| { |
| "_name_or_path": "MiniPLM-Mamba-130M", |
| "architectures": [ |
| "MambaForCausalLM" |
| ], |
| "bos_token_id": 0, |
| "conv_kernel": 4, |
| "d_inner": 1536, |
| "d_model": 768, |
| "eos_token_id": 11, |
| "expand": 2, |
| "fused_add_norm": true, |
| "hidden_act": "silu", |
| "hidden_size": 768, |
| "initializer_range": 0.1, |
| "intermediate_size": 1536, |
| "is_model_parallel": false, |
| "layer_norm_epsilon": 1e-05, |
| "model_type": "mamba", |
| "n_layer": 24, |
| "num_hidden_layers": 24, |
| "pad_token_id": 11, |
| "pad_vocab_size_multiple": 8, |
| "quantization_config": { |
| "_load_in_4bit": true, |
| "_load_in_8bit": false, |
| "bnb_4bit_compute_dtype": "float32", |
| "bnb_4bit_quant_storage": "uint8", |
| "bnb_4bit_quant_type": "fp4", |
| "bnb_4bit_use_double_quant": false, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": null, |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": true, |
| "load_in_8bit": false, |
| "quant_method": "bitsandbytes" |
| }, |
| "rescale_prenorm_residual": false, |
| "residual_in_fp32": true, |
| "rms_norm": true, |
| "ssm_cfg": {}, |
| "state_size": 16, |
| "time_step_floor": 0.0001, |
| "time_step_init_scheme": "random", |
| "time_step_max": 0.1, |
| "time_step_min": 0.001, |
| "time_step_rank": 48, |
| "time_step_scale": 1.0, |
| "torch_dtype": "float16", |
| "transformers_version": "4.47.1", |
| "use_bias": false, |
| "use_cache": true, |
| "use_conv_bias": true, |
| "use_mambapy": false, |
| "use_memory_efficient_attention": true, |
| "vocab_size": 65024 |
| } |
|
|
