ai21labs/Jamba-tiny-dev
14352k
1{2 "architectures": [3 "JambaForCausalLM"4 ],5 "attention_dropout": 0.0,6 "attn_layer_offset": 4,7 "attn_layer_period": 8,8 "bos_token_id": 1,9 "eos_token_id": 2,10 "expert_layer_offset": 1,11 "expert_layer_period": 2,12 "hidden_act": "silu",13 "hidden_size": 512,14 "initializer_range": 0.02,15 "intermediate_size": 2048,16 "mamba_conv_bias": true,17 "mamba_d_conv": 4,18 "mamba_d_state": 16,19 "mamba_dt_rank": 32,20 "mamba_expand": 2,21 "mamba_proj_bias": false,22 "max_position_embeddings": 262144,23 "model_type": "jamba",24 "num_attention_heads": 8,25 "num_experts": 8,26 "num_experts_per_tok": 2,27 "num_hidden_layers": 16,28 "num_key_value_heads": 2,29 "num_logits_to_keep": 1,30 "output_router_logits": false,31 "pad_token_id": 0,32 "rms_norm_eps": 1e-06,33 "router_aux_loss_coef": 0.001,34 "sliding_window": null,35 "tie_word_embeddings": false,36 "torch_dtype": "bfloat16",37 "transformers_version": "4.40.2",38 "use_cache": true,39 "use_mamba_kernels": true,40 "vocab_size": 6553641}42 