Text Classification
Transformers
Safetensors
English
deberta-v2
function calling
on-device language model
text-embeddings-inference
Instructions to use squeeze-ai-lab/TinyAgent-ToolRAG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use squeeze-ai-lab/TinyAgent-ToolRAG with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="squeeze-ai-lab/TinyAgent-ToolRAG")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("squeeze-ai-lab/TinyAgent-ToolRAG") model = AutoModelForSequenceClassification.from_pretrained("squeeze-ai-lab/TinyAgent-ToolRAG", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download added_tokens.json from squeeze-ai-lab/TinyAgent-ToolRAG: direct link, hf CLI and curl.
- Browser
- Download file 23 Bytes
-
https://huggingface.co/squeeze-ai-lab/TinyAgent-ToolRAG/resolve/main/added_tokens.json
- Command line
-
hf download hf://squeeze-ai-lab/TinyAgent-ToolRAG/added_tokens.json
-
curl -L -o added_tokens.json https://huggingface.co/squeeze-ai-lab/TinyAgent-ToolRAG/resolve/main/added_tokens.json
23 Bytes
| { | |
| "[MASK]": 128000 | |
| } | |