size_bytes": 143153344, | |
| "size_mb": 143.15 | |
| }, | |
| { | |
| "file": "pulpie-orange-small-Q4_K_M.gguf", | |
| "size_bytes": 156968320, | |
| "size_mb": 156.97 | |
| }, | |
| { | |
| "file": "pulpie-orange-small-Q5_K_M.gguf", | |
| "size_bytes": 168912448, | |
| "size_mb": 168.91 | |
| }, | |
| { | |
| "file": "pulpie-orange-small-Q6_K.gguf", | |
| "size_bytes": 181603104, | |
| "size_mb": 181.6 | |
| }, | |
| { | |
| "file": "pulpie-orange-small-Q8_0.gguf", | |
| "size_bytes": 232886080, | |
| "size_mb": 232.89 | |
| } | |
| ], | |
| "load_checks": { | |
| "pulpie-orange-small-F16.gguf": { | |
| "llama_cli_single_turn_exit_code": 0, | |
| "llama_cli_loaded": true, | |
| "llama_cli_note": "llama-cli is a generation frontend; this encoder classifier has no causal LM logits.", | |
| "llama_embedding_exit_code": 0, | |
| "llama_embedding_output_rows": 2, | |
| "llama_cli_elapsed_seconds": 3.8506942209787667, | |
| "llama_embedding_elapsed_seconds": 2.693078241078183 | |
| }, | |
| "pulpie-orange-small-Q2_K.gguf": { | |
| "llama_cli_single_turn_exit_code": 0, | |
| "llama_cli_loaded": true, | |
| "llama_cli_note": "llama-cli is a generation frontend; this encoder classifier has no causal LM logits.", | |
| "llama_embedding_exit_code": 0, | |
| "llama_embedding_output_rows": 2, | |
| "llama_cli_elapsed_seconds": 2.4174793811980635, | |
| "llama_embedding_elapsed_seconds": 2.4536153939552605 | |
| }, | |
| "pulpie-orange-small-Q3_K_M.gguf": { | |
| "llama_cli_single_turn_exit_code": 0, | |
| "llama_cli_loaded": true, | |
| "llama_cli_note": "llama-cli is a generation frontend; this encoder classifier has no causal LM logits.", | |
| "llama_embedding_exit_code": 0, | |
| "llama_embedding_output_rows": 2, | |
| "llama_cli_elapsed_seconds": 2.399886897066608, | |
| "llama_embedding_elapsed_seconds": 2.485915848053992 | |
| }, | |
| "pulpie-orange-small-Q4_K_M.gguf": { | |
| "llama_cli_single_turn_exit_code": 0, | |
| "llama_cli_loaded": true, | |
| "llama_cli_note": "llama-cli is a generation frontend; this encoder classifier has no causal LM logits.", | |
| "llama_embedding_exit_code": 0, | |
| "llama_embedding_output_rows": 2, | |
| "llama_cli_elapsed_seconds": 2.6905582370236516, | |
| "llama_embedding_elapsed_seconds": 2.5811137680429965 | |
| }, | |
| "pulpie-orange-small-Q5_K_M.gguf": { | |
| "llama_cli_single_turn_exit_code": 0, | |
| "llama_cli_loaded": true, | |
| "llama_cli_note": "llama-cli is a generation frontend; this encoder classifier has no causal LM logits.", | |
| "llama_embedding_exit_code": 0, | |
| "llama_embedding_output_rows": 2, | |
| "llama_cli_elapsed_seconds": 2.3842295249924064, | |
| "llama_embedding_elapsed_seconds": 2.456760450033471 | |
| }, | |
| "pulpie-orange-small-Q6_K.gguf": { | |
| "llama_cli_single_turn_exit_code": 0, | |
| "llama_cli_loaded": true, | |
| "llama_cli_note": "llama-cli is a generation frontend; this encoder classifier has no causal LM logits.", | |
| "llama_embedding_exit_code": 0, | |
| "llama_embedding_output_rows": 2, | |
| "llama_cli_elapsed_seconds": 2.419072214048356, | |
| "llama_embedding_elapsed_seconds": 2.4600620470009744 | |
| }, | |
| "pulpie-orange-small-Q8_0.gguf": { | |
| "llama_cli_single_turn_exit_code": 0, | |
| "llama_cli_loaded": true, | |
| "llama_cli_note": "llama-cli is a generation frontend; this encoder classifier has no causal LM logits.", | |
| "llama_embedding_exit_code": 0, | |
| "llama_embedding_output_rows": 2, | |
| "llama_cli_elapsed_seconds": 2.568599973106757, | |
| "llama_embedding_elapsed_seconds": 2.5757998879998922 | |
| } | |
| }, | |
| "accuracy": { | |
| "pulpie-orange-small-F16.gguf": { | |
| "texts": { | |
| "test": { | |
| "max_abs_diff": 0.004654441717529156, | |
| "mean_abs_diff": 0.0022773042905806784, | |
| "token_count": 2, | |
| "prediction_agreement": 1.0 | |
| }, | |
| "Hello world": { | |
| "max_abs_diff": 0.010810604415893543, | |
| "mean_abs_diff": 0.005295509957885747, | |
| "token_count": 3, | |
| "prediction_agreement": 1.0 | |
| }, | |
| "<html><body><h1>Title</h1><p>Main text.</p></body></html>": { | |
| "max_abs_diff": 0.06980780208435067, | |
| "mean_abs_diff": 0.030381664234144044, | |
| "token_count": 22, | |
| "prediction_agreement": 1.0 | |
| } | |
| }, | |
| "max_abs_diff": 0.06980780208435067, | |
| "mean_abs_diff": 0.012651492827536822 | |
| }, | |
| "pulpie-orange-small-Q8_0.gguf": { | |
| "texts": { | |
| "test": { | |
| "max_abs_diff": 0.06683230650177002, | |
| "mean_abs_diff": 0.04104299360065457, | |
| "token_count": 2, | |
| "prediction_agreement": 1.0 | |
| }, | |
| "Hello world": { | |
| "max_abs_diff": 0.0720623857818603, | |
| "mean_abs_diff": 0.059363839538574215, | |
| "token_count": 3, | |
| "prediction_agreement": 1.0 | |
| }, | |
| "<html><body><h1>Title</h1><p>Main text.</p></body></html>": { | |
| "max_abs_diff": 0.057413787133789064, | |
| "mean_abs_diff": 0.021704604984231428, | |
| "token_count": 22, | |
| "prediction_agreement": 1.0 | |
| } | |
| }, | |
| "max_abs_diff": 0.0720623857818603, | |
| "mean_abs_diff": 0.040703812707820065 | |
| } | |
| }, | |
| "e2e_extraction": { | |
| "pulpie-orange-small-F16.gguf": { | |
| "ok": true, | |
| "n_blocks": 4, | |
| "n_main": 3, | |
| "n_other": 1, | |
| "markdown": "<html><body>\n <main><h1 _item_id=\"1\">Orange harvest report</h1>\n <p _item_id=\"2\">The main article explains how growers sort oranges after harvest.</p>\n <p _item_id=\"3\">It includes storage notes and quality checks for shipment.</p>\n </main></body></html>", | |
| "labels": { | |
| "1": "main", | |
| "2": "main", | |
| "3": "main", | |
| "4": "other" | |
| }, | |
| "tokenization_roundtrip_ok": true, | |
| "latency_seconds": 13.650275907013565 | |
| }, | |
| "pulpie-orange-small-Q8_0.gguf": { | |
| "ok": true, | |
| "n_blocks": 4, | |
| "n_main": 3, | |
| "n_other": 1, | |
| "markdown": "<html><body>\n <main><h1 _item_id=\"1\">Orange harvest report</h1>\n <p _item_id=\"2\">The main article explains how growers sort oranges after harvest.</p>\n <p _item_id=\"3\">It includes storage notes and quality checks for shipment.</p>\n </main></body></html>", | |
| "labels": { | |
| "1": "main", | |
| "2": "main", | |
| "3": "main", | |
| "4": "other" | |
| }, | |
| "tokenization_roundtrip_ok": true, | |
| "latency_seconds": 2.537674251012504 | |
| } | |
| }, | |
| "latency_seconds": { | |
| "pytorch": { | |
| "pulpie-orange-small-F16.gguf": [ | |
| 0.04418429802171886, | |
| 0.07586899190209806, | |
| 0.0618554730899632 | |
| ], | |
| "pulpie-orange-small-Q8_0.gguf": [ | |
| 0.027146564098075032, | |
| 0.032363954000175, | |
| 0.05264966515824199 | |
| ] | |
| }, | |
| "gguf_subprocess": { | |
| "pulpie-orange-small-F16.gguf": [ | |
| 2.542310531018302, | |
| 2.5629363812040538, | |
| 2.5437233441043645 | |
| ], | |
| "pulpie-orange-small-Q8_0.gguf": [ | |
| 2.990182199049741, | |
| 2.4438916840590537, | |
| 2.455025817034766 | |
| ], | |
| "pulpie-orange-small-Q2_K.gguf": [ | |
| 37.14351637708023, | |
| 2.4945668019354343, | |
| 2.5103745961096138 | |
| ], | |
| "pulpie-orange-small-Q3_K_M.gguf": [ | |
| 28.285755896009505, | |
| 2.4585004050750285, | |
| 2.3625288009643555 | |
| ], | |
| "pulpie-orange-small-Q4_K_M.gguf": [ | |
| 18.12280774395913, | |
| 2.4188850200735033, | |
| 2.4106604028493166 | |
| ], | |
| "pulpie-orange-small-Q5_K_M.gguf": [ | |
| 2.9326697760261595, | |
| 2.4721172840800136, | |
| 2.514459784142673 | |
| ], | |
| "pulpie-orange-small-Q6_K.gguf": [ | |
| 2.9089490061160177, | |
| 2.4514556501526386, | |
| 2.4820459550246596 | |
| ] | |
| }, | |
| "pytorch_baseline": [ | |
| 0.11215555900707841, | |
| 0.19677641009911895, | |
| 0.11335471202619374, | |
| 0.17645823606289923, | |
| 0.11712144990451634 | |
| ] | |
| } | |
| } |