LoneStriker commited on
Commit
9ad0dc3
1 Parent(s): f87eb64

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - not-for-all-audiences
5
+ - nsfw
6
+ ---
7
+
8
+ ## MiquMaid v2 2x70 DPO
9
+
10
+ Check out our blogpost about this model series [Here!](https://ikaridevgit.github.io/index.html?blog=blogid-6&bo=true#Miqu-base) - Join our Discord server [Here!](https://discord.gg/Bb8pRUXy3Z)
11
+
12
+ <center>[<a href="https://huggingface.co/NeverSleep/MiquMaid-v2-70B">V2-70B</a> - <a href="https://huggingface.co/NeverSleep/MiquMaid-v2-70B-DPO">V2-70B-DPO</a> - <a href="https://huggingface.co/NeverSleep/MiquMaid-v2-2x70B">V2-2x70B</a> - <a href="https://huggingface.co/NeverSleep/MiquMaid-v2-2x70B-DPO">V2-2x70B-DPO</a>]
13
+ </br>
14
+ <div style="width: 100%;">
15
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/Wbzwoko-IZbOJfvPaImre.png" style="display: block; margin: auto;">
16
+ </div></center>
17
+
18
+ This model uses the Alpaca **prompting format**
19
+
20
+ Then, we have done a MoE, made of MiquMaid-v2-70B-DPO and Miqu-70B-DPO base, making the model using the finetune AND the base model for each token, working together.
21
+
22
+ The two model have been trained on DPO for uncensoring, more info on Miqu-70B-DPO [here](https://huggingface.co/Undi95/Miqu-70B-Alpaca-DPO-GGUF)
23
+
24
+ We have seen a significant improvement, so we decided to share that, even if the model is very big.
25
+
26
+ ## Credits:
27
+ - Undi
28
+ - IkariDev
29
+
30
+ ## Description
31
+
32
+ This repo contains FP16 files of MiquMaid-v2-2x70B-DPO.
33
+
34
+ Switch: [FP16](https://huggingface.co/NeverSleep/MiquMaid-v2-2x70B-DPO) - [GGUF](https://huggingface.co/NeverSleep/MiquMaid-v2-2x70B-DPO-GGUF)
35
+
36
+ ## Training data used:
37
+ - [Aesir datasets](https://huggingface.co/MinervaAI)
38
+ - [NoRobots](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt)
39
+ - [limarp](https://huggingface.co/datasets/lemonilia/LimaRP)
40
+ - [toxic-dpo-v0.1-sharegpt](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt)
41
+ - [ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal)
42
+
43
+ ## DPO training data used:
44
+ - [ToxicDPOqa](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicDPOqa)
45
+ - [toxic-dpo-v0.1-NoWarning](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-NoWarning)
46
+
47
+ ### Custom format:
48
+ ```
49
+ ### Instruction:
50
+ {system prompt}
51
+
52
+ ### Input:
53
+ {input}
54
+
55
+ ### Response:
56
+ {reply}
57
+ ```
58
+
59
+ ## Others
60
+
61
+ Undi: If you want to support us, you can [here](https://ko-fi.com/undiai).
62
+
63
+ IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./Miqu-70B-DPO/merged",
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": 32764,
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": "bfloat16",
31
+ "transformers_version": "4.37.2",
32
+ "use_cache": false,
33
+ "vocab_size": 32000
34
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/NeverSleep/MiquMaid-v2-2x70B-DPO
2
+ branch: main
3
+ download date: 2024-02-13 20:40:43
4
+ sha256sum:
5
+ 5ac7a9769961a7060fd48d88bc9827671105792a8d630af031529bd583118b2e model-00001-of-00026.safetensors
6
+ 84c62eb0799e80abb902c713d2f17fd6a4bd9ac09c324bb2c05e6280f9b0d672 model-00002-of-00026.safetensors
7
+ e367c95aeff0a212bb5f1438efe7a7c56422738fcc8c2f261c916a1a253922ff model-00003-of-00026.safetensors
8
+ cc7c708ce9b83c9ee00cb0aaeb5d83bdff235504da5f5ef5efa9d37f11e59c3a model-00004-of-00026.safetensors
9
+ 6da3c7609f4be51c6eadcd9efa6546d3d179e9258ad7b493081ff22efae55bbe model-00005-of-00026.safetensors
10
+ 8c2c385a4d482f39273f9be18b0a0ffcb448232ebb4b11ff0a79c805da551914 model-00006-of-00026.safetensors
11
+ 85f63132cbb4292078911a4c27cc93fca8feb67078efc2c89bc3ff08726b3415 model-00007-of-00026.safetensors
12
+ 83857cce9a036c621d5c8925f9285357707ccf624f066d9333f8c7992b8ca0d9 model-00008-of-00026.safetensors
13
+ d867f2ba9352106f04bed6ff8abee1caad41030c469373fbbfaf8bc8da88e615 model-00009-of-00026.safetensors
14
+ d85ec76c7c215f56024ff5edb1e3b1c032b0e4fd389b9298d296a2a28c3482b3 model-00010-of-00026.safetensors
15
+ d7535ba145d699ac14804e92fb208e6aa4cfa2b25e2c6aa40b2d9f1ee7b90684 model-00011-of-00026.safetensors
16
+ c7f7d5c2eed5ec4885ef218e5dfaa2885621f1bc6d6a9cf5be56323f194502e6 model-00012-of-00026.safetensors
17
+ 57bca296d7a27f827adb70ced7a01778da180dc1909d6503168d9382a2a42997 model-00013-of-00026.safetensors
18
+ 28b27a262800f937184f646fbc953fa13d40ed221ce9794a6f3a5767dc1e568d model-00014-of-00026.safetensors
19
+ 7549bbd14b94430270ccf4544334a3fffad0d73ca0e583e392bbd1676300244d model-00015-of-00026.safetensors
20
+ 7486400e650b5fafd0a8e722198485217275cd9dfaaf24273726a38105123820 model-00016-of-00026.safetensors
21
+ 189174afa89d1458a4dad9d057141cc23b38bce2d687dba64850256675db183b model-00017-of-00026.safetensors
22
+ 0dadd8dbad4da1f4d8fd63fbf7085bfbd5b18ddc230eff390f01021632ab33f8 model-00018-of-00026.safetensors
23
+ 4b5a123e1f3ff7a6e8bb8848eae3a22dd00f37e6959e20ad2e6d726d57741018 model-00019-of-00026.safetensors
24
+ 91196d61c0057381587fbf673bf1ae4038593319e2a911bebe73635e2492cd01 model-00020-of-00026.safetensors
25
+ b0c1c4ddea76a394be55f2c1323948833bcc187c0cbb5ddba58fcf3b9687f320 model-00021-of-00026.safetensors
26
+ 2d77689a5ba1aee5b9437c0d8643f78b33d7a359f56adb413ab458597fb9ea4d model-00022-of-00026.safetensors
27
+ 2f05bd00e8b7f1e3398c5623fc1e07451cbbc28876f22cae32ba92d69e4b4fb3 model-00023-of-00026.safetensors
28
+ 58f758d2dc94ad6aa38bcfa7ce78f7ff3df1fff43e018a50def099d7c9348818 model-00024-of-00026.safetensors
29
+ 20b065a3bac97da6a9d0635c6f6b51875e4ba2b3876253aef1a454b4005248dd model-00025-of-00026.safetensors
30
+ 2a1e41a992462688dff2b5ba18e4307f6eb8944a3da1d67c5e2457018300d4d9 model-00026-of-00026.safetensors
31
+ 9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model
mergekit_moe_config.yml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ base_model: ./Miqu-70B-DPO/merged
2
+ gate_mode: random
3
+ experts:
4
+ - source_model: ./Miqu-70B-DPO/merged
5
+ positive_prompts: []
6
+ - source_model: ./MiquMaid-v2-70B-DPO/merged
7
+ positive_prompts: []
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"}}
output-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5df02cb9a23cf8da6a835e3dcb9867a4929602ca25aaf5a273939d0c0fab034
3
+ size 8547572092
output-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28b0dc509351633b6dd18d10d1ad931b046da27ad80f20842dd67f647c52592
3
+ size 8555832892
output-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da034c13a23352148374c8fe931195896e52a98dcd7d6132347e6c25d495dc23
3
+ size 8578731596
output-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8cb12c6113dc31ad853698dfbba67ba5c6540a7886895f9da9a0ce7c1cfcf7
3
+ size 8564090816
output-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623878d77a8dd0307fddecc6687e1b6737a417e5b563dc185c4ca2e64fe61747
3
+ size 3936111672
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "trust_remote_code": false,
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }