Feature Extraction
Transformers
Safetensors
llama_bidirec
mergekit
Merge
custom_code
text-embeddings-inference
8-bit precision
quanto
Instructions to use KwangHwi/quantization_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KwangHwi/quantization_v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="KwangHwi/quantization_v2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KwangHwi/quantization_v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "backend": "tokenizers", | |
| "bos_token": "<|begin_of_text|>", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "<|end_of_text|>", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "max_length": 8192, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 131072, | |
| "pad_token": "<|end_of_text|>", | |
| "stride": 0, | |
| "tokenizer_class": "TokenizersBackend", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first" | |
| } | |