| { | |
| "_name_or_path": "/scr/jay/ckpt/2024-03-11/Mistral_Sparse_refined_web_50p_no_adapter", | |
| "architectures": [ | |
| "SparseMistralforCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "sparsification_sftt.SparseMistralConfig", | |
| "AutoModelForCausalLM": "sparsification_sftt.SparseMistralforCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "sparse_mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "thresholds": [ | |
| 0.017051145434379578, | |
| 0.023069201037287712, | |
| 0.049147434532642365, | |
| 0.051153454929590225, | |
| 0.061183542013168335, | |
| 0.07121363282203674, | |
| 0.0732196494936943, | |
| 0.07923770695924759, | |
| 0.08324974030256271, | |
| 0.08124372363090515, | |
| 0.089267797768116, | |
| 0.09127381443977356, | |
| 0.10130390524864197, | |
| 0.0992978885769844, | |
| 0.10732196271419525, | |
| 0.12337010353803635, | |
| 0.14343027770519257, | |
| 0.16148445010185242, | |
| 0.17953860759735107, | |
| 0.1935807317495346, | |
| 0.1995987892150879, | |
| 0.2196589708328247, | |
| 0.2196589708328247, | |
| 0.23169508576393127, | |
| 0.2357071191072464, | |
| 0.23370109498500824, | |
| 0.225677028298378, | |
| 0.22968906164169312, | |
| 0.225677028298378, | |
| 0.22768303751945496, | |
| 0.2457372099161148, | |
| 0.2678034007549286 | |
| ], | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.2", | |
| "use_cache": false, | |
| "use_relu": false, | |
| "use_sparse_model": true, | |
| "use_sparse_predictor": false, | |
| "use_sparse_regularization": false, | |
| "vocab_size": 32000 | |
| } | |