Text Generation
MLX
Safetensors
English
falcon_mamba
conversational
8-bit precision
ybelkada's picture
2d5f1cf2bd87ebcf23f9635326508c7b4b33df3d42cc64dde1f4e82d02efab3c
1bfee59 verified
raw
history blame
1.04 kB
{
"architectures": [
"FalconMambaForCausalLM"
],
"bos_token_id": 8,
"conv_kernel": 4,
"eos_token_id": 11,
"expand": 16,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.1,
"intermediate_size": 8192,
"layer_norm_epsilon": 1e-05,
"model_type": "falcon_mamba",
"num_hidden_layers": 64,
"pad_token_id": 0,
"quantization": {
"group_size": 64,
"bits": 8
},
"quantization_config": {
"group_size": 64,
"bits": 8
},
"rescale_prenorm_residual": false,
"residual_in_fp32": true,
"state_size": 16,
"tie_word_embeddings": false,
"time_step_floor": 0.0001,
"time_step_init_scheme": "random",
"time_step_max": 0.1,
"time_step_min": 0.001,
"time_step_rank": 256,
"time_step_scale": 1.0,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.0.dev0",
"use_bias": false,
"use_cache": true,
"use_conv_bias": true,
"use_mambapy": false,
"vocab_size": 65024
}