CofeAI/Tele-FLM
3018k
1{2 "architectures": [3 "TeleFLMModel", "TeleFLMForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "auto_map": {8 "AutoConfig": "configuration_teleflm.TeleFLMConfig",9 "AutoModel": "modeling_teleflm.TeleFLMModel",10 "AutoModelForCausalLM": "modeling_teleflm.TeleFLMForCausalLM"11 },12 "bos_token_id": 1,13 "eos_token_id": 2,14 "hidden_act": "silu",15 "hidden_size": 8192,16 "initializer_range": 0.02,17 "input_mult": 1.0,18 "intermediate_size": 21824,19 "max_position_embeddings": 4096,20 "model_type": "TeleFLM",21 "mup_scale_factor": 16.0,22 "num_attention_heads": 64,23 "num_hidden_layers": 64,24 "num_key_value_heads": 64,25 "output_mult": 0.5,26 "pretraining_tp": 1,27 "rms_norm_eps": 1e-05,28 "rope_scaling": null,29 "rope_theta": 10000,30 "tie_word_embeddings": false,31 "torch_dtype": "bfloat16",32 "transformers_version": "4.40.0",33 "use_cache": true,34 "use_mup": true,35 "vocab_size": 8038436}37 