Instructions to use PrunaAI/Tiiny-SmallThinker-3B-Preview-HQQ-4bit-smashed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pruna AI
How to use PrunaAI/Tiiny-SmallThinker-3B-Preview-HQQ-4bit-smashed with Pruna AI:
from pruna import PrunaModel model = PrunaModel.from_pretrained("PrunaAI/Tiiny-SmallThinker-3B-Preview-HQQ-4bit-smashed") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "/root/.cache/huggingface/hub/models--Tiiny--SmallThinker-3B-Preview/snapshots/2ca6a4093f3e9f178d61a5364a0335877a4e9b07", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 70, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |