atcsecure commited on
Commit
45bbd44
·
verified ·
1 Parent(s): 17bceec

mhm-8x7B-FrankenMoE-v1.0 - exl2 6.0

Browse files
README.md CHANGED
@@ -1,3 +1,69 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - merge
7
+ - moe
8
  ---
9
+
10
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/dUkIQhg6CBAESsPkhtSkX.jpeg)
11
+
12
+ ## Recipe for a Beautiful Frankenstein
13
+
14
+ In the laboratory of the mind, where thoughts entwine,
15
+ MHM and MOE, a potion for a unique design.
16
+ With stitches of curiosity and bolts of creativity,
17
+ 8 times 7, the magic number, a poetic proclivity.
18
+
19
+ ### Ingredients:
20
+
21
+ - **MHM:** A dash of mystery, a sprinkle of hum,
22
+ Blend with a melody, let the heartstrings strum.
23
+ Murmurs in the shadows, whispers in the light,
24
+ Stir the concoction gently, make the emotions ignite.
25
+
26
+ - **MOE:** Essence of the moment, like dew on a rose,
27
+ Capture the now, before time swiftly goes.
28
+ Colors of experience, a palette so divine,
29
+ Mix with MHM, let the fusion entwine.
30
+
31
+ ### Directions:
32
+
33
+ 1. **Take 8 parts MHM,** elusive and profound,
34
+ Let it dance in your thoughts, on imagination's ground.
35
+ Blend it with the echoes, the silent undertones,
36
+ A symphony of ideas, where inspiration condones.
37
+
38
+ 2. **Add 7 parts MOE,** the fleeting embrace,
39
+ Seize the seconds, let them leave a trace.
40
+ Infuse it with memories, both bitter and sweet,
41
+ The tapestry of time, where moments and dreams meet.
42
+
43
+ 3. **Stir the potion with wonder,** a wand of delight,
44
+ Let the sparks fly, in the dark of the night.
45
+ Watch as the alchemy unfolds its grand design,
46
+ MHM and MOE, a beautiful Frankenstein.
47
+
48
+ ### Conclusion:
49
+
50
+ In the laboratory of life, where dreams come alive,
51
+ MHM and MOE, the recipe to thrive.
52
+ A creation so poetic, a fusion so divine,
53
+ 8 times 7, a symphony of time.
54
+
55
+ As the echoes resonate, and the moments blend,
56
+ A masterpiece unfolds, where beginnings and ends,
57
+ MHM and MOE, a concoction so rare,
58
+ A beautiful Frankenstein, beyond compare.
59
+
60
+ ---
61
+
62
+ MoE model build with:
63
+ 1. https://github.com/cg123/mergekit/tree/mixtral
64
+ 2. Mistral models, latest merges and fine tunes.
65
+ 3. Expert prompts heavily inspired by https://huggingface.co/Kquant03/Eukaryote-8x7B-bf16
66
+
67
+ For details check model files, there is config yaml I used to create that model.
68
+
69
+ Come back later for more details.
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mlabonne/Beagle14-7B",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.36.2",
28
+ "use_cache": false,
29
+ "vocab_size": 32000,
30
+ "quantization_config": {
31
+ "quant_method": "exl2",
32
+ "version": "0.0.17",
33
+ "bits": 6.0,
34
+ "head_bits": 6,
35
+ "calibration": {
36
+ "rows": 100,
37
+ "length": 2048,
38
+ "dataset": "(default)"
39
+ }
40
+ }
41
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/h2m/mhm-8x7B-FrankenMoE-v1.0
2
+ branch: main
3
+ download date: 2024-04-06 11:41:33
4
+ sha256sum:
5
+ 7d9cef00da0fe3f9a0d6133e40e161c4bd87cd745134f2b4a581e5d648b9a905 model-00001-of-00010.safetensors
6
+ e8c5e517cda583a43abd5fe33012f9c70c0a356560b8836379b57dbddc333ea1 model-00002-of-00010.safetensors
7
+ f2318ea1e1fe6fe95c20e3fa74f557a5986778ad936d2701334b3c2454d4edf6 model-00003-of-00010.safetensors
8
+ 8f04e6f6dd251a16f6caf1ea87c04778526af45c5c70f41c7d26a4d8989b6e84 model-00004-of-00010.safetensors
9
+ ddeb07a6ecd130ee527aaa3a52e85a4e278dd513b1f9f5e4949497ceaf763405 model-00005-of-00010.safetensors
10
+ afab070b4e1b7f080c7aa183b690490f205bab37c723c7d1d573b4b2d4601b2a model-00006-of-00010.safetensors
11
+ c1eadd619781381f3983d468e11088476a84b42051f58fae99e4066881b9882c model-00007-of-00010.safetensors
12
+ b0c23f3449e8c03c039f0cfdf7f9fd3e66b737a988a9ec4f6694931351b99bb4 model-00008-of-00010.safetensors
13
+ 7f3f0246252c01bbda4ffc27cc9b450e92818ec8033f0d4618a2094100c8b063 model-00009-of-00010.safetensors
14
+ f935e1ef6ae576a4707c7deeb4bd8b2e3eca2eb6141b7ede32fc5a59b3ba0117 model-00010-of-00010.safetensors
15
+ dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 tokenizer.model
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.norm.weight": "model-00001-of-00010.safetensors", "lm_head.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors"}}
output-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e5156974c284b51ac69cb56a959d39320b275c3907cd2dfb632ed8d8c58a3a
3
+ size 8589723064
output-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aaa9f23535fa94f7ba061e0317c54f2aec61b6ea9f190f5d9b262c96644e0f5
3
+ size 8589414128
output-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc58d704cbe73d6caef0a0b6f769f111e2b1ebca732cc69828065b56d8e63aa6
3
+ size 8574414816
output-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d46eb6aef112ea34fc6b2506120bc6ca3e19a76ad5382c4eed2be97a8e8d7f3
3
+ size 8572052488
output-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:393bfc8c4f63f4968f26a23ca6db01255282f976ad32092c79a03bcf63f00a86
3
+ size 867326312
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": true,
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "<s>",
41
+ "padding_side": "left",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "split_special_tokens": false,
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }