Upload params.json with huggingface_hub
Browse files- params.json +111 -10
params.json
CHANGED
|
@@ -1,11 +1,112 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"dim": 12288,
|
| 3 |
+
"n_layers": 88,
|
| 4 |
+
"head_dim": 128,
|
| 5 |
+
"hidden_dim": 28672,
|
| 6 |
+
"n_heads": 96,
|
| 7 |
+
"n_kv_heads": 8,
|
| 8 |
+
"use_biases": false,
|
| 9 |
+
"causal": true,
|
| 10 |
+
"rope_theta": 1000000000.0,
|
| 11 |
+
"norm_eps": 1e-05,
|
| 12 |
+
"init": "DEFAULT",
|
| 13 |
+
"dropout": 0.0,
|
| 14 |
+
"vocab_size": 32768,
|
| 15 |
+
"model_parallel": 1,
|
| 16 |
+
"is_sequence_parallel": false,
|
| 17 |
+
"context_parallel": 1,
|
| 18 |
+
"tied_embeddings": false,
|
| 19 |
+
"model_pipelining": 1,
|
| 20 |
+
"virtual_model_pipelining": 1,
|
| 21 |
+
"efficient_attn": true,
|
| 22 |
+
"fused_rms_norm": true,
|
| 23 |
+
"ragged_attention": null,
|
| 24 |
+
"checkpoint": true,
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"max_concurrent_tokens": 65536,
|
| 27 |
+
"rms_norm": "PRE",
|
| 28 |
+
"cust_bwd": false,
|
| 29 |
+
"recompute_w1_every": 0,
|
| 30 |
+
"recompute_w3_every": 0,
|
| 31 |
+
"recompute_attn_every": 0,
|
| 32 |
+
"freeze_nonembedding": false,
|
| 33 |
+
"fsdp2": false,
|
| 34 |
+
"zero2": false,
|
| 35 |
+
"fsdp_optimize_backward_concat_if_pp": true,
|
| 36 |
+
"cutlass": false,
|
| 37 |
+
"attn_tanh_gating": null,
|
| 38 |
+
"softmax_tanh_gating": null,
|
| 39 |
+
"deterministic_flash_attn": false,
|
| 40 |
+
"moe": null,
|
| 41 |
+
"mamba": null,
|
| 42 |
+
"multimodal": {
|
| 43 |
+
"vis_encoder_id": "ViT-g-16-1024-rope2d",
|
| 44 |
+
"encoder_type": "vit_packed_sequence",
|
| 45 |
+
"vision_encoder_args": {
|
| 46 |
+
"hidden_size": 1408,
|
| 47 |
+
"num_channels": 3,
|
| 48 |
+
"max_image_size": 1024,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"inference_args": {
|
| 51 |
+
"centering": "default",
|
| 52 |
+
"interpolation": "bicubic",
|
| 53 |
+
"eval_image_size": 1024,
|
| 54 |
+
"variable_image_size": true,
|
| 55 |
+
"spatial_merge_size": 1,
|
| 56 |
+
"use_cv2_resize": true
|
| 57 |
+
},
|
| 58 |
+
"stride": null,
|
| 59 |
+
"residual_connection": null,
|
| 60 |
+
"pos_embed": "rope-2D",
|
| 61 |
+
"rope_theta": 10000.0,
|
| 62 |
+
"quick_gelu": true,
|
| 63 |
+
"ln_pre": true,
|
| 64 |
+
"pool_type": "tok",
|
| 65 |
+
"final_ln_after_pool": false,
|
| 66 |
+
"intermediate_size": 6144,
|
| 67 |
+
"projection_dim": 1024,
|
| 68 |
+
"num_hidden_layers": 40,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"qk_norm": false,
|
| 71 |
+
"checkpoint": true
|
| 72 |
+
},
|
| 73 |
+
"vis_encoder_pretraining": null,
|
| 74 |
+
"pretrained_model_path": null,
|
| 75 |
+
"bos_token_id": 1,
|
| 76 |
+
"image_token_id": 10,
|
| 77 |
+
"image_newline_id": -1,
|
| 78 |
+
"image_end_id": -1,
|
| 79 |
+
"load_pretrained_encoder": false,
|
| 80 |
+
"mm_projector_id": "mlp",
|
| 81 |
+
"use_mlp_bias": false,
|
| 82 |
+
"add_layer_norm": false,
|
| 83 |
+
"self_attention_args": {
|
| 84 |
+
"freeze_vis_encoder": false,
|
| 85 |
+
"freeze_lang_decoder": false
|
| 86 |
+
},
|
| 87 |
+
"cross_attention_args": null,
|
| 88 |
+
"use_cross_attention": false,
|
| 89 |
+
"spatial_merge_size": 1
|
| 90 |
+
},
|
| 91 |
+
"quantization": {
|
| 92 |
+
"qformat_weight": "fp8_e4m3",
|
| 93 |
+
"qformat_emb": null,
|
| 94 |
+
"qformat_classif": null,
|
| 95 |
+
"qformat_norm": null,
|
| 96 |
+
"qformat_act": "fp8_e4m3",
|
| 97 |
+
"qformat_kv": "fp8_e4m3",
|
| 98 |
+
"qformat_image_tokens": "fp8_e4m3",
|
| 99 |
+
"qscheme_weight": "TENSOR",
|
| 100 |
+
"qscheme_emb": "TENSOR",
|
| 101 |
+
"qscheme_classif": "TENSOR",
|
| 102 |
+
"qscheme_act": "TENSOR",
|
| 103 |
+
"calibration_steps": 200,
|
| 104 |
+
"block_size": 128,
|
| 105 |
+
"tie_qkv": true,
|
| 106 |
+
"tie_w123_moe": false,
|
| 107 |
+
"save_act_logs": false
|
| 108 |
+
},
|
| 109 |
+
"layer_drop": null,
|
| 110 |
+
"override_parameters_str": "",
|
| 111 |
+
"max_seq_len": 32768
|
| 112 |
+
}
|