| { |
| "architectures": [ |
| "JambaForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "attn_layer_offset": 4, |
| "attn_layer_period": 8, |
| "bos_token_id": 1, |
| "dtype": "bfloat16", |
| "eos_token_id": 519, |
| "expert_layer_offset": 1, |
| "expert_layer_period": 2, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "mamba_conv_bias": true, |
| "mamba_d_conv": 4, |
| "mamba_d_state": 16, |
| "mamba_dt_rank": 256, |
| "mamba_expand": 2, |
| "mamba_proj_bias": false, |
| "max_position_embeddings": 262144, |
| "model_type": "jamba", |
| "num_attention_heads": 32, |
| "num_experts": 16, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "num_logits_to_keep": 1, |
| "output_router_logits": false, |
| "pad_token_id": 0, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "float-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": true, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": null, |
| "observer_kwargs": {}, |
| "strategy": "token", |
| "symmetric": true, |
| "type": "float" |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "minmax", |
| "observer_kwargs": {}, |
| "strategy": "channel", |
| "symmetric": true, |
| "type": "float" |
| } |
| } |
| }, |
| "format": "float-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.layers.0.mamba.in_proj", |
| "model.layers.0.mamba.x_proj", |
| "model.layers.0.mamba.dt_proj", |
| "model.layers.0.mamba.out_proj", |
| "model.layers.1.mamba.in_proj", |
| "model.layers.1.mamba.x_proj", |
| "model.layers.1.mamba.dt_proj", |
| "model.layers.1.mamba.out_proj", |
| "model.layers.1.feed_forward.router", |
| "model.layers.2.mamba.in_proj", |
| "model.layers.2.mamba.x_proj", |
| "model.layers.2.mamba.dt_proj", |
| "model.layers.2.mamba.out_proj", |
| "model.layers.3.mamba.in_proj", |
| "model.layers.3.mamba.x_proj", |
| "model.layers.3.mamba.dt_proj", |
| "model.layers.3.mamba.out_proj", |
| "model.layers.3.feed_forward.router", |
| "model.layers.5.mamba.in_proj", |
| "model.layers.5.mamba.x_proj", |
| "model.layers.5.mamba.dt_proj", |
| "model.layers.5.mamba.out_proj", |
| "model.layers.5.feed_forward.router", |
| "model.layers.6.mamba.in_proj", |
| "model.layers.6.mamba.x_proj", |
| "model.layers.6.mamba.dt_proj", |
| "model.layers.6.mamba.out_proj", |
| "model.layers.7.mamba.in_proj", |
| "model.layers.7.mamba.x_proj", |
| "model.layers.7.mamba.dt_proj", |
| "model.layers.7.mamba.out_proj", |
| "model.layers.7.feed_forward.router", |
| "model.layers.8.mamba.in_proj", |
| "model.layers.8.mamba.x_proj", |
| "model.layers.8.mamba.dt_proj", |
| "model.layers.8.mamba.out_proj", |
| "model.layers.9.mamba.in_proj", |
| "model.layers.9.mamba.x_proj", |
| "model.layers.9.mamba.dt_proj", |
| "model.layers.9.mamba.out_proj", |
| "model.layers.9.feed_forward.router", |
| "model.layers.10.mamba.in_proj", |
| "model.layers.10.mamba.x_proj", |
| "model.layers.10.mamba.dt_proj", |
| "model.layers.10.mamba.out_proj", |
| "model.layers.11.mamba.in_proj", |
| "model.layers.11.mamba.x_proj", |
| "model.layers.11.mamba.dt_proj", |
| "model.layers.11.mamba.out_proj", |
| "model.layers.11.feed_forward.router", |
| "model.layers.13.mamba.in_proj", |
| "model.layers.13.mamba.x_proj", |
| "model.layers.13.mamba.dt_proj", |
| "model.layers.13.mamba.out_proj", |
| "model.layers.13.feed_forward.router", |
| "model.layers.14.mamba.in_proj", |
| "model.layers.14.mamba.x_proj", |
| "model.layers.14.mamba.dt_proj", |
| "model.layers.14.mamba.out_proj", |
| "model.layers.15.mamba.in_proj", |
| "model.layers.15.mamba.x_proj", |
| "model.layers.15.mamba.dt_proj", |
| "model.layers.15.mamba.out_proj", |
| "model.layers.15.feed_forward.router", |
| "model.layers.16.mamba.in_proj", |
| "model.layers.16.mamba.x_proj", |
| "model.layers.16.mamba.dt_proj", |
| "model.layers.16.mamba.out_proj", |
| "model.layers.17.mamba.in_proj", |
| "model.layers.17.mamba.x_proj", |
| "model.layers.17.mamba.dt_proj", |
| "model.layers.17.mamba.out_proj", |
| "model.layers.17.feed_forward.router", |
| "model.layers.18.mamba.in_proj", |
| "model.layers.18.mamba.x_proj", |
| "model.layers.18.mamba.dt_proj", |
| "model.layers.18.mamba.out_proj", |
| "model.layers.19.mamba.in_proj", |
| "model.layers.19.mamba.x_proj", |
| "model.layers.19.mamba.dt_proj", |
| "model.layers.19.mamba.out_proj", |
| "model.layers.19.feed_forward.router", |
| "model.layers.21.mamba.in_proj", |
| "model.layers.21.mamba.x_proj", |
| "model.layers.21.mamba.dt_proj", |
| "model.layers.21.mamba.out_proj", |
| "model.layers.21.feed_forward.router", |
| "model.layers.22.mamba.in_proj", |
| "model.layers.22.mamba.x_proj", |
| "model.layers.22.mamba.dt_proj", |
| "model.layers.22.mamba.out_proj", |
| "model.layers.23.mamba.in_proj", |
| "model.layers.23.mamba.x_proj", |
| "model.layers.23.mamba.dt_proj", |
| "model.layers.23.mamba.out_proj", |
| "model.layers.23.feed_forward.router", |
| "model.layers.24.mamba.in_proj", |
| "model.layers.24.mamba.x_proj", |
| "model.layers.24.mamba.dt_proj", |
| "model.layers.24.mamba.out_proj", |
| "model.layers.25.mamba.in_proj", |
| "model.layers.25.mamba.x_proj", |
| "model.layers.25.mamba.dt_proj", |
| "model.layers.25.mamba.out_proj", |
| "model.layers.25.feed_forward.router", |
| "model.layers.26.mamba.in_proj", |
| "model.layers.26.mamba.x_proj", |
| "model.layers.26.mamba.dt_proj", |
| "model.layers.26.mamba.out_proj", |
| "model.layers.27.mamba.in_proj", |
| "model.layers.27.mamba.x_proj", |
| "model.layers.27.mamba.dt_proj", |
| "model.layers.27.mamba.out_proj", |
| "model.layers.27.feed_forward.router", |
| "model.layers.29.mamba.in_proj", |
| "model.layers.29.mamba.x_proj", |
| "model.layers.29.mamba.dt_proj", |
| "model.layers.29.mamba.out_proj", |
| "model.layers.29.feed_forward.router", |
| "model.layers.30.mamba.in_proj", |
| "model.layers.30.mamba.x_proj", |
| "model.layers.30.mamba.dt_proj", |
| "model.layers.30.mamba.out_proj", |
| "model.layers.31.mamba.in_proj", |
| "model.layers.31.mamba.x_proj", |
| "model.layers.31.mamba.dt_proj", |
| "model.layers.31.mamba.out_proj", |
| "model.layers.31.feed_forward.router", |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.13.0" |
| }, |
| "rms_norm_eps": 1e-06, |
| "router_aux_loss_coef": 0.001, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.3", |
| "use_cache": true, |
| "use_mamba_kernels": true, |
| "vocab_size": 65536 |
| } |
|
|