Text Classification
Transformers
Safetensors
English
qwen3_5_text
text-generation
decision-model
typed-decisions
one-pass
option-probabilities
Instructions to use thegovind/blink-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thegovind/blink-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="thegovind/blink-4b")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("thegovind/blink-4b") model = AutoModelForCausalLM.from_pretrained("thegovind/blink-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval/jevbench-public-proxy.json from thegovind/blink-4b: direct link, hf CLI and curl.
- Browser
- Download file 776 Bytes
-
https://huggingface.co/thegovind/blink-4b/resolve/a2e49b395461da8982bcf1461e93a4de52097148/eval/jevbench-public-proxy.json
- Command line
-
hf download hf://thegovind/blink-4b@a2e49b395461da8982bcf1461e93a4de52097148/eval/jevbench-public-proxy.json
-
curl -L -o jevbench-public-proxy.json https://huggingface.co/thegovind/blink-4b/resolve/a2e49b395461da8982bcf1461e93a4de52097148/eval/jevbench-public-proxy.json
776 Bytes
| { | |
| "tiers": { | |
| "easy": 1.0, | |
| "standard": 0.9861111111111112, | |
| "hard": 0.7207207207207207 | |
| }, | |
| "hard_ece": 0.0672866582962707, | |
| "prob_tvd": 0.2258727428861121, | |
| "calibration": 81.97769702606733, | |
| "intelligence_public": 81.67291558166173, | |
| "input_tokens_per_decision": 698.922077922078, | |
| "temperature": 1.0, | |
| "hard_by_family": { | |
| "adversarial": 1.0, | |
| "ambiguous": 0.857, | |
| "judge_hard": 0.647, | |
| "long_policy": 0.579, | |
| "multi_hop": 0.833, | |
| "probability": 0.7, | |
| "routing_hard": 1.0, | |
| "temporal_numeric": 0.4, | |
| "tradeoff": 0.833, | |
| "trap": 1.0 | |
| }, | |
| "p50_s": 0.06382748000032734, | |
| "p95_s": 0.17542972600494977, | |
| "speed": 88.5677868991755, | |
| "note": "JevBench v1.2 public items (231) scored with JevBench's own code; a development proxy, not an official JevBench result." | |
| } |