Upload folder using huggingface_hub
Browse files- config.json +34 -0
- mergekit_moe_config.yml +10 -0
- model-00001-of-00026.safetensors +3 -0
- model-00002-of-00026.safetensors +3 -0
- model-00003-of-00026.safetensors +3 -0
- model-00004-of-00026.safetensors +3 -0
- model-00005-of-00026.safetensors +3 -0
- model-00006-of-00026.safetensors +3 -0
- model-00007-of-00026.safetensors +3 -0
- model-00008-of-00026.safetensors +3 -0
- model-00009-of-00026.safetensors +3 -0
- model-00010-of-00026.safetensors +3 -0
- model-00011-of-00026.safetensors +3 -0
- model-00012-of-00026.safetensors +3 -0
- model-00013-of-00026.safetensors +3 -0
- model-00014-of-00026.safetensors +3 -0
- model-00015-of-00026.safetensors +3 -0
- model-00016-of-00026.safetensors +3 -0
- model-00017-of-00026.safetensors +3 -0
- model-00018-of-00026.safetensors +3 -0
- model-00019-of-00026.safetensors +3 -0
- model-00020-of-00026.safetensors +3 -0
- model-00021-of-00026.safetensors +3 -0
- model-00022-of-00026.safetensors +3 -0
- model-00023-of-00026.safetensors +3 -0
- model-00024-of-00026.safetensors +3 -0
- model-00025-of-00026.safetensors +3 -0
- model-00026-of-00026.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "lodrick-the-lafted/Grafted-Wind-Elementals-2x70B",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 8192,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"model_type": "mixtral",
|
16 |
+
"num_attention_heads": 64,
|
17 |
+
"num_experts_per_tok": 2,
|
18 |
+
"num_hidden_layers": 80,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"num_local_experts": 2,
|
21 |
+
"output_router_logits": false,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 1000000,
|
27 |
+
"router_aux_loss_coef": 0.001,
|
28 |
+
"sliding_window": null,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "float16",
|
31 |
+
"transformers_version": "4.38.0.dev0",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 32000
|
34 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: /workspace/Borean
|
2 |
+
gate_mode: hidden
|
3 |
+
dtype: float16
|
4 |
+
|
5 |
+
experts:
|
6 |
+
- source_model: /workspace/Borean
|
7 |
+
positive_prompts: ["stories", "writing", "personal assistant"]
|
8 |
+
|
9 |
+
- source_model: /workspace/Senku
|
10 |
+
positive_prompts: ["math", "assistant", "metric", "unit conversion"]
|
model-00001-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d4faae53433a7093a055800e9a01e738ebb7b02715a270362d8681a23316d57
|
3 |
+
size 9975393672
|
model-00002-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a41e61cab7580fc9fa2186c36284277af86270de2e60a4f920abeea73af42c8
|
3 |
+
size 9865005792
|
model-00003-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54f81f5ab5afe6e972c0fb1efdc8f9bf316a4e362cd54bc9ff0b720c956e0f37
|
3 |
+
size 9865005792
|
model-00004-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e94d86c50a0c3b83a507df10b3fb28e6e1c75177fb0fb7ead9bd8d53e2bde4d
|
3 |
+
size 9865005792
|
model-00005-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d73595b31b409335a05afb3691351d7bb5b3be3273b5232262baa4d651f00b53
|
3 |
+
size 9865005792
|
model-00006-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0498caac6629a6bd14c1f380a5b7d575204115f81da6afc0069b2a1aa18fe1a3
|
3 |
+
size 9865005792
|
model-00007-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9102c52e3d1c05e5bf7ef8a2ee19840c0beba1f7f3257c51efa6d9fd4577e853
|
3 |
+
size 9865005792
|
model-00008-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87fd745c927d5b66c9e8f130c1da32bcfed5782805e03b776b40f3dd80116e15
|
3 |
+
size 9865005784
|
model-00009-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b7749c82052f2add5b15f71427b67f1f16fa1140b01a908a16ce8755d16eb64
|
3 |
+
size 9865005776
|
model-00010-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cdce5a41b9107120a2bb98841572f1a5b7e596c819423f8bdeba90f72417a11
|
3 |
+
size 9865005792
|
model-00011-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08222914677eda86c0c17a72d88713b2a617eae2ebabfb8435f7ee9aeeb31107
|
3 |
+
size 9865005792
|
model-00012-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53aca8ad9118219ef2c29530331a54644a956f69a9b7685b6f96d622570cfdb1
|
3 |
+
size 9865005792
|
model-00013-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56854448552c7100511dc1dddbc87bc2eadd5ff9678fb61eea6241a7eb7cd450
|
3 |
+
size 9865005792
|
model-00014-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4802cc1cc980b5dec678f09111c7912aabae2e0a0d587cabc46688908be7d097
|
3 |
+
size 9865005792
|
model-00015-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5f939f806f14169390fa5c2fe96e3e8085024128d022e0df4b6330f02a6d1f1
|
3 |
+
size 9865005792
|
model-00016-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27ecd24a4ef1e4338ef239663a9f92186e3fed42128992a368ffe86594e1158b
|
3 |
+
size 9865005776
|
model-00017-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ee5658cf79e3f36e8816d661d9be34936d0c5d955314feefcc9393883602c37
|
3 |
+
size 9865005784
|
model-00018-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5596707840c1066b2c19c7f1a7005f8a0725465303b005e26ead5cd9531681e
|
3 |
+
size 9865005792
|
model-00019-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ca08d19eb5f5742041e375c181b836ecbeffeb912969f21d90e353450a2b9ca
|
3 |
+
size 9865005792
|
model-00020-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df3ae30f403ef3aaca074de26ceef05c5522f02c5e8ce383d214300d05a1308c
|
3 |
+
size 9865005792
|
model-00021-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9cf922e9c0a81b478d3dddefb8f00d587213af0c5d3915b83b93d6824494ea3
|
3 |
+
size 9865005792
|
model-00022-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8c234e499f5fffb70ce0f9c1738077a7aaae4c06f67bdd442d2d916786db5d4
|
3 |
+
size 9865005792
|
model-00023-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7d7c7ce99691091e86da4eb33631bc7072e07c48e1714e53f3a685534815afc
|
3 |
+
size 9933435152
|
model-00024-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62547c3ecba7de9654620a10c71b353bce55a2cb0e1bb3762c067ed6f9947fd5
|
3 |
+
size 9932120544
|
model-00025-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca3d354dea4bf6ac825ac992ca5df8ee39df5f85f5e8975f9109ec55df037569
|
3 |
+
size 9932136880
|
model-00026-of-00026.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5525fd509c95f42986aa5c8b061d3ac80c75d82399f2b370ba9340a666f965cb
|
3 |
+
size 3760730256
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00026.safetensors", "model.norm.weight": "model-00001-of-00026.safetensors", "lm_head.weight": "model-00001-of-00026.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.56.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.57.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.58.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.59.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.60.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.61.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.62.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.63.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.64.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.65.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.66.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.67.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.68.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.69.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.70.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.71.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.72.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.73.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.74.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.75.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.76.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.77.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.78.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.79.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00025-of-00026.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00025-of-00026.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.60.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.61.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.62.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.63.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.64.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.65.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.66.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.67.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.68.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.69.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.70.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.71.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.72.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.73.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.74.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.75.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.76.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.77.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.78.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.79.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<s>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"spaces_between_special_tokens": false,
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": false
|
41 |
+
}
|