Feature Extraction
Transformers
Safetensors
llama_bidirec
mergekit
Merge
custom_code
text-embeddings-inference
8-bit precision
Instructions to use KwangHwi/quantization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KwangHwi/quantization with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="KwangHwi/quantization", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KwangHwi/quantization", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "LlamaBidirectionalModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "llama_bidirectional_model.LlamaBidirectionalConfig", | |
| "AutoModel": "llama_bidirectional_model.LlamaBidirectionalModel" | |
| }, | |
| "bos_token_id": 128000, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 128001, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama_bidirec", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "pooling": "avg", | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_theta": 500000.0, | |
| "rope_type": "llama3" | |
| }, | |
| "temperature": 1.0, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.14.1", | |
| "use_bidirectional_attention": true, | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |