Text Classification
Transformers
Safetensors
English
qwen3
text-generation
qwen
decision-model
finance
wealth-management
sec-filings
news
central-banks
calibration
lora
jev
text-embeddings-inference
Instructions to use ternary/Arbiter-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ternary/Arbiter-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ternary/Arbiter-8B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ternary/Arbiter-8B") model = AutoModelForCausalLM.from_pretrained("ternary/Arbiter-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download calibration.json from ternary/Arbiter-8B: direct link, hf CLI and curl.
- Browser
- Download file 476 Bytes
-
https://huggingface.co/ternary/Arbiter-8B/resolve/main/calibration.json
- Command line
-
hf download hf://ternary/Arbiter-8B/calibration.json
-
curl -L -o calibration.json https://huggingface.co/ternary/Arbiter-8B/resolve/main/calibration.json
476 Bytes
| { | |
| "split": "dev", | |
| "temperatures": { | |
| "choice": 1.056737703565464, | |
| "noul": 1.0, | |
| "score": 1.0000000000000013 | |
| }, | |
| "counts": { | |
| "choice": 83, | |
| "noul": 39, | |
| "score": 29 | |
| }, | |
| "nll_raw": { | |
| "choice": 0.5215100010627519, | |
| "noul": 0.1584453682220628, | |
| "score": 0.4403726302605306 | |
| }, | |
| "nll_calibrated": { | |
| "choice": 0.5202457346238334, | |
| "noul": 0.1584453682220628, | |
| "score": 0.4403726302605305 | |
| }, | |
| "fallback_types_without_data": [] | |
| } |