Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+license: cc-by-nc-4.0
+tags:
+- not-for-all-audiences
+- nsfw
+language:
+- en
+---
+## Miqu PlayMaid 2x70B v0.1
+
+<center>
+Image to be replaced :P
+<div style="width: 100%;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/tPFdudSae6SCDNvhe1lC9.png" style="display: block; margin: auto;">
+</div>
+</center>
+
+This model uses the Alpaca **prompting format**. Unlike the base model this one is tuned on **16384 sequence length**. This was due to memory constraints.
+
+This is the second part of my endeavor by following their approach by making a MoE, made of Miqu PlayMaid 70B and Miqu 70B DPO.
+
+Miqu PlayMaid 70B a roleplay focused finetune using MiquMaid v2 70B DPO by [Undi95](https://huggingface.co/Undi95) and [IkariDev](https://huggingface.co/IkariDev) as base.
+
+My goal was to further push MiquMaid into creative writing and roleplay, hopefully adding some spice to it. 
+
+
+## Credits:
+- Netrve
+- Special thanks to everyone on TheBloke's Discord who helped me!
+
+Credits for MiquMaid:
+- Undi
+- IkariDev
+
+## Description
+
+This repo contains the BF16 files of Miqu-PlayMaid-2x70B-v0.1
+
+## Training data used:
+- [AndrijDavid Roleplay](https://huggingface.co/datasets/Undi95/andrijdavid_roleplay-conversation-sharegpt)
+- [LimaRP Augmented](https://huggingface.co/datasets/grimulkan/LimaRP-augmented)
+- [Airoboros 3.2](https://huggingface.co/datasets/jondurbin/airoboros-3.2)
+- [Bluemoon Fandom RP](https://huggingface.co/datasets/Squish42/bluemoon-fandom-1-1-rp-cleaned)
+
+### Format:
+
+I can only guarantee that it works with a maximum context length of 16384. Might work with 32768, but no promises. 
+
+```
+### Instruction:
+{system prompt}
+### Input:
+{input}
+### Response:
+{reply}
+```
+
+## Support
+
+- Netrve: If you like what I did, feel free to support future work [here](https://ko-fi.com/netrve)
+
+Don't forget to send some love to the original masterminds behind MiquMaid:
+
+- Undi: If you want to support us, you can [here](https://ko-fi.com/undiai)
+- IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/workspace/Undi95_Miqu-70B-Alpaca-DPO",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 32764,
+  "model_type": "mixtral",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,7 @@
+base_model: /workspace/Undi95_Miqu-70B-Alpaca-DPO
+gate_mode: random
+experts:
+  - source_model: /workspace/Undi95_Miqu-70B-Alpaca-DPO
+    positive_prompts: []
+  - source_model: /workspace/Miqu-PlayMaid-70B-v0.1
+    positive_prompts: []

model-00001-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83236acdd6791f37d528d2772065d0aff63f1587310f2d69653f00d7e1aa9231
+size 9940619816

model-00002-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef6df6ce566093d4d19347c886cd156243fe540bd9d044af35a435b99a4fa26
+size 9999340504

model-00003-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13672171437d0dcb63a4b2e7a90e38c560101220b8c23c358ed596a5688098b
+size 9965785848

model-00004-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2108117dfe8cf88ac08ff9b2b58f51eb2d5130038708a767da81f34711000dce
+size 9831551528

model-00005-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c31d496c7204972c918b6c5b9a1af1456b3103c14d720ea5aa19dc584a2be287
+size 9831551536

model-00006-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669eb48daa0d5f36958577f8d13fe8b57f39960845fdc4775a754148267f4fde
+size 9831551536

model-00007-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f18fe93a89e52e6fcb0ad3738c1a4fe165e08f06026bff021db0136eb8a0d7
+size 9831551536

model-00008-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae232f100923f481da862b7650802df5d25b8b099f3fdb6583884e07bf500e30
+size 9999340544

model-00009-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac998278e49461a2126e3e5e0d5629a99f74992168b548624522fb632236fada
+size 9965785888

model-00010-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c167186ea62414b226a6a3a5de2afeeb331e145d2dcd687cbd1084a64a60b3db
+size 9831551536

model-00011-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7009933d795459f86a8c1807fdef4e538a663e9a7339868a7559b7eae09b1ff4
+size 9831551536

model-00012-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92389cb16657808c2b020bc8eabfb60e87652908f3913f30432147847955c046
+size 9831551536

model-00013-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d256d35662550089ed5ab5e04cd1030298273086503edeed9e95712778cb18ad
+size 9831551536

model-00014-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50457a077cd9c94f3618bdb70919c701fec410c7f59636a2ffde002163ecd550
+size 9999340544

model-00015-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfdbb59492b2dc7f2b5aac6a8d80f372ae3f18549e4dd27da828a8771e8d223
+size 9965785888

model-00016-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4c7048dd5afaae4e1c9959f9337b3096fab8165fda9e69923c2a66833d53b6
+size 9831551536

model-00017-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391bfa816ccd347441d5da87fb8787f216b2348e0c156af5d6414b38426705ec
+size 9831551536

model-00018-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75a6449a43e0b26ffebe698fdddc3a9a405c56fbb2181149ac1f269573d3acc
+size 9831551536

model-00019-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f68d13821c477155ebc9b3b27cf0be1712a45a638b221ba2479d449a0aebf5
+size 9831551536

model-00020-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4878d9cfee1f2db79578360f6191a7dbd8311ea8671e745f87ef212969671d0
+size 9999340544

model-00021-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c75c3b566594779e13e268ab080b03c01c1e7929f779522d0edddb0d65256fc
+size 9965785888

model-00022-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a974774758298738333a60fc7575118f0780154118f7ff636f40cbd85c77553d
+size 9831551536

model-00023-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10fecc7161b2e17c764534039267752b49271618b76a9e0ee64815bc44217e4
+size 9831551536

model-00024-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ad51ffffcaa8a5e2662ebcff78ba9d0ca55361ebc41a333b5bb205f8801726f
+size 9831551536

model-00025-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2de4f219c2f717ead8da948aeff65f840c86ca98e802c0f1de47629e8c00988
+size 9831551536

model-00026-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5e6e1d640e2395dae462e8ac5a535824f782e408b29d639f71765edceb9b74
+size 3592989160

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "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.0.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", "model.layers.0.post_attention_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.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00026.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00026.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", "model.layers.1.post_attention_layernorm.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.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00026.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00026.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00026.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", "model.layers.2.post_attention_layernorm.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.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00026.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00026.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00026.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00026.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00026.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00026.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00026.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00026.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00026.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00026.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00026.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00026.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00026.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00026.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00026.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00026.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00026.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00026.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00026.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00026.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00026.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00026.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00026.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00026.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00026.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00026.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00026.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00026.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00026.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00026.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00026.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00026.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00026.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00026.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00026.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00026.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00026.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00026.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00026.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00026.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00026.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00026.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00026.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00026.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00026.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00026.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00026.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00026.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00026.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00026.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00026.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00026.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00026.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00026.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00026.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00026.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00026.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00026.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00026.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00026.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00026.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00026.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00026.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00026.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00026.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00026.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00026.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00026.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00026.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00026.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00026.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00026.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00026.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00026.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00026.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00026.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00026.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00026.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00026.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00026.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00026.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00026.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00026.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00026.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00026.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00026.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00026.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00026.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00026.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00026.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00026.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00026.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00026.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00026.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00026.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00026.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00026.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00026.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00026.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00026.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00026.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00026.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00026.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00026.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00026.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00026.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00026.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00026.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00026.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00026.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00026.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00026.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00026.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00026.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00026.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00026.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00026.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00026.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00026.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00026.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00026.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00026.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00026.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00026.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00026.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00026.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00026.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00026.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00026.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00026.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00026.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00026.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00026.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00026.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00026.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00026.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00026.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00026.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00026.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00026.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00026.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00026.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00026.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00026.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00026.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00026.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00026.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00026.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00026.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00026.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00026.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00026.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00026.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00026.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00026.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00026.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00026.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00026.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00026.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00026.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00026.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00026.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00026.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00026.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00026.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00026.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00026.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00026.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00026.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00026.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00026.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00026.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00026.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00026.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00026.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00026.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00026.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00026.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00026.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00026.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00026.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00026.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00026.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00026.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00026.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00013-of-00026.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00013-of-00026.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00013-of-00026.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00026.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00013-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00026.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00014-of-00026.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00026.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00014-of-00026.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00026.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.42.input_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00014-of-00026.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00014-of-00026.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00014-of-00026.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00014-of-00026.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.43.input_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00014-of-00026.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00014-of-00026.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00014-of-00026.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00014-of-00026.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00026.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00026.safetensors", "model.layers.44.input_layernorm.weight": "model-00014-of-00026.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00014-of-00026.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00014-of-00026.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00014-of-00026.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.45.input_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00015-of-00026.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00015-of-00026.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00015-of-00026.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.46.input_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00015-of-00026.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00015-of-00026.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00015-of-00026.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00026.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00026.safetensors", "model.layers.47.input_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00015-of-00026.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00015-of-00026.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00015-of-00026.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00026.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00026.safetensors", "model.layers.48.input_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00026.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00026.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00026.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00026.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00026.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00026.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00016-of-00026.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00016-of-00026.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00016-of-00026.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00016-of-00026.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00026.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00026.safetensors", "model.layers.50.input_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00016-of-00026.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00016-of-00026.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00016-of-00026.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00016-of-00026.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00016-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00026.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00026.safetensors", "model.layers.51.input_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00017-of-00026.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00017-of-00026.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00017-of-00026.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00017-of-00026.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00026.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00026.safetensors", "model.layers.52.input_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00017-of-00026.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00017-of-00026.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00017-of-00026.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00017-of-00026.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00026.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00026.safetensors", "model.layers.53.input_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00017-of-00026.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00017-of-00026.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00017-of-00026.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00017-of-00026.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00017-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00026.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00026.safetensors", "model.layers.54.input_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00026.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00026.safetensors", "model.layers.55.input_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00026.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00026.safetensors", "model.layers.56.input_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00026.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00026.safetensors", "model.layers.57.input_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00019-of-00026.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00019-of-00026.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00019-of-00026.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00019-of-00026.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00026.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00026.safetensors", "model.layers.58.input_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00019-of-00026.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00019-of-00026.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00019-of-00026.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00019-of-00026.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00026.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00026.safetensors", "model.layers.59.input_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00019-of-00026.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00019-of-00026.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00019-of-00026.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00019-of-00026.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00019-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00026.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00026.safetensors", "model.layers.60.input_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00020-of-00026.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00020-of-00026.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00020-of-00026.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00020-of-00026.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00026.safetensors", "model.layers.60.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00026.safetensors", "model.layers.61.input_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00020-of-00026.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00020-of-00026.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00020-of-00026.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00020-of-00026.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00026.safetensors", "model.layers.61.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00026.safetensors", "model.layers.62.input_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00020-of-00026.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00020-of-00026.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00020-of-00026.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00020-of-00026.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00026.safetensors", "model.layers.62.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00026.safetensors", "model.layers.63.input_layernorm.weight": "model-00020-of-00026.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00020-of-00026.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00020-of-00026.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00020-of-00026.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00026.safetensors", "model.layers.63.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00026.safetensors", "model.layers.64.input_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00021-of-00026.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00021-of-00026.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00021-of-00026.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00026.safetensors", "model.layers.64.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00026.safetensors", "model.layers.65.input_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00021-of-00026.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00021-of-00026.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00021-of-00026.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00026.safetensors", "model.layers.65.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00026.safetensors", "model.layers.66.input_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00021-of-00026.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00021-of-00026.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00021-of-00026.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.1.w3.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.66.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00026.safetensors", "model.layers.66.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00026.safetensors", "model.layers.67.input_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00022-of-00026.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00022-of-00026.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00022-of-00026.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00022-of-00026.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.1.w3.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.67.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00026.safetensors", "model.layers.67.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00026.safetensors", "model.layers.68.input_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00022-of-00026.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00022-of-00026.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00022-of-00026.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00022-of-00026.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.1.w3.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.68.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00026.safetensors", "model.layers.68.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00026.safetensors", "model.layers.69.input_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00022-of-00026.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00022-of-00026.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00022-of-00026.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00022-of-00026.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00022-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00026.safetensors", "model.layers.69.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00026.safetensors", "model.layers.70.input_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00023-of-00026.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00023-of-00026.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00023-of-00026.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.1.w3.weight": "model-00023-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.70.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00026.safetensors", "model.layers.70.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00026.safetensors", "model.layers.71.input_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00023-of-00026.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00023-of-00026.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00023-of-00026.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.1.w3.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.71.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00026.safetensors", "model.layers.71.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00026.safetensors", "model.layers.72.input_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00023-of-00026.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00023-of-00026.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00023-of-00026.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.1.w3.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-00024-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00026.safetensors", "model.layers.72.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00026.safetensors", "model.layers.73.input_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00024-of-00026.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00024-of-00026.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00024-of-00026.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00026.safetensors", "model.layers.73.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00026.safetensors", "model.layers.74.input_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00024-of-00026.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00024-of-00026.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00024-of-00026.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00026.safetensors", "model.layers.74.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00026.safetensors", "model.layers.75.input_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00024-of-00026.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00024-of-00026.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00024-of-00026.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00024-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00026.safetensors", "model.layers.75.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00026.safetensors", "model.layers.76.input_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00025-of-00026.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00026.safetensors", "model.layers.76.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00026.safetensors", "model.layers.77.input_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00025-of-00026.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00026.safetensors", "model.layers.77.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00026.safetensors", "model.layers.78.input_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00025-of-00026.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00025-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00026.safetensors", "model.layers.78.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00026.safetensors", "model.layers.79.input_layernorm.weight": "model-00026-of-00026.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00026-of-00026.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00026-of-00026.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00026-of-00026.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00026-of-00026.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00026-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00026.safetensors", "model.layers.79.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00026.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.60.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.61.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.62.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.63.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.64.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.65.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.66.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.67.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.68.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.69.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.70.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.71.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.72.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.73.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.74.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.75.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.76.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.77.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.78.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors", "model.layers.79.block_sparse_moe.gate.weight": "model-00026-of-00026.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}