Add WebGPU pack for Maple 361db5da
Browse files- .gitattributes +27 -0
- README.md +29 -0
- config.json +120 -0
- embeddings.mwg +3 -0
- final-norm.mwg +1 -0
- flash-head.mwg +3 -0
- layers/layer-00.mwg +3 -0
- layers/layer-01.mwg +3 -0
- layers/layer-02.mwg +3 -0
- layers/layer-03.mwg +3 -0
- layers/layer-04.mwg +3 -0
- layers/layer-05.mwg +3 -0
- layers/layer-06.mwg +3 -0
- layers/layer-07.mwg +3 -0
- layers/layer-08.mwg +3 -0
- layers/layer-09.mwg +3 -0
- layers/layer-10.mwg +3 -0
- layers/layer-11.mwg +3 -0
- layers/layer-12.mwg +3 -0
- layers/layer-13.mwg +3 -0
- layers/layer-14.mwg +3 -0
- layers/layer-15.mwg +3 -0
- layers/layer-16.mwg +3 -0
- layers/layer-17.mwg +3 -0
- layers/layer-18.mwg +3 -0
- layers/layer-19.mwg +3 -0
- layers/layer-20.mwg +3 -0
- layers/layer-21.mwg +3 -0
- layers/layer-22.mwg +3 -0
- layers/layer-23.mwg +3 -0
- lm-head.mwg +3 -0
- manifest.json +1 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,30 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
embeddings.mwg filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
flash-head.mwg filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
layers/layer-00.mwg filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
layers/layer-01.mwg filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
layers/layer-02.mwg filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
layers/layer-03.mwg filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
layers/layer-04.mwg filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
layers/layer-05.mwg filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
layers/layer-06.mwg filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
layers/layer-07.mwg filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
layers/layer-08.mwg filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
layers/layer-09.mwg filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
layers/layer-10.mwg filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
layers/layer-11.mwg filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
layers/layer-12.mwg filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
layers/layer-13.mwg filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
layers/layer-14.mwg filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
layers/layer-15.mwg filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
layers/layer-16.mwg filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
layers/layer-17.mwg filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
layers/layer-18.mwg filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
layers/layer-19.mwg filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
layers/layer-20.mwg filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
layers/layer-21.mwg filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
layers/layer-22.mwg filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
layers/layer-23.mwg filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
lm-head.mwg filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: webgpu
|
| 4 |
+
base_model: deepgrove/maple-preview
|
| 5 |
+
tags:
|
| 6 |
+
- webgpu
|
| 7 |
+
- browser
|
| 8 |
+
- text-generation
|
| 9 |
+
- quantized
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Maple-Preview WebGPU Pack
|
| 13 |
+
|
| 14 |
+
Lossless browser-streaming repack of
|
| 15 |
+
[`deepgrove/maple-preview-2bit-mlx`](https://huggingface.co/deepgrove/maple-preview-2bit-mlx)
|
| 16 |
+
for [`ProCreations/maple-webgpu`](https://huggingface.co/spaces/ProCreations/maple-webgpu).
|
| 17 |
+
|
| 18 |
+
No model values are changed and no additional quantization is applied. The
|
| 19 |
+
official 2-bit/4-bit MLX tensors are regrouped into one aligned binary file per
|
| 20 |
+
transformer layer, reducing browser loading from hundreds of range requests to
|
| 21 |
+
a small set of sequential CDN downloads.
|
| 22 |
+
|
| 23 |
+
- Source revision: `361db5da5e74ff6fcdd852d478e1f266ce11013a`
|
| 24 |
+
- Packed tensor bytes: `5.31 GB`
|
| 25 |
+
- Container format: `maple-webgpu-pack-v1`
|
| 26 |
+
- Original model and weights: MIT, © DeepGrove AI
|
| 27 |
+
|
| 28 |
+
This is a runtime artifact, not a separate model release. See `manifest.json`
|
| 29 |
+
for exact byte offsets, shapes, dtypes, and source tensor names.
|
config.json
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MapleForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"embedding_dropout": 0.0,
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"first_k_dense_replace": 0,
|
| 11 |
+
"flash_head": {
|
| 12 |
+
"bits": 4,
|
| 13 |
+
"cluster_size": 32,
|
| 14 |
+
"force_tokens": [
|
| 15 |
+
151645,
|
| 16 |
+
151668,
|
| 17 |
+
151643
|
| 18 |
+
],
|
| 19 |
+
"group_size": 64,
|
| 20 |
+
"head_bits": 4,
|
| 21 |
+
"head_group_size": 64,
|
| 22 |
+
"n_clusters": 4748,
|
| 23 |
+
"n_probes": 512,
|
| 24 |
+
"scaled_centroids": true
|
| 25 |
+
},
|
| 26 |
+
"hc": false,
|
| 27 |
+
"head_dim": 128,
|
| 28 |
+
"headwise_gate_swa": false,
|
| 29 |
+
"hidden_act": "silu",
|
| 30 |
+
"hidden_size": 2048,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 5120,
|
| 33 |
+
"layer_types": [
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"full_attention"
|
| 58 |
+
],
|
| 59 |
+
"max_position_embeddings": 128000,
|
| 60 |
+
"max_window_layers": 24,
|
| 61 |
+
"model_file": "maple.py",
|
| 62 |
+
"model_type": "maple",
|
| 63 |
+
"moe_intermediate_size": 512,
|
| 64 |
+
"moe_router_enable_expert_bias": false,
|
| 65 |
+
"moe_shared_expert_intermediate_size": 512,
|
| 66 |
+
"mtp_loss_scaling_factor": 0,
|
| 67 |
+
"nope_on_global_attention": false,
|
| 68 |
+
"norm_topk_prob": true,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_experts": 256,
|
| 71 |
+
"num_experts_per_tok": 8,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 4,
|
| 74 |
+
"num_nextn_predict_layers": 0,
|
| 75 |
+
"num_shared_experts": 0,
|
| 76 |
+
"output_dropout": 0.0,
|
| 77 |
+
"output_router_logits": false,
|
| 78 |
+
"pad_token_id": null,
|
| 79 |
+
"partial_rotary_factor": 0.5,
|
| 80 |
+
"preaffine": false,
|
| 81 |
+
"quantization": {
|
| 82 |
+
"bits": 2,
|
| 83 |
+
"group_size": 128,
|
| 84 |
+
"lm_head": {
|
| 85 |
+
"bits": 4,
|
| 86 |
+
"group_size": 64
|
| 87 |
+
},
|
| 88 |
+
"mode": "affine",
|
| 89 |
+
"model.word_embeddings": {
|
| 90 |
+
"bits": 4,
|
| 91 |
+
"group_size": 64
|
| 92 |
+
}
|
| 93 |
+
},
|
| 94 |
+
"quantization_config": {
|
| 95 |
+
"bits": 2,
|
| 96 |
+
"group_size": 128,
|
| 97 |
+
"lm_head": {
|
| 98 |
+
"bits": 4,
|
| 99 |
+
"group_size": 64
|
| 100 |
+
},
|
| 101 |
+
"mode": "affine",
|
| 102 |
+
"model.word_embeddings": {
|
| 103 |
+
"bits": 4,
|
| 104 |
+
"group_size": 64
|
| 105 |
+
}
|
| 106 |
+
},
|
| 107 |
+
"rms_norm_eps": 1e-06,
|
| 108 |
+
"rope_scaling": null,
|
| 109 |
+
"rope_theta": 10000,
|
| 110 |
+
"router_dtype": "fp32",
|
| 111 |
+
"sliding_window": 512,
|
| 112 |
+
"tie_word_embeddings": false,
|
| 113 |
+
"transformers_version": "4.57.1",
|
| 114 |
+
"use_bias": false,
|
| 115 |
+
"use_cache": true,
|
| 116 |
+
"use_qk_norm": true,
|
| 117 |
+
"use_qkv_bias": false,
|
| 118 |
+
"use_rmsnorm": true,
|
| 119 |
+
"vocab_size": 151936
|
| 120 |
+
}
|
embeddings.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aa71252d85643970971d08aec5401ad1380b9330726e1536203b1487aae43e4
|
| 3 |
+
size 175030272
|
final-norm.mwg
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?{?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?v?�?�?�?�?�?�?�?�?t?�?�?�?�?�?�?�?D?�?�?�?w?�?�?�?�?�?�?�?�?�?�?�?�?�?�?`?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?;��?h?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?~?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?z?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�??�?�?�?�?�?�?�?f?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?M?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?x?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?z?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?`?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?]?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?~?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?r?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?a?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?t?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?\?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�??�?�?�?�?[?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�???�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?r?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?z?�?�?�?�?�?�?�?�?�?{?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?S?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?~?�?�?�?�?�?�?�?�?�?�?e?�?�?�?�?�?�?�?i?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?^?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?E?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?_?�?�?�?@L?�?�?C?�?�?�?�?�?�?�?�?�?�?�?�?f?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?8?�?�?�?�?�?�?�?�?�?�?A?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?g?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?n?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�???�?�?�?�?�?{?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�;�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�??�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?y?�?�?�?�?�?�?�?�?�?�?�?�?Z?�?�?�?�?�?�?�?�?�?�?�?�?�?�?[?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?l?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?y?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?]?�?�?�?�?�?�?�?�?�?�?�?�?�?|?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?x?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?x?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?q?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?{?�?�?T?�?�?�?L?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?y?�?�?�?�?`?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?l?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?}?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?n?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�??�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?X?�?�?>?�?�?�?�?�?�?F?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?~?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?]?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�??�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?a?�?�?�?�?�?�?�?�?�?�?\?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?a?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?�?
|
flash-head.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9aaaf06eeef6e0ba5b75dc08e1ef333fc8d0984962d602fccb04ad796c40214b
|
| 3 |
+
size 6087168
|
layers/layer-00.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1053db29e0808e5591fc4a474ea7b28a564ef15e50362ffd199d21f349898b26
|
| 3 |
+
size 206588416
|
layers/layer-01.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bedfb318ad72cfee27bb80dce3626f2f14c6fcf846193b6b5bcee8141e2a9b56
|
| 3 |
+
size 206588416
|
layers/layer-02.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:905a24d044534ab7dd4b80160f750b1be435d9219247931e068076ccc32caf39
|
| 3 |
+
size 206588416
|
layers/layer-03.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f664e54c29ce6030ab6f53b7ee089c06b4efddd852569832ad07afbdc63fe03f
|
| 3 |
+
size 206588416
|
layers/layer-04.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8341b8e9c76c94e483ca324cb27e01fff2f8081996f3fcb981f973a264db7d9
|
| 3 |
+
size 206588416
|
layers/layer-05.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff09d57ef313906abb432268a4f7ba5a68fcbb7b125969dafc9493ba20bf51ef
|
| 3 |
+
size 206588416
|
layers/layer-06.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a98732c2b2f89cdb0e16db558ccaf3f00293338a446fbdf9dacbab55dafa0ed7
|
| 3 |
+
size 206588416
|
layers/layer-07.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d2260ec99b7ded37f76010d089d1a64099b1b07e78f643bc10cac1b91d0807a
|
| 3 |
+
size 206588416
|
layers/layer-08.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1842131738e2f51644c59b55cad9b065d1313c40efea195888c48755718208c2
|
| 3 |
+
size 206588416
|
layers/layer-09.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3df604a15e9d863b17647b4e9f16996fbb1d947947c5377327d193b8b48dd190
|
| 3 |
+
size 206588416
|
layers/layer-10.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6893d64244fb2c949f274ed76fa90e388ba6027a262c4c18d8e2abf49fd849ab
|
| 3 |
+
size 206588416
|
layers/layer-11.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05c6047ac144dd36a46be8aaba2526de817895ce9881178c1fcf0b9edc6e603b
|
| 3 |
+
size 206588416
|
layers/layer-12.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:721f36873bc9b863a67305cea3854e03bd5c2cb398ac87cfeb6a95aefa472dd2
|
| 3 |
+
size 206588416
|
layers/layer-13.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d544ab7652df34f7857ec32294a4b4db9add7f5d0ab032d55480a7486bef2e9
|
| 3 |
+
size 206588416
|
layers/layer-14.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b73560b606ecbcad3c47cb22eea6a8f6cf8f778d17b2a6391dff41e0ed61ecd6
|
| 3 |
+
size 206588416
|
layers/layer-15.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a5a38e65250df412c7b18adfea9009b5bd66a60bf5ce460cd0cc52fe8b4f029
|
| 3 |
+
size 206588416
|
layers/layer-16.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03720e30d8f23502dbaa027bd948b171ff0c2013555f133260ce85a171ccd194
|
| 3 |
+
size 206588416
|
layers/layer-17.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:905b927d311bd71a8889e95e4c6325368507fbc679f451043650f55e34bfae20
|
| 3 |
+
size 206588416
|
layers/layer-18.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e81d077bdb804b4f06cfc101787dd76505680a8d5d18b15d4230c2658179fb34
|
| 3 |
+
size 206588416
|
layers/layer-19.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a578082041cbb2e3794ef89cc4e17bcfda941c6626194eeacb872e35f2a37452
|
| 3 |
+
size 206588416
|
layers/layer-20.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93198fe8e1bf67adabc1a121be27a6daf32c6187b74fadf4e351172aa86c3dd3
|
| 3 |
+
size 206588416
|
layers/layer-21.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c793752185414a683f8e8a2d82899fa3c7eab07dca6d12a1984bed381b2a88e7
|
| 3 |
+
size 206588416
|
layers/layer-22.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dea25dc7f666b0ec2e46d588db09552f672ff53dc97ca0d7c9a7193246658a1
|
| 3 |
+
size 206588416
|
layers/layer-23.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5028a1b4296bbc72cb8a41a3917c6595de97067a4340dd1f107c3ae6d4cddd53
|
| 3 |
+
size 206588416
|
lm-head.mwg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a621ca715d5fec85b2d8c7707c2f757e5fd425ebe68ddd3ae3cbcf2c1506fea
|
| 3 |
+
size 175030272
|
manifest.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"format":"maple-webgpu-pack-v1","source":"deepgrove/maple-preview-2bit-mlx","source_revision":"361db5da5e74ff6fcdd852d478e1f266ce11013a","alignment":256,"files":{"embeddings.mwg":{"size":175030272,"tensors":["model.word_embeddings.biases","model.word_embeddings.scales","model.word_embeddings.weight"]},"final-norm.mwg":{"size":4096,"tensors":["model.norm.weight"]},"flash-head.mwg":{"size":6087168,"tensors":["lm_head_flash.centroids.biases","lm_head_flash.centroids.scales","lm_head_flash.centroids.weight","lm_head_flash.cluster_scale","lm_head_flash.token_map"]},"layers/layer-00.mwg":{"size":206588416,"tensors":["model.layers.0.input_layernorm.weight","model.layers.0.mlp.gate.weight","model.layers.0.mlp.switch_mlp.down_proj.row_alpha","model.layers.0.mlp.switch_mlp.down_proj.weight","model.layers.0.mlp.switch_mlp.gate_proj.row_alpha","model.layers.0.mlp.switch_mlp.gate_proj.weight","model.layers.0.mlp.switch_mlp.up_proj.row_alpha","model.layers.0.mlp.switch_mlp.up_proj.weight","model.layers.0.post_attention_layernorm.weight","model.layers.0.self_attn.k_norm.weight","model.layers.0.self_attn.k_proj.row_alpha","model.layers.0.self_attn.k_proj.weight","model.layers.0.self_attn.o_proj.row_alpha","model.layers.0.self_attn.o_proj.weight","model.layers.0.self_attn.q_norm.weight","model.layers.0.self_attn.q_proj.row_alpha","model.layers.0.self_attn.q_proj.weight","model.layers.0.self_attn.v_proj.row_alpha","model.layers.0.self_attn.v_proj.weight"]},"layers/layer-01.mwg":{"size":206588416,"tensors":["model.layers.1.input_layernorm.weight","model.layers.1.mlp.gate.weight","model.layers.1.mlp.switch_mlp.down_proj.row_alpha","model.layers.1.mlp.switch_mlp.down_proj.weight","model.layers.1.mlp.switch_mlp.gate_proj.row_alpha","model.layers.1.mlp.switch_mlp.gate_proj.weight","model.layers.1.mlp.switch_mlp.up_proj.row_alpha","model.layers.1.mlp.switch_mlp.up_proj.weight","model.layers.1.post_attention_layernorm.weight","model.layers.1.self_attn.k_norm.weight","model.layers.1.self_attn.k_proj.row_alpha","model.layers.1.self_attn.k_proj.weight","model.layers.1.self_attn.o_proj.row_alpha","model.layers.1.self_attn.o_proj.weight","model.layers.1.self_attn.q_norm.weight","model.layers.1.self_attn.q_proj.row_alpha","model.layers.1.self_attn.q_proj.weight","model.layers.1.self_attn.v_proj.row_alpha","model.layers.1.self_attn.v_proj.weight"]},"layers/layer-02.mwg":{"size":206588416,"tensors":["model.layers.2.input_layernorm.weight","model.layers.2.mlp.gate.weight","model.layers.2.mlp.switch_mlp.down_proj.row_alpha","model.layers.2.mlp.switch_mlp.down_proj.weight","model.layers.2.mlp.switch_mlp.gate_proj.row_alpha","model.layers.2.mlp.switch_mlp.gate_proj.weight","model.layers.2.mlp.switch_mlp.up_proj.row_alpha","model.layers.2.mlp.switch_mlp.up_proj.weight","model.layers.2.post_attention_layernorm.weight","model.layers.2.self_attn.k_norm.weight","model.layers.2.self_attn.k_proj.row_alpha","model.layers.2.self_attn.k_proj.weight","model.layers.2.self_attn.o_proj.row_alpha","model.layers.2.self_attn.o_proj.weight","model.layers.2.self_attn.q_norm.weight","model.layers.2.self_attn.q_proj.row_alpha","model.layers.2.self_attn.q_proj.weight","model.layers.2.self_attn.v_proj.row_alpha","model.layers.2.self_attn.v_proj.weight"]},"layers/layer-03.mwg":{"size":206588416,"tensors":["model.layers.3.input_layernorm.weight","model.layers.3.mlp.gate.weight","model.layers.3.mlp.switch_mlp.down_proj.row_alpha","model.layers.3.mlp.switch_mlp.down_proj.weight","model.layers.3.mlp.switch_mlp.gate_proj.row_alpha","model.layers.3.mlp.switch_mlp.gate_proj.weight","model.layers.3.mlp.switch_mlp.up_proj.row_alpha","model.layers.3.mlp.switch_mlp.up_proj.weight","model.layers.3.post_attention_layernorm.weight","model.layers.3.self_attn.k_norm.weight","model.layers.3.self_attn.k_proj.row_alpha","model.layers.3.self_attn.k_proj.weight","model.layers.3.self_attn.o_proj.row_alpha","model.layers.3.self_attn.o_proj.weight","model.layers.3.self_attn.q_norm.weight","model.layers.3.self_attn.q_proj.row_alpha","model.layers.3.self_attn.q_proj.weight","model.layers.3.self_attn.v_proj.row_alpha","model.layers.3.self_attn.v_proj.weight"]},"layers/layer-04.mwg":{"size":206588416,"tensors":["model.layers.4.input_layernorm.weight","model.layers.4.mlp.gate.weight","model.layers.4.mlp.switch_mlp.down_proj.row_alpha","model.layers.4.mlp.switch_mlp.down_proj.weight","model.layers.4.mlp.switch_mlp.gate_proj.row_alpha","model.layers.4.mlp.switch_mlp.gate_proj.weight","model.layers.4.mlp.switch_mlp.up_proj.row_alpha","model.layers.4.mlp.switch_mlp.up_proj.weight","model.layers.4.post_attention_layernorm.weight","model.layers.4.self_attn.k_norm.weight","model.layers.4.self_attn.k_proj.row_alpha","model.layers.4.self_attn.k_proj.weight","model.layers.4.self_attn.o_proj.row_alpha","model.layers.4.self_attn.o_proj.weight","model.layers.4.self_attn.q_norm.weight","model.layers.4.self_attn.q_proj.row_alpha","model.layers.4.self_attn.q_proj.weight","model.layers.4.self_attn.v_proj.row_alpha","model.layers.4.self_attn.v_proj.weight"]},"layers/layer-05.mwg":{"size":206588416,"tensors":["model.layers.5.input_layernorm.weight","model.layers.5.mlp.gate.weight","model.layers.5.mlp.switch_mlp.down_proj.row_alpha","model.layers.5.mlp.switch_mlp.down_proj.weight","model.layers.5.mlp.switch_mlp.gate_proj.row_alpha","model.layers.5.mlp.switch_mlp.gate_proj.weight","model.layers.5.mlp.switch_mlp.up_proj.row_alpha","model.layers.5.mlp.switch_mlp.up_proj.weight","model.layers.5.post_attention_layernorm.weight","model.layers.5.self_attn.k_norm.weight","model.layers.5.self_attn.k_proj.row_alpha","model.layers.5.self_attn.k_proj.weight","model.layers.5.self_attn.o_proj.row_alpha","model.layers.5.self_attn.o_proj.weight","model.layers.5.self_attn.q_norm.weight","model.layers.5.self_attn.q_proj.row_alpha","model.layers.5.self_attn.q_proj.weight","model.layers.5.self_attn.v_proj.row_alpha","model.layers.5.self_attn.v_proj.weight"]},"layers/layer-06.mwg":{"size":206588416,"tensors":["model.layers.6.input_layernorm.weight","model.layers.6.mlp.gate.weight","model.layers.6.mlp.switch_mlp.down_proj.row_alpha","model.layers.6.mlp.switch_mlp.down_proj.weight","model.layers.6.mlp.switch_mlp.gate_proj.row_alpha","model.layers.6.mlp.switch_mlp.gate_proj.weight","model.layers.6.mlp.switch_mlp.up_proj.row_alpha","model.layers.6.mlp.switch_mlp.up_proj.weight","model.layers.6.post_attention_layernorm.weight","model.layers.6.self_attn.k_norm.weight","model.layers.6.self_attn.k_proj.row_alpha","model.layers.6.self_attn.k_proj.weight","model.layers.6.self_attn.o_proj.row_alpha","model.layers.6.self_attn.o_proj.weight","model.layers.6.self_attn.q_norm.weight","model.layers.6.self_attn.q_proj.row_alpha","model.layers.6.self_attn.q_proj.weight","model.layers.6.self_attn.v_proj.row_alpha","model.layers.6.self_attn.v_proj.weight"]},"layers/layer-07.mwg":{"size":206588416,"tensors":["model.layers.7.input_layernorm.weight","model.layers.7.mlp.gate.weight","model.layers.7.mlp.switch_mlp.down_proj.row_alpha","model.layers.7.mlp.switch_mlp.down_proj.weight","model.layers.7.mlp.switch_mlp.gate_proj.row_alpha","model.layers.7.mlp.switch_mlp.gate_proj.weight","model.layers.7.mlp.switch_mlp.up_proj.row_alpha","model.layers.7.mlp.switch_mlp.up_proj.weight","model.layers.7.post_attention_layernorm.weight","model.layers.7.self_attn.k_norm.weight","model.layers.7.self_attn.k_proj.row_alpha","model.layers.7.self_attn.k_proj.weight","model.layers.7.self_attn.o_proj.row_alpha","model.layers.7.self_attn.o_proj.weight","model.layers.7.self_attn.q_norm.weight","model.layers.7.self_attn.q_proj.row_alpha","model.layers.7.self_attn.q_proj.weight","model.layers.7.self_attn.v_proj.row_alpha","model.layers.7.self_attn.v_proj.weight"]},"layers/layer-08.mwg":{"size":206588416,"tensors":["model.layers.8.input_layernorm.weight","model.layers.8.mlp.gate.weight","model.layers.8.mlp.switch_mlp.down_proj.row_alpha","model.layers.8.mlp.switch_mlp.down_proj.weight","model.layers.8.mlp.switch_mlp.gate_proj.row_alpha","model.layers.8.mlp.switch_mlp.gate_proj.weight","model.layers.8.mlp.switch_mlp.up_proj.row_alpha","model.layers.8.mlp.switch_mlp.up_proj.weight","model.layers.8.post_attention_layernorm.weight","model.layers.8.self_attn.k_norm.weight","model.layers.8.self_attn.k_proj.row_alpha","model.layers.8.self_attn.k_proj.weight","model.layers.8.self_attn.o_proj.row_alpha","model.layers.8.self_attn.o_proj.weight","model.layers.8.self_attn.q_norm.weight","model.layers.8.self_attn.q_proj.row_alpha","model.layers.8.self_attn.q_proj.weight","model.layers.8.self_attn.v_proj.row_alpha","model.layers.8.self_attn.v_proj.weight"]},"layers/layer-09.mwg":{"size":206588416,"tensors":["model.layers.9.input_layernorm.weight","model.layers.9.mlp.gate.weight","model.layers.9.mlp.switch_mlp.down_proj.row_alpha","model.layers.9.mlp.switch_mlp.down_proj.weight","model.layers.9.mlp.switch_mlp.gate_proj.row_alpha","model.layers.9.mlp.switch_mlp.gate_proj.weight","model.layers.9.mlp.switch_mlp.up_proj.row_alpha","model.layers.9.mlp.switch_mlp.up_proj.weight","model.layers.9.post_attention_layernorm.weight","model.layers.9.self_attn.k_norm.weight","model.layers.9.self_attn.k_proj.row_alpha","model.layers.9.self_attn.k_proj.weight","model.layers.9.self_attn.o_proj.row_alpha","model.layers.9.self_attn.o_proj.weight","model.layers.9.self_attn.q_norm.weight","model.layers.9.self_attn.q_proj.row_alpha","model.layers.9.self_attn.q_proj.weight","model.layers.9.self_attn.v_proj.row_alpha","model.layers.9.self_attn.v_proj.weight"]},"layers/layer-10.mwg":{"size":206588416,"tensors":["model.layers.10.input_layernorm.weight","model.layers.10.mlp.gate.weight","model.layers.10.mlp.switch_mlp.down_proj.row_alpha","model.layers.10.mlp.switch_mlp.down_proj.weight","model.layers.10.mlp.switch_mlp.gate_proj.row_alpha","model.layers.10.mlp.switch_mlp.gate_proj.weight","model.layers.10.mlp.switch_mlp.up_proj.row_alpha","model.layers.10.mlp.switch_mlp.up_proj.weight","model.layers.10.post_attention_layernorm.weight","model.layers.10.self_attn.k_norm.weight","model.layers.10.self_attn.k_proj.row_alpha","model.layers.10.self_attn.k_proj.weight","model.layers.10.self_attn.o_proj.row_alpha","model.layers.10.self_attn.o_proj.weight","model.layers.10.self_attn.q_norm.weight","model.layers.10.self_attn.q_proj.row_alpha","model.layers.10.self_attn.q_proj.weight","model.layers.10.self_attn.v_proj.row_alpha","model.layers.10.self_attn.v_proj.weight"]},"layers/layer-11.mwg":{"size":206588416,"tensors":["model.layers.11.input_layernorm.weight","model.layers.11.mlp.gate.weight","model.layers.11.mlp.switch_mlp.down_proj.row_alpha","model.layers.11.mlp.switch_mlp.down_proj.weight","model.layers.11.mlp.switch_mlp.gate_proj.row_alpha","model.layers.11.mlp.switch_mlp.gate_proj.weight","model.layers.11.mlp.switch_mlp.up_proj.row_alpha","model.layers.11.mlp.switch_mlp.up_proj.weight","model.layers.11.post_attention_layernorm.weight","model.layers.11.self_attn.k_norm.weight","model.layers.11.self_attn.k_proj.row_alpha","model.layers.11.self_attn.k_proj.weight","model.layers.11.self_attn.o_proj.row_alpha","model.layers.11.self_attn.o_proj.weight","model.layers.11.self_attn.q_norm.weight","model.layers.11.self_attn.q_proj.row_alpha","model.layers.11.self_attn.q_proj.weight","model.layers.11.self_attn.v_proj.row_alpha","model.layers.11.self_attn.v_proj.weight"]},"layers/layer-12.mwg":{"size":206588416,"tensors":["model.layers.12.input_layernorm.weight","model.layers.12.mlp.gate.weight","model.layers.12.mlp.switch_mlp.down_proj.row_alpha","model.layers.12.mlp.switch_mlp.down_proj.weight","model.layers.12.mlp.switch_mlp.gate_proj.row_alpha","model.layers.12.mlp.switch_mlp.gate_proj.weight","model.layers.12.mlp.switch_mlp.up_proj.row_alpha","model.layers.12.mlp.switch_mlp.up_proj.weight","model.layers.12.post_attention_layernorm.weight","model.layers.12.self_attn.k_norm.weight","model.layers.12.self_attn.k_proj.row_alpha","model.layers.12.self_attn.k_proj.weight","model.layers.12.self_attn.o_proj.row_alpha","model.layers.12.self_attn.o_proj.weight","model.layers.12.self_attn.q_norm.weight","model.layers.12.self_attn.q_proj.row_alpha","model.layers.12.self_attn.q_proj.weight","model.layers.12.self_attn.v_proj.row_alpha","model.layers.12.self_attn.v_proj.weight"]},"layers/layer-13.mwg":{"size":206588416,"tensors":["model.layers.13.input_layernorm.weight","model.layers.13.mlp.gate.weight","model.layers.13.mlp.switch_mlp.down_proj.row_alpha","model.layers.13.mlp.switch_mlp.down_proj.weight","model.layers.13.mlp.switch_mlp.gate_proj.row_alpha","model.layers.13.mlp.switch_mlp.gate_proj.weight","model.layers.13.mlp.switch_mlp.up_proj.row_alpha","model.layers.13.mlp.switch_mlp.up_proj.weight","model.layers.13.post_attention_layernorm.weight","model.layers.13.self_attn.k_norm.weight","model.layers.13.self_attn.k_proj.row_alpha","model.layers.13.self_attn.k_proj.weight","model.layers.13.self_attn.o_proj.row_alpha","model.layers.13.self_attn.o_proj.weight","model.layers.13.self_attn.q_norm.weight","model.layers.13.self_attn.q_proj.row_alpha","model.layers.13.self_attn.q_proj.weight","model.layers.13.self_attn.v_proj.row_alpha","model.layers.13.self_attn.v_proj.weight"]},"layers/layer-14.mwg":{"size":206588416,"tensors":["model.layers.14.input_layernorm.weight","model.layers.14.mlp.gate.weight","model.layers.14.mlp.switch_mlp.down_proj.row_alpha","model.layers.14.mlp.switch_mlp.down_proj.weight","model.layers.14.mlp.switch_mlp.gate_proj.row_alpha","model.layers.14.mlp.switch_mlp.gate_proj.weight","model.layers.14.mlp.switch_mlp.up_proj.row_alpha","model.layers.14.mlp.switch_mlp.up_proj.weight","model.layers.14.post_attention_layernorm.weight","model.layers.14.self_attn.k_norm.weight","model.layers.14.self_attn.k_proj.row_alpha","model.layers.14.self_attn.k_proj.weight","model.layers.14.self_attn.o_proj.row_alpha","model.layers.14.self_attn.o_proj.weight","model.layers.14.self_attn.q_norm.weight","model.layers.14.self_attn.q_proj.row_alpha","model.layers.14.self_attn.q_proj.weight","model.layers.14.self_attn.v_proj.row_alpha","model.layers.14.self_attn.v_proj.weight"]},"layers/layer-15.mwg":{"size":206588416,"tensors":["model.layers.15.input_layernorm.weight","model.layers.15.mlp.gate.weight","model.layers.15.mlp.switch_mlp.down_proj.row_alpha","model.layers.15.mlp.switch_mlp.down_proj.weight","model.layers.15.mlp.switch_mlp.gate_proj.row_alpha","model.layers.15.mlp.switch_mlp.gate_proj.weight","model.layers.15.mlp.switch_mlp.up_proj.row_alpha","model.layers.15.mlp.switch_mlp.up_proj.weight","model.layers.15.post_attention_layernorm.weight","model.layers.15.self_attn.k_norm.weight","model.layers.15.self_attn.k_proj.row_alpha","model.layers.15.self_attn.k_proj.weight","model.layers.15.self_attn.o_proj.row_alpha","model.layers.15.self_attn.o_proj.weight","model.layers.15.self_attn.q_norm.weight","model.layers.15.self_attn.q_proj.row_alpha","model.layers.15.self_attn.q_proj.weight","model.layers.15.self_attn.v_proj.row_alpha","model.layers.15.self_attn.v_proj.weight"]},"layers/layer-16.mwg":{"size":206588416,"tensors":["model.layers.16.input_layernorm.weight","model.layers.16.mlp.gate.weight","model.layers.16.mlp.switch_mlp.down_proj.row_alpha","model.layers.16.mlp.switch_mlp.down_proj.weight","model.layers.16.mlp.switch_mlp.gate_proj.row_alpha","model.layers.16.mlp.switch_mlp.gate_proj.weight","model.layers.16.mlp.switch_mlp.up_proj.row_alpha","model.layers.16.mlp.switch_mlp.up_proj.weight","model.layers.16.post_attention_layernorm.weight","model.layers.16.self_attn.k_norm.weight","model.layers.16.self_attn.k_proj.row_alpha","model.layers.16.self_attn.k_proj.weight","model.layers.16.self_attn.o_proj.row_alpha","model.layers.16.self_attn.o_proj.weight","model.layers.16.self_attn.q_norm.weight","model.layers.16.self_attn.q_proj.row_alpha","model.layers.16.self_attn.q_proj.weight","model.layers.16.self_attn.v_proj.row_alpha","model.layers.16.self_attn.v_proj.weight"]},"layers/layer-17.mwg":{"size":206588416,"tensors":["model.layers.17.input_layernorm.weight","model.layers.17.mlp.gate.weight","model.layers.17.mlp.switch_mlp.down_proj.row_alpha","model.layers.17.mlp.switch_mlp.down_proj.weight","model.layers.17.mlp.switch_mlp.gate_proj.row_alpha","model.layers.17.mlp.switch_mlp.gate_proj.weight","model.layers.17.mlp.switch_mlp.up_proj.row_alpha","model.layers.17.mlp.switch_mlp.up_proj.weight","model.layers.17.post_attention_layernorm.weight","model.layers.17.self_attn.k_norm.weight","model.layers.17.self_attn.k_proj.row_alpha","model.layers.17.self_attn.k_proj.weight","model.layers.17.self_attn.o_proj.row_alpha","model.layers.17.self_attn.o_proj.weight","model.layers.17.self_attn.q_norm.weight","model.layers.17.self_attn.q_proj.row_alpha","model.layers.17.self_attn.q_proj.weight","model.layers.17.self_attn.v_proj.row_alpha","model.layers.17.self_attn.v_proj.weight"]},"layers/layer-18.mwg":{"size":206588416,"tensors":["model.layers.18.input_layernorm.weight","model.layers.18.mlp.gate.weight","model.layers.18.mlp.switch_mlp.down_proj.row_alpha","model.layers.18.mlp.switch_mlp.down_proj.weight","model.layers.18.mlp.switch_mlp.gate_proj.row_alpha","model.layers.18.mlp.switch_mlp.gate_proj.weight","model.layers.18.mlp.switch_mlp.up_proj.row_alpha","model.layers.18.mlp.switch_mlp.up_proj.weight","model.layers.18.post_attention_layernorm.weight","model.layers.18.self_attn.k_norm.weight","model.layers.18.self_attn.k_proj.row_alpha","model.layers.18.self_attn.k_proj.weight","model.layers.18.self_attn.o_proj.row_alpha","model.layers.18.self_attn.o_proj.weight","model.layers.18.self_attn.q_norm.weight","model.layers.18.self_attn.q_proj.row_alpha","model.layers.18.self_attn.q_proj.weight","model.layers.18.self_attn.v_proj.row_alpha","model.layers.18.self_attn.v_proj.weight"]},"layers/layer-19.mwg":{"size":206588416,"tensors":["model.layers.19.input_layernorm.weight","model.layers.19.mlp.gate.weight","model.layers.19.mlp.switch_mlp.down_proj.row_alpha","model.layers.19.mlp.switch_mlp.down_proj.weight","model.layers.19.mlp.switch_mlp.gate_proj.row_alpha","model.layers.19.mlp.switch_mlp.gate_proj.weight","model.layers.19.mlp.switch_mlp.up_proj.row_alpha","model.layers.19.mlp.switch_mlp.up_proj.weight","model.layers.19.post_attention_layernorm.weight","model.layers.19.self_attn.k_norm.weight","model.layers.19.self_attn.k_proj.row_alpha","model.layers.19.self_attn.k_proj.weight","model.layers.19.self_attn.o_proj.row_alpha","model.layers.19.self_attn.o_proj.weight","model.layers.19.self_attn.q_norm.weight","model.layers.19.self_attn.q_proj.row_alpha","model.layers.19.self_attn.q_proj.weight","model.layers.19.self_attn.v_proj.row_alpha","model.layers.19.self_attn.v_proj.weight"]},"layers/layer-20.mwg":{"size":206588416,"tensors":["model.layers.20.input_layernorm.weight","model.layers.20.mlp.gate.weight","model.layers.20.mlp.switch_mlp.down_proj.row_alpha","model.layers.20.mlp.switch_mlp.down_proj.weight","model.layers.20.mlp.switch_mlp.gate_proj.row_alpha","model.layers.20.mlp.switch_mlp.gate_proj.weight","model.layers.20.mlp.switch_mlp.up_proj.row_alpha","model.layers.20.mlp.switch_mlp.up_proj.weight","model.layers.20.post_attention_layernorm.weight","model.layers.20.self_attn.k_norm.weight","model.layers.20.self_attn.k_proj.row_alpha","model.layers.20.self_attn.k_proj.weight","model.layers.20.self_attn.o_proj.row_alpha","model.layers.20.self_attn.o_proj.weight","model.layers.20.self_attn.q_norm.weight","model.layers.20.self_attn.q_proj.row_alpha","model.layers.20.self_attn.q_proj.weight","model.layers.20.self_attn.v_proj.row_alpha","model.layers.20.self_attn.v_proj.weight"]},"layers/layer-21.mwg":{"size":206588416,"tensors":["model.layers.21.input_layernorm.weight","model.layers.21.mlp.gate.weight","model.layers.21.mlp.switch_mlp.down_proj.row_alpha","model.layers.21.mlp.switch_mlp.down_proj.weight","model.layers.21.mlp.switch_mlp.gate_proj.row_alpha","model.layers.21.mlp.switch_mlp.gate_proj.weight","model.layers.21.mlp.switch_mlp.up_proj.row_alpha","model.layers.21.mlp.switch_mlp.up_proj.weight","model.layers.21.post_attention_layernorm.weight","model.layers.21.self_attn.k_norm.weight","model.layers.21.self_attn.k_proj.row_alpha","model.layers.21.self_attn.k_proj.weight","model.layers.21.self_attn.o_proj.row_alpha","model.layers.21.self_attn.o_proj.weight","model.layers.21.self_attn.q_norm.weight","model.layers.21.self_attn.q_proj.row_alpha","model.layers.21.self_attn.q_proj.weight","model.layers.21.self_attn.v_proj.row_alpha","model.layers.21.self_attn.v_proj.weight"]},"layers/layer-22.mwg":{"size":206588416,"tensors":["model.layers.22.input_layernorm.weight","model.layers.22.mlp.gate.weight","model.layers.22.mlp.switch_mlp.down_proj.row_alpha","model.layers.22.mlp.switch_mlp.down_proj.weight","model.layers.22.mlp.switch_mlp.gate_proj.row_alpha","model.layers.22.mlp.switch_mlp.gate_proj.weight","model.layers.22.mlp.switch_mlp.up_proj.row_alpha","model.layers.22.mlp.switch_mlp.up_proj.weight","model.layers.22.post_attention_layernorm.weight","model.layers.22.self_attn.k_norm.weight","model.layers.22.self_attn.k_proj.row_alpha","model.layers.22.self_attn.k_proj.weight","model.layers.22.self_attn.o_proj.row_alpha","model.layers.22.self_attn.o_proj.weight","model.layers.22.self_attn.q_norm.weight","model.layers.22.self_attn.q_proj.row_alpha","model.layers.22.self_attn.q_proj.weight","model.layers.22.self_attn.v_proj.row_alpha","model.layers.22.self_attn.v_proj.weight"]},"layers/layer-23.mwg":{"size":206588416,"tensors":["model.layers.23.input_layernorm.weight","model.layers.23.mlp.gate.weight","model.layers.23.mlp.switch_mlp.down_proj.row_alpha","model.layers.23.mlp.switch_mlp.down_proj.weight","model.layers.23.mlp.switch_mlp.gate_proj.row_alpha","model.layers.23.mlp.switch_mlp.gate_proj.weight","model.layers.23.mlp.switch_mlp.up_proj.row_alpha","model.layers.23.mlp.switch_mlp.up_proj.weight","model.layers.23.post_attention_layernorm.weight","model.layers.23.self_attn.k_norm.weight","model.layers.23.self_attn.k_proj.row_alpha","model.layers.23.self_attn.k_proj.weight","model.layers.23.self_attn.o_proj.row_alpha","model.layers.23.self_attn.o_proj.weight","model.layers.23.self_attn.q_norm.weight","model.layers.23.self_attn.q_proj.row_alpha","model.layers.23.self_attn.q_proj.weight","model.layers.23.self_attn.v_proj.row_alpha","model.layers.23.self_attn.v_proj.weight"]},"lm-head.mwg":{"size":175030272,"tensors":["lm_head.biases","lm_head.scales","lm_head.weight"]}},"tensors":{"model.word_embeddings.biases":{"file":"embeddings.mwg","offset":0,"nbytes":9723904,"dtype":"BF16","shape":[151936,32]},"model.word_embeddings.scales":{"file":"embeddings.mwg","offset":9723904,"nbytes":9723904,"dtype":"BF16","shape":[151936,32]},"model.word_embeddings.weight":{"file":"embeddings.mwg","offset":19447808,"nbytes":155582464,"dtype":"U32","shape":[151936,256]},"model.norm.weight":{"file":"final-norm.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"lm_head_flash.centroids.biases":{"file":"flash-head.mwg","offset":0,"nbytes":303872,"dtype":"BF16","shape":[4748,32]},"lm_head_flash.centroids.scales":{"file":"flash-head.mwg","offset":303872,"nbytes":303872,"dtype":"BF16","shape":[4748,32]},"lm_head_flash.centroids.weight":{"file":"flash-head.mwg","offset":607744,"nbytes":4861952,"dtype":"U32","shape":[4748,256]},"lm_head_flash.cluster_scale":{"file":"flash-head.mwg","offset":5469696,"nbytes":9496,"dtype":"BF16","shape":[4748]},"lm_head_flash.token_map":{"file":"flash-head.mwg","offset":5479424,"nbytes":607744,"dtype":"I32","shape":[4748,32]},"model.layers.0.input_layernorm.weight":{"file":"layers/layer-00.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.0.mlp.gate.weight":{"file":"layers/layer-00.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.0.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-00.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.0.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-00.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.0.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-00.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.0.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-00.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.0.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-00.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.0.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-00.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.0.post_attention_layernorm.weight":{"file":"layers/layer-00.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.0.self_attn.k_norm.weight":{"file":"layers/layer-00.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.0.self_attn.k_proj.row_alpha":{"file":"layers/layer-00.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.0.self_attn.k_proj.weight":{"file":"layers/layer-00.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.0.self_attn.o_proj.row_alpha":{"file":"layers/layer-00.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.0.self_attn.o_proj.weight":{"file":"layers/layer-00.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.0.self_attn.q_norm.weight":{"file":"layers/layer-00.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.0.self_attn.q_proj.row_alpha":{"file":"layers/layer-00.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.0.self_attn.q_proj.weight":{"file":"layers/layer-00.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.0.self_attn.v_proj.row_alpha":{"file":"layers/layer-00.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.0.self_attn.v_proj.weight":{"file":"layers/layer-00.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.1.input_layernorm.weight":{"file":"layers/layer-01.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.1.mlp.gate.weight":{"file":"layers/layer-01.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.1.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-01.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.1.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-01.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.1.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-01.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.1.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-01.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.1.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-01.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.1.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-01.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.1.post_attention_layernorm.weight":{"file":"layers/layer-01.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.1.self_attn.k_norm.weight":{"file":"layers/layer-01.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.1.self_attn.k_proj.row_alpha":{"file":"layers/layer-01.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.1.self_attn.k_proj.weight":{"file":"layers/layer-01.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.1.self_attn.o_proj.row_alpha":{"file":"layers/layer-01.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.1.self_attn.o_proj.weight":{"file":"layers/layer-01.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.1.self_attn.q_norm.weight":{"file":"layers/layer-01.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.1.self_attn.q_proj.row_alpha":{"file":"layers/layer-01.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.1.self_attn.q_proj.weight":{"file":"layers/layer-01.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.1.self_attn.v_proj.row_alpha":{"file":"layers/layer-01.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.1.self_attn.v_proj.weight":{"file":"layers/layer-01.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.2.input_layernorm.weight":{"file":"layers/layer-02.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.2.mlp.gate.weight":{"file":"layers/layer-02.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.2.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-02.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.2.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-02.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.2.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-02.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.2.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-02.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.2.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-02.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.2.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-02.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.2.post_attention_layernorm.weight":{"file":"layers/layer-02.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.2.self_attn.k_norm.weight":{"file":"layers/layer-02.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.2.self_attn.k_proj.row_alpha":{"file":"layers/layer-02.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.2.self_attn.k_proj.weight":{"file":"layers/layer-02.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.2.self_attn.o_proj.row_alpha":{"file":"layers/layer-02.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.2.self_attn.o_proj.weight":{"file":"layers/layer-02.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.2.self_attn.q_norm.weight":{"file":"layers/layer-02.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.2.self_attn.q_proj.row_alpha":{"file":"layers/layer-02.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.2.self_attn.q_proj.weight":{"file":"layers/layer-02.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.2.self_attn.v_proj.row_alpha":{"file":"layers/layer-02.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.2.self_attn.v_proj.weight":{"file":"layers/layer-02.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.3.input_layernorm.weight":{"file":"layers/layer-03.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.3.mlp.gate.weight":{"file":"layers/layer-03.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.3.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-03.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.3.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-03.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.3.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-03.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.3.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-03.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.3.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-03.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.3.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-03.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.3.post_attention_layernorm.weight":{"file":"layers/layer-03.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.3.self_attn.k_norm.weight":{"file":"layers/layer-03.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.3.self_attn.k_proj.row_alpha":{"file":"layers/layer-03.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.3.self_attn.k_proj.weight":{"file":"layers/layer-03.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.3.self_attn.o_proj.row_alpha":{"file":"layers/layer-03.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.3.self_attn.o_proj.weight":{"file":"layers/layer-03.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.3.self_attn.q_norm.weight":{"file":"layers/layer-03.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.3.self_attn.q_proj.row_alpha":{"file":"layers/layer-03.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.3.self_attn.q_proj.weight":{"file":"layers/layer-03.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.3.self_attn.v_proj.row_alpha":{"file":"layers/layer-03.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.3.self_attn.v_proj.weight":{"file":"layers/layer-03.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.4.input_layernorm.weight":{"file":"layers/layer-04.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.4.mlp.gate.weight":{"file":"layers/layer-04.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.4.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-04.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.4.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-04.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.4.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-04.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.4.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-04.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.4.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-04.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.4.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-04.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.4.post_attention_layernorm.weight":{"file":"layers/layer-04.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.4.self_attn.k_norm.weight":{"file":"layers/layer-04.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.4.self_attn.k_proj.row_alpha":{"file":"layers/layer-04.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.4.self_attn.k_proj.weight":{"file":"layers/layer-04.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.4.self_attn.o_proj.row_alpha":{"file":"layers/layer-04.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.4.self_attn.o_proj.weight":{"file":"layers/layer-04.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.4.self_attn.q_norm.weight":{"file":"layers/layer-04.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.4.self_attn.q_proj.row_alpha":{"file":"layers/layer-04.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.4.self_attn.q_proj.weight":{"file":"layers/layer-04.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.4.self_attn.v_proj.row_alpha":{"file":"layers/layer-04.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.4.self_attn.v_proj.weight":{"file":"layers/layer-04.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.5.input_layernorm.weight":{"file":"layers/layer-05.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.5.mlp.gate.weight":{"file":"layers/layer-05.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.5.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-05.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.5.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-05.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.5.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-05.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.5.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-05.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.5.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-05.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.5.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-05.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.5.post_attention_layernorm.weight":{"file":"layers/layer-05.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.5.self_attn.k_norm.weight":{"file":"layers/layer-05.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.5.self_attn.k_proj.row_alpha":{"file":"layers/layer-05.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.5.self_attn.k_proj.weight":{"file":"layers/layer-05.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.5.self_attn.o_proj.row_alpha":{"file":"layers/layer-05.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.5.self_attn.o_proj.weight":{"file":"layers/layer-05.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.5.self_attn.q_norm.weight":{"file":"layers/layer-05.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.5.self_attn.q_proj.row_alpha":{"file":"layers/layer-05.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.5.self_attn.q_proj.weight":{"file":"layers/layer-05.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.5.self_attn.v_proj.row_alpha":{"file":"layers/layer-05.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.5.self_attn.v_proj.weight":{"file":"layers/layer-05.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.6.input_layernorm.weight":{"file":"layers/layer-06.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.6.mlp.gate.weight":{"file":"layers/layer-06.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.6.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-06.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.6.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-06.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.6.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-06.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.6.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-06.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.6.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-06.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.6.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-06.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.6.post_attention_layernorm.weight":{"file":"layers/layer-06.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.6.self_attn.k_norm.weight":{"file":"layers/layer-06.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.6.self_attn.k_proj.row_alpha":{"file":"layers/layer-06.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.6.self_attn.k_proj.weight":{"file":"layers/layer-06.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.6.self_attn.o_proj.row_alpha":{"file":"layers/layer-06.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.6.self_attn.o_proj.weight":{"file":"layers/layer-06.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.6.self_attn.q_norm.weight":{"file":"layers/layer-06.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.6.self_attn.q_proj.row_alpha":{"file":"layers/layer-06.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.6.self_attn.q_proj.weight":{"file":"layers/layer-06.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.6.self_attn.v_proj.row_alpha":{"file":"layers/layer-06.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.6.self_attn.v_proj.weight":{"file":"layers/layer-06.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.7.input_layernorm.weight":{"file":"layers/layer-07.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.7.mlp.gate.weight":{"file":"layers/layer-07.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.7.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-07.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.7.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-07.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.7.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-07.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.7.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-07.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.7.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-07.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.7.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-07.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.7.post_attention_layernorm.weight":{"file":"layers/layer-07.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.7.self_attn.k_norm.weight":{"file":"layers/layer-07.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.7.self_attn.k_proj.row_alpha":{"file":"layers/layer-07.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.7.self_attn.k_proj.weight":{"file":"layers/layer-07.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.7.self_attn.o_proj.row_alpha":{"file":"layers/layer-07.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.7.self_attn.o_proj.weight":{"file":"layers/layer-07.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.7.self_attn.q_norm.weight":{"file":"layers/layer-07.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.7.self_attn.q_proj.row_alpha":{"file":"layers/layer-07.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.7.self_attn.q_proj.weight":{"file":"layers/layer-07.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.7.self_attn.v_proj.row_alpha":{"file":"layers/layer-07.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.7.self_attn.v_proj.weight":{"file":"layers/layer-07.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.8.input_layernorm.weight":{"file":"layers/layer-08.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.8.mlp.gate.weight":{"file":"layers/layer-08.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.8.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-08.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.8.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-08.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.8.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-08.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.8.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-08.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.8.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-08.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.8.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-08.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.8.post_attention_layernorm.weight":{"file":"layers/layer-08.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.8.self_attn.k_norm.weight":{"file":"layers/layer-08.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.8.self_attn.k_proj.row_alpha":{"file":"layers/layer-08.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.8.self_attn.k_proj.weight":{"file":"layers/layer-08.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.8.self_attn.o_proj.row_alpha":{"file":"layers/layer-08.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.8.self_attn.o_proj.weight":{"file":"layers/layer-08.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.8.self_attn.q_norm.weight":{"file":"layers/layer-08.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.8.self_attn.q_proj.row_alpha":{"file":"layers/layer-08.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.8.self_attn.q_proj.weight":{"file":"layers/layer-08.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.8.self_attn.v_proj.row_alpha":{"file":"layers/layer-08.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.8.self_attn.v_proj.weight":{"file":"layers/layer-08.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.9.input_layernorm.weight":{"file":"layers/layer-09.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.9.mlp.gate.weight":{"file":"layers/layer-09.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.9.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-09.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.9.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-09.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.9.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-09.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.9.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-09.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.9.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-09.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.9.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-09.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.9.post_attention_layernorm.weight":{"file":"layers/layer-09.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.9.self_attn.k_norm.weight":{"file":"layers/layer-09.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.9.self_attn.k_proj.row_alpha":{"file":"layers/layer-09.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.9.self_attn.k_proj.weight":{"file":"layers/layer-09.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.9.self_attn.o_proj.row_alpha":{"file":"layers/layer-09.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.9.self_attn.o_proj.weight":{"file":"layers/layer-09.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.9.self_attn.q_norm.weight":{"file":"layers/layer-09.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.9.self_attn.q_proj.row_alpha":{"file":"layers/layer-09.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.9.self_attn.q_proj.weight":{"file":"layers/layer-09.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.9.self_attn.v_proj.row_alpha":{"file":"layers/layer-09.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.9.self_attn.v_proj.weight":{"file":"layers/layer-09.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.10.input_layernorm.weight":{"file":"layers/layer-10.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.10.mlp.gate.weight":{"file":"layers/layer-10.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.10.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-10.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.10.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-10.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.10.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-10.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.10.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-10.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.10.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-10.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.10.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-10.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.10.post_attention_layernorm.weight":{"file":"layers/layer-10.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.10.self_attn.k_norm.weight":{"file":"layers/layer-10.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.10.self_attn.k_proj.row_alpha":{"file":"layers/layer-10.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.10.self_attn.k_proj.weight":{"file":"layers/layer-10.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.10.self_attn.o_proj.row_alpha":{"file":"layers/layer-10.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.10.self_attn.o_proj.weight":{"file":"layers/layer-10.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.10.self_attn.q_norm.weight":{"file":"layers/layer-10.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.10.self_attn.q_proj.row_alpha":{"file":"layers/layer-10.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.10.self_attn.q_proj.weight":{"file":"layers/layer-10.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.10.self_attn.v_proj.row_alpha":{"file":"layers/layer-10.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.10.self_attn.v_proj.weight":{"file":"layers/layer-10.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.11.input_layernorm.weight":{"file":"layers/layer-11.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.11.mlp.gate.weight":{"file":"layers/layer-11.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.11.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-11.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.11.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-11.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.11.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-11.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.11.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-11.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.11.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-11.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.11.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-11.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.11.post_attention_layernorm.weight":{"file":"layers/layer-11.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.11.self_attn.k_norm.weight":{"file":"layers/layer-11.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.11.self_attn.k_proj.row_alpha":{"file":"layers/layer-11.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.11.self_attn.k_proj.weight":{"file":"layers/layer-11.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.11.self_attn.o_proj.row_alpha":{"file":"layers/layer-11.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.11.self_attn.o_proj.weight":{"file":"layers/layer-11.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.11.self_attn.q_norm.weight":{"file":"layers/layer-11.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.11.self_attn.q_proj.row_alpha":{"file":"layers/layer-11.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.11.self_attn.q_proj.weight":{"file":"layers/layer-11.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.11.self_attn.v_proj.row_alpha":{"file":"layers/layer-11.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.11.self_attn.v_proj.weight":{"file":"layers/layer-11.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.12.input_layernorm.weight":{"file":"layers/layer-12.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.12.mlp.gate.weight":{"file":"layers/layer-12.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.12.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-12.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.12.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-12.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.12.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-12.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.12.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-12.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.12.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-12.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.12.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-12.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.12.post_attention_layernorm.weight":{"file":"layers/layer-12.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.12.self_attn.k_norm.weight":{"file":"layers/layer-12.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.12.self_attn.k_proj.row_alpha":{"file":"layers/layer-12.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.12.self_attn.k_proj.weight":{"file":"layers/layer-12.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.12.self_attn.o_proj.row_alpha":{"file":"layers/layer-12.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.12.self_attn.o_proj.weight":{"file":"layers/layer-12.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.12.self_attn.q_norm.weight":{"file":"layers/layer-12.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.12.self_attn.q_proj.row_alpha":{"file":"layers/layer-12.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.12.self_attn.q_proj.weight":{"file":"layers/layer-12.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.12.self_attn.v_proj.row_alpha":{"file":"layers/layer-12.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.12.self_attn.v_proj.weight":{"file":"layers/layer-12.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.13.input_layernorm.weight":{"file":"layers/layer-13.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.13.mlp.gate.weight":{"file":"layers/layer-13.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.13.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-13.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.13.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-13.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.13.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-13.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.13.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-13.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.13.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-13.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.13.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-13.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.13.post_attention_layernorm.weight":{"file":"layers/layer-13.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.13.self_attn.k_norm.weight":{"file":"layers/layer-13.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.13.self_attn.k_proj.row_alpha":{"file":"layers/layer-13.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.13.self_attn.k_proj.weight":{"file":"layers/layer-13.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.13.self_attn.o_proj.row_alpha":{"file":"layers/layer-13.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.13.self_attn.o_proj.weight":{"file":"layers/layer-13.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.13.self_attn.q_norm.weight":{"file":"layers/layer-13.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.13.self_attn.q_proj.row_alpha":{"file":"layers/layer-13.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.13.self_attn.q_proj.weight":{"file":"layers/layer-13.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.13.self_attn.v_proj.row_alpha":{"file":"layers/layer-13.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.13.self_attn.v_proj.weight":{"file":"layers/layer-13.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.14.input_layernorm.weight":{"file":"layers/layer-14.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.14.mlp.gate.weight":{"file":"layers/layer-14.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.14.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-14.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.14.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-14.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.14.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-14.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.14.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-14.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.14.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-14.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.14.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-14.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.14.post_attention_layernorm.weight":{"file":"layers/layer-14.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.14.self_attn.k_norm.weight":{"file":"layers/layer-14.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.14.self_attn.k_proj.row_alpha":{"file":"layers/layer-14.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.14.self_attn.k_proj.weight":{"file":"layers/layer-14.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.14.self_attn.o_proj.row_alpha":{"file":"layers/layer-14.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.14.self_attn.o_proj.weight":{"file":"layers/layer-14.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.14.self_attn.q_norm.weight":{"file":"layers/layer-14.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.14.self_attn.q_proj.row_alpha":{"file":"layers/layer-14.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.14.self_attn.q_proj.weight":{"file":"layers/layer-14.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.14.self_attn.v_proj.row_alpha":{"file":"layers/layer-14.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.14.self_attn.v_proj.weight":{"file":"layers/layer-14.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.15.input_layernorm.weight":{"file":"layers/layer-15.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.15.mlp.gate.weight":{"file":"layers/layer-15.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.15.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-15.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.15.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-15.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.15.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-15.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.15.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-15.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.15.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-15.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.15.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-15.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.15.post_attention_layernorm.weight":{"file":"layers/layer-15.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.15.self_attn.k_norm.weight":{"file":"layers/layer-15.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.15.self_attn.k_proj.row_alpha":{"file":"layers/layer-15.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.15.self_attn.k_proj.weight":{"file":"layers/layer-15.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.15.self_attn.o_proj.row_alpha":{"file":"layers/layer-15.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.15.self_attn.o_proj.weight":{"file":"layers/layer-15.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.15.self_attn.q_norm.weight":{"file":"layers/layer-15.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.15.self_attn.q_proj.row_alpha":{"file":"layers/layer-15.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.15.self_attn.q_proj.weight":{"file":"layers/layer-15.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.15.self_attn.v_proj.row_alpha":{"file":"layers/layer-15.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.15.self_attn.v_proj.weight":{"file":"layers/layer-15.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.16.input_layernorm.weight":{"file":"layers/layer-16.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.16.mlp.gate.weight":{"file":"layers/layer-16.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.16.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-16.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.16.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-16.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.16.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-16.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.16.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-16.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.16.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-16.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.16.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-16.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.16.post_attention_layernorm.weight":{"file":"layers/layer-16.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.16.self_attn.k_norm.weight":{"file":"layers/layer-16.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.16.self_attn.k_proj.row_alpha":{"file":"layers/layer-16.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.16.self_attn.k_proj.weight":{"file":"layers/layer-16.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.16.self_attn.o_proj.row_alpha":{"file":"layers/layer-16.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.16.self_attn.o_proj.weight":{"file":"layers/layer-16.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.16.self_attn.q_norm.weight":{"file":"layers/layer-16.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.16.self_attn.q_proj.row_alpha":{"file":"layers/layer-16.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.16.self_attn.q_proj.weight":{"file":"layers/layer-16.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.16.self_attn.v_proj.row_alpha":{"file":"layers/layer-16.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.16.self_attn.v_proj.weight":{"file":"layers/layer-16.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.17.input_layernorm.weight":{"file":"layers/layer-17.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.17.mlp.gate.weight":{"file":"layers/layer-17.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.17.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-17.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.17.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-17.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.17.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-17.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.17.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-17.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.17.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-17.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.17.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-17.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.17.post_attention_layernorm.weight":{"file":"layers/layer-17.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.17.self_attn.k_norm.weight":{"file":"layers/layer-17.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.17.self_attn.k_proj.row_alpha":{"file":"layers/layer-17.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.17.self_attn.k_proj.weight":{"file":"layers/layer-17.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.17.self_attn.o_proj.row_alpha":{"file":"layers/layer-17.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.17.self_attn.o_proj.weight":{"file":"layers/layer-17.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.17.self_attn.q_norm.weight":{"file":"layers/layer-17.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.17.self_attn.q_proj.row_alpha":{"file":"layers/layer-17.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.17.self_attn.q_proj.weight":{"file":"layers/layer-17.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.17.self_attn.v_proj.row_alpha":{"file":"layers/layer-17.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.17.self_attn.v_proj.weight":{"file":"layers/layer-17.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.18.input_layernorm.weight":{"file":"layers/layer-18.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.18.mlp.gate.weight":{"file":"layers/layer-18.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.18.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-18.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.18.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-18.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.18.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-18.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.18.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-18.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.18.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-18.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.18.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-18.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.18.post_attention_layernorm.weight":{"file":"layers/layer-18.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.18.self_attn.k_norm.weight":{"file":"layers/layer-18.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.18.self_attn.k_proj.row_alpha":{"file":"layers/layer-18.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.18.self_attn.k_proj.weight":{"file":"layers/layer-18.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.18.self_attn.o_proj.row_alpha":{"file":"layers/layer-18.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.18.self_attn.o_proj.weight":{"file":"layers/layer-18.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.18.self_attn.q_norm.weight":{"file":"layers/layer-18.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.18.self_attn.q_proj.row_alpha":{"file":"layers/layer-18.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.18.self_attn.q_proj.weight":{"file":"layers/layer-18.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.18.self_attn.v_proj.row_alpha":{"file":"layers/layer-18.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.18.self_attn.v_proj.weight":{"file":"layers/layer-18.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.19.input_layernorm.weight":{"file":"layers/layer-19.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.19.mlp.gate.weight":{"file":"layers/layer-19.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.19.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-19.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.19.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-19.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.19.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-19.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.19.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-19.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.19.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-19.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.19.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-19.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.19.post_attention_layernorm.weight":{"file":"layers/layer-19.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.19.self_attn.k_norm.weight":{"file":"layers/layer-19.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.19.self_attn.k_proj.row_alpha":{"file":"layers/layer-19.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.19.self_attn.k_proj.weight":{"file":"layers/layer-19.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.19.self_attn.o_proj.row_alpha":{"file":"layers/layer-19.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.19.self_attn.o_proj.weight":{"file":"layers/layer-19.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.19.self_attn.q_norm.weight":{"file":"layers/layer-19.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.19.self_attn.q_proj.row_alpha":{"file":"layers/layer-19.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.19.self_attn.q_proj.weight":{"file":"layers/layer-19.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.19.self_attn.v_proj.row_alpha":{"file":"layers/layer-19.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.19.self_attn.v_proj.weight":{"file":"layers/layer-19.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.20.input_layernorm.weight":{"file":"layers/layer-20.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.20.mlp.gate.weight":{"file":"layers/layer-20.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.20.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-20.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.20.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-20.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.20.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-20.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.20.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-20.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.20.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-20.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.20.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-20.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.20.post_attention_layernorm.weight":{"file":"layers/layer-20.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.20.self_attn.k_norm.weight":{"file":"layers/layer-20.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.20.self_attn.k_proj.row_alpha":{"file":"layers/layer-20.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.20.self_attn.k_proj.weight":{"file":"layers/layer-20.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.20.self_attn.o_proj.row_alpha":{"file":"layers/layer-20.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.20.self_attn.o_proj.weight":{"file":"layers/layer-20.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.20.self_attn.q_norm.weight":{"file":"layers/layer-20.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.20.self_attn.q_proj.row_alpha":{"file":"layers/layer-20.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.20.self_attn.q_proj.weight":{"file":"layers/layer-20.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.20.self_attn.v_proj.row_alpha":{"file":"layers/layer-20.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.20.self_attn.v_proj.weight":{"file":"layers/layer-20.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.21.input_layernorm.weight":{"file":"layers/layer-21.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.21.mlp.gate.weight":{"file":"layers/layer-21.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.21.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-21.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.21.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-21.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.21.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-21.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.21.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-21.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.21.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-21.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.21.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-21.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.21.post_attention_layernorm.weight":{"file":"layers/layer-21.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.21.self_attn.k_norm.weight":{"file":"layers/layer-21.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.21.self_attn.k_proj.row_alpha":{"file":"layers/layer-21.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.21.self_attn.k_proj.weight":{"file":"layers/layer-21.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.21.self_attn.o_proj.row_alpha":{"file":"layers/layer-21.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.21.self_attn.o_proj.weight":{"file":"layers/layer-21.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.21.self_attn.q_norm.weight":{"file":"layers/layer-21.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.21.self_attn.q_proj.row_alpha":{"file":"layers/layer-21.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.21.self_attn.q_proj.weight":{"file":"layers/layer-21.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.21.self_attn.v_proj.row_alpha":{"file":"layers/layer-21.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.21.self_attn.v_proj.weight":{"file":"layers/layer-21.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.22.input_layernorm.weight":{"file":"layers/layer-22.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.22.mlp.gate.weight":{"file":"layers/layer-22.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.22.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-22.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.22.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-22.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.22.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-22.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.22.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-22.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.22.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-22.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.22.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-22.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.22.post_attention_layernorm.weight":{"file":"layers/layer-22.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.22.self_attn.k_norm.weight":{"file":"layers/layer-22.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.22.self_attn.k_proj.row_alpha":{"file":"layers/layer-22.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.22.self_attn.k_proj.weight":{"file":"layers/layer-22.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.22.self_attn.o_proj.row_alpha":{"file":"layers/layer-22.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.22.self_attn.o_proj.weight":{"file":"layers/layer-22.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.22.self_attn.q_norm.weight":{"file":"layers/layer-22.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.22.self_attn.q_proj.row_alpha":{"file":"layers/layer-22.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.22.self_attn.q_proj.weight":{"file":"layers/layer-22.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.22.self_attn.v_proj.row_alpha":{"file":"layers/layer-22.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.22.self_attn.v_proj.weight":{"file":"layers/layer-22.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.23.input_layernorm.weight":{"file":"layers/layer-23.mwg","offset":0,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.23.mlp.gate.weight":{"file":"layers/layer-23.mwg","offset":4096,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.23.mlp.switch_mlp.down_proj.row_alpha":{"file":"layers/layer-23.mwg","offset":1052672,"nbytes":1048576,"dtype":"BF16","shape":[256,2048]},"model.layers.23.mlp.switch_mlp.down_proj.weight":{"file":"layers/layer-23.mwg","offset":2101248,"nbytes":67108864,"dtype":"U32","shape":[256,2048,32]},"model.layers.23.mlp.switch_mlp.gate_proj.row_alpha":{"file":"layers/layer-23.mwg","offset":69210112,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.23.mlp.switch_mlp.gate_proj.weight":{"file":"layers/layer-23.mwg","offset":69472256,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.23.mlp.switch_mlp.up_proj.row_alpha":{"file":"layers/layer-23.mwg","offset":136581120,"nbytes":262144,"dtype":"BF16","shape":[256,512]},"model.layers.23.mlp.switch_mlp.up_proj.weight":{"file":"layers/layer-23.mwg","offset":136843264,"nbytes":67108864,"dtype":"U32","shape":[256,512,128]},"model.layers.23.post_attention_layernorm.weight":{"file":"layers/layer-23.mwg","offset":203952128,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.23.self_attn.k_norm.weight":{"file":"layers/layer-23.mwg","offset":203956224,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.23.self_attn.k_proj.row_alpha":{"file":"layers/layer-23.mwg","offset":203956480,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.23.self_attn.k_proj.weight":{"file":"layers/layer-23.mwg","offset":203957504,"nbytes":262144,"dtype":"U32","shape":[512,128]},"model.layers.23.self_attn.o_proj.row_alpha":{"file":"layers/layer-23.mwg","offset":204219648,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.23.self_attn.o_proj.weight":{"file":"layers/layer-23.mwg","offset":204223744,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.23.self_attn.q_norm.weight":{"file":"layers/layer-23.mwg","offset":205272320,"nbytes":256,"dtype":"BF16","shape":[128]},"model.layers.23.self_attn.q_proj.row_alpha":{"file":"layers/layer-23.mwg","offset":205272576,"nbytes":4096,"dtype":"BF16","shape":[2048]},"model.layers.23.self_attn.q_proj.weight":{"file":"layers/layer-23.mwg","offset":205276672,"nbytes":1048576,"dtype":"U32","shape":[2048,128]},"model.layers.23.self_attn.v_proj.row_alpha":{"file":"layers/layer-23.mwg","offset":206325248,"nbytes":1024,"dtype":"BF16","shape":[512]},"model.layers.23.self_attn.v_proj.weight":{"file":"layers/layer-23.mwg","offset":206326272,"nbytes":262144,"dtype":"U32","shape":[512,128]},"lm_head.biases":{"file":"lm-head.mwg","offset":0,"nbytes":9723904,"dtype":"BF16","shape":[151936,32]},"lm_head.scales":{"file":"lm-head.mwg","offset":9723904,"nbytes":9723904,"dtype":"BF16","shape":[151936,32]},"lm_head.weight":{"file":"lm-head.mwg","offset":19447808,"nbytes":155582464,"dtype":"U32","shape":[151936,256]}},"skipped":[],"total_tensor_bytes":5314273560}
|