| { | |
| "_name_or_path": "BeardedMonster/MOE", | |
| "architectures": [ | |
| "GPTJXMoEForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration.GPTJXMoEConfig", | |
| "AutoModelForCausalLM": "modeling.GPTJXMoEForCausalLM" | |
| }, | |
| "bias": false, | |
| "block_size": 32768, | |
| "dropout": 0.0, | |
| "kv_cache_dtype": "float32", | |
| "max_batch_size": 1, | |
| "model_type": "sabiyarn", | |
| "moe_dim": 3072, | |
| "n_embd": 768, | |
| "n_heads": 12, | |
| "n_layer": 12, | |
| "num_experts": 7, | |
| "num_experts_per_tok": 2, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.2", | |
| "use_kv_cache": true, | |
| "use_moe": true, | |
| "vocab_size": 52050 | |
| } | |