| { | |
| "_name_or_path": "llmware/bling-sheared-llama-1.3b-0.1", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "description": "Instruct train fine-tuning using distilled knowledge based critical reading tasks training dataset", | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5504, | |
| "max_position_embeddings": 4096, | |
| "model_name": "bling-sheared-llama-1.3b-0.1", | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "training_comments": "sheared-llama-1.3b-base", | |
| "training_timestamp": "Sun Oct 22 14:31:15 2023", | |
| "transformers_version": "4.31.0", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |