yzhuang's picture
Training in progress, step 1000
484b217 verified
raw
history blame
3.44 kB
{
"_name_or_path": "yzhuang/llava-jamba-1.5-Mini-linear-anyres-patch",
"architectures": [
"LlavaJambaForCausalLM"
],
"attention_dropout": 0.0,
"attn_layer_offset": 4,
"attn_layer_period": 8,
"bos_token_id": 1,
"eos_token_id": [
2,
518
],
"expert_layer_offset": 1,
"expert_layer_period": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "anyres",
"image_grid_pinpoints": [
[
336,
336
],
[
336,
672
],
[
336,
1008
],
[
336,
1344
],
[
336,
1680
],
[
336,
2016
],
[
336,
2352
],
[
336,
2688
],
[
336,
3024
],
[
336,
3360
],
[
336,
3696
],
[
336,
4032
],
[
336,
4368
],
[
336,
4704
],
[
336,
5040
],
[
672,
336
],
[
672,
672
],
[
672,
1008
],
[
672,
1344
],
[
672,
1680
],
[
672,
2016
],
[
672,
2352
],
[
672,
2688
],
[
1008,
336
],
[
1008,
672
],
[
1008,
1008
],
[
1008,
1344
],
[
1008,
1680
],
[
1344,
336
],
[
1344,
672
],
[
1344,
1008
],
[
1344,
1344
],
[
1680,
336
],
[
1680,
672
],
[
1680,
1008
],
[
2016,
336
],
[
2016,
672
],
[
2352,
336
],
[
2352,
672
],
[
2688,
336
],
[
2688,
672
],
[
3024,
336
],
[
3360,
336
],
[
3696,
336
],
[
4032,
336
],
[
4368,
336
],
[
4704,
336
],
[
5040,
336
]
],
"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,
"mm_hidden_size": 1024,
"mm_patch_merge_type": "spatial_unpad",
"mm_projector_lr": null,
"mm_projector_type": "linear",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
"mm_vision_tower_lr": 2e-06,
"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,
"rms_norm_eps": 1e-06,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 18240,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.45.0.dev0",
"tune_mm_mlp_adapter": false,
"unfreeze_mm_vision_tower": false,
"use_cache": false,
"use_image_rope": false,
"use_mamba_kernels": true,
"use_mm_proj": true,
"vocab_size": 65536
}