Token Classification
Transformers
ONNX
Safetensors
Transformers.js
modernbert
prompt-compression
context-compression
llmlingua
agents
tool-use
mmbert
claude-code
Instructions to use darioooooo0o/ctxprune-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use darioooooo0o/ctxprune-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="darioooooo0o/ctxprune-small")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("darioooooo0o/ctxprune-small") model = AutoModelForTokenClassification.from_pretrained("darioooooo0o/ctxprune-small", device_map="auto") - Transformers.js
How to use darioooooo0o/ctxprune-small with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('token-classification', 'darioooooo0o/ctxprune-small'); - Notebooks
- Google Colab
- Kaggle
Download eval/qa_v1-final-v1v3__deepseek_deepseek-v4-flash.json from darioooooo0o/ctxprune-small: direct link, hf CLI and curl.
- Browser
- Download file 3.99 kB
-
https://huggingface.co/darioooooo0o/ctxprune-small/resolve/main/eval/qa_v1-final-v1v3__deepseek_deepseek-v4-flash.json
- Command line
-
hf download hf://darioooooo0o/ctxprune-small/eval/qa_v1-final-v1v3__deepseek_deepseek-v4-flash.json
-
curl -L -o qa_v1-final-v1v3__deepseek_deepseek-v4-flash.json https://huggingface.co/darioooooo0o/ctxprune-small/resolve/main/eval/qa_v1-final-v1v3__deepseek_deepseek-v4-flash.json
3.99 kB
| { | |
| "original": { | |
| "fineweb2": { | |
| "em": 0.722, | |
| "f1": 0.722, | |
| "n": 18 | |
| }, | |
| "_all": { | |
| "em": 0.918, | |
| "f1": 0.88, | |
| "n": 376 | |
| }, | |
| "fineweb_edu": { | |
| "em": 0.966, | |
| "f1": 0.942, | |
| "n": 58 | |
| }, | |
| "github_code": { | |
| "em": 0.938, | |
| "f1": 0.923, | |
| "n": 65 | |
| }, | |
| "oasst2": { | |
| "em": 0.938, | |
| "f1": 0.81, | |
| "n": 16 | |
| }, | |
| "swe_rebench_assistant": { | |
| "em": 0.946, | |
| "f1": 0.949, | |
| "n": 37 | |
| }, | |
| "swe_rebench_tool": { | |
| "em": 0.896, | |
| "f1": 0.802, | |
| "n": 77 | |
| }, | |
| "toucan_mcp": { | |
| "em": 0.926, | |
| "f1": 0.908, | |
| "n": 54 | |
| }, | |
| "swe_smith_tool": { | |
| "em": 0.902, | |
| "f1": 0.873, | |
| "n": 51 | |
| }, | |
| "_char_ratio": 1.0, | |
| "_llm_token_ratio": 1.0 | |
| }, | |
| "ours@0.5": { | |
| "fineweb2": { | |
| "em": 0.556, | |
| "f1": 0.556, | |
| "n": 18 | |
| }, | |
| "_all": { | |
| "em": 0.688, | |
| "f1": 0.684, | |
| "n": 378 | |
| }, | |
| "fineweb_edu": { | |
| "em": 0.733, | |
| "f1": 0.789, | |
| "n": 60 | |
| }, | |
| "github_code": { | |
| "em": 0.723, | |
| "f1": 0.708, | |
| "n": 65 | |
| }, | |
| "oasst2": { | |
| "em": 0.75, | |
| "f1": 0.77, | |
| "n": 16 | |
| }, | |
| "swe_rebench_assistant": { | |
| "em": 0.703, | |
| "f1": 0.786, | |
| "n": 37 | |
| }, | |
| "swe_rebench_tool": { | |
| "em": 0.597, | |
| "f1": 0.543, | |
| "n": 77 | |
| }, | |
| "toucan_mcp": { | |
| "em": 0.593, | |
| "f1": 0.617, | |
| "n": 54 | |
| }, | |
| "swe_smith_tool": { | |
| "em": 0.843, | |
| "f1": 0.76, | |
| "n": 51 | |
| }, | |
| "_char_ratio": 0.485, | |
| "_llm_token_ratio": 0.492 | |
| }, | |
| "ours+ids@0.5": { | |
| "fineweb2": { | |
| "em": 0.556, | |
| "f1": 0.556, | |
| "n": 18 | |
| }, | |
| "_all": { | |
| "em": 0.635, | |
| "f1": 0.64, | |
| "n": 378 | |
| }, | |
| "fineweb_edu": { | |
| "em": 0.7, | |
| "f1": 0.744, | |
| "n": 60 | |
| }, | |
| "github_code": { | |
| "em": 0.692, | |
| "f1": 0.679, | |
| "n": 65 | |
| }, | |
| "oasst2": { | |
| "em": 0.75, | |
| "f1": 0.77, | |
| "n": 16 | |
| }, | |
| "swe_rebench_assistant": { | |
| "em": 0.676, | |
| "f1": 0.74, | |
| "n": 37 | |
| }, | |
| "swe_rebench_tool": { | |
| "em": 0.571, | |
| "f1": 0.555, | |
| "n": 77 | |
| }, | |
| "toucan_mcp": { | |
| "em": 0.556, | |
| "f1": 0.571, | |
| "n": 54 | |
| }, | |
| "swe_smith_tool": { | |
| "em": 0.627, | |
| "f1": 0.586, | |
| "n": 51 | |
| }, | |
| "_char_ratio": 0.498, | |
| "_llm_token_ratio": 0.559 | |
| }, | |
| "ours@0.33": { | |
| "fineweb2": { | |
| "em": 0.389, | |
| "f1": 0.452, | |
| "n": 18 | |
| }, | |
| "_all": { | |
| "em": 0.534, | |
| "f1": 0.538, | |
| "n": 378 | |
| }, | |
| "fineweb_edu": { | |
| "em": 0.55, | |
| "f1": 0.637, | |
| "n": 60 | |
| }, | |
| "github_code": { | |
| "em": 0.508, | |
| "f1": 0.477, | |
| "n": 65 | |
| }, | |
| "oasst2": { | |
| "em": 0.688, | |
| "f1": 0.648, | |
| "n": 16 | |
| }, | |
| "swe_rebench_assistant": { | |
| "em": 0.622, | |
| "f1": 0.639, | |
| "n": 37 | |
| }, | |
| "swe_rebench_tool": { | |
| "em": 0.468, | |
| "f1": 0.444, | |
| "n": 77 | |
| }, | |
| "toucan_mcp": { | |
| "em": 0.481, | |
| "f1": 0.478, | |
| "n": 54 | |
| }, | |
| "swe_smith_tool": { | |
| "em": 0.647, | |
| "f1": 0.626, | |
| "n": 51 | |
| }, | |
| "_char_ratio": 0.31, | |
| "_llm_token_ratio": 0.322 | |
| }, | |
| "ours+ids@0.33": { | |
| "fineweb2": { | |
| "em": 0.444, | |
| "f1": 0.444, | |
| "n": 18 | |
| }, | |
| "_all": { | |
| "em": 0.529, | |
| "f1": 0.541, | |
| "n": 378 | |
| }, | |
| "fineweb_edu": { | |
| "em": 0.533, | |
| "f1": 0.615, | |
| "n": 60 | |
| }, | |
| "github_code": { | |
| "em": 0.585, | |
| "f1": 0.551, | |
| "n": 65 | |
| }, | |
| "oasst2": { | |
| "em": 0.688, | |
| "f1": 0.648, | |
| "n": 16 | |
| }, | |
| "swe_rebench_assistant": { | |
| "em": 0.432, | |
| "f1": 0.509, | |
| "n": 37 | |
| }, | |
| "swe_rebench_tool": { | |
| "em": 0.558, | |
| "f1": 0.536, | |
| "n": 77 | |
| }, | |
| "toucan_mcp": { | |
| "em": 0.481, | |
| "f1": 0.528, | |
| "n": 54 | |
| }, | |
| "swe_smith_tool": { | |
| "em": 0.51, | |
| "f1": 0.49, | |
| "n": 51 | |
| }, | |
| "_char_ratio": 0.382, | |
| "_llm_token_ratio": 0.459 | |
| } | |
| } |