diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000000000000000000000000000000000000..a6344aac8c09253b3b630fb776ae94478aa0275b
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..fe7604e153c2c0f687e3c23f939e195482694b8c
--- /dev/null
+++ b/README.md
@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+datasets:
+- 0-hero/Matter-0.2-alpha-Slim-A
+language:
+- en
+---
+
+## Matter 8x22B - 0.2 (Mixtral 8x22B 0.2 Finetune)
+
+Matter 8x22B 0.2 is finetune on the **Matter 0.2 dataset**, which is curated from over 35 datsets analyzing >6B tokens
+
+### Recommended Usage for best results
+System Prompt - `You are a helpful assistant`
+
+### Training
+
+Prompt format: This model uses ChatML prompt format.
+```
+<|im_start|>system
+You are a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+### Function Calling
+
+Model also supports function calling. Additional tokens for function calling
+
+Model function call tokens
+- `` - Function call start token
+- `` - Function call end token
+
+Function call response tokens
+- `` - Function response start token
+- `` - Function response end token
+
+Example
+```
+<|im_start|>system
+ You are a helpful assistant with access to the following functions. Use them if required -
+ { "name": "get_news_headlines",
+ "description": "Get the latest news headlines",
+ "parameters":
+ { "type": "object",
+ "properties":
+ { "country":
+ { "type": "string",
+ "description": "The country for which to fetch news"
+ }
+ },
+ "required": [ "country" ]
+ }
+ }
+<|im_end|>
+<|im_start|>user
+ Can you tell me the latest news headlines for the United States?<|im_end|>
+<|im_start|>assistant
+ {"name": "get_news_headlines", "arguments": '{"country": "United States"}'}<|im_end|>
+<|im_start|>user
+ {
+ "headlines":
+ [
+ "Biden announces new vaccine mandates",
+ "Hurricane Ida devastates Louisiana",
+ "Apple unveils new iPhone",
+ "NASA's Perseverance rover collects first Mars rock sample"
+ ]
+ }
+<|im_end|>
+<|im_start|>assistant
+ Here are the latest news headlines for the United States:
+ 1. Biden announces new vaccine mandates
+ 2. Hurricane Ida devastates Louisiana
+ 3. Apple unveils new iPhone
+ 4. NASA's Perseverance rover collects first Mars rock sample
+<|im_end|>
+```
\ No newline at end of file
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..dbc1a792eceeb5b94f393163b9127ef3c3f6bc26
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,8 @@
+{
+ "<|begin_func_response|>": 32003,
+ "<|begin_func|>": 32001,
+ "<|end_func_response|>": 32004,
+ "<|end_func|>": 32002,
+ "<|im_end|>": 32000,
+ "<|im_start|>": 32005
+}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ddf4df897fff465b72920a99039547d0394f8de9
--- /dev/null
+++ b/config.json
@@ -0,0 +1,31 @@
+{
+ "_name_or_path": "mistral-community/Mixtral-8x22B-v0.1",
+ "architectures": [
+ "MixtralForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 32000,
+ "hidden_act": "silu",
+ "hidden_size": 6144,
+ "initializer_range": 0.02,
+ "intermediate_size": 16384,
+ "max_position_embeddings": 65536,
+ "model_type": "mixtral",
+ "num_attention_heads": 48,
+ "num_experts_per_tok": 2,
+ "num_hidden_layers": 56,
+ "num_key_value_heads": 8,
+ "num_local_experts": 8,
+ "output_router_logits": false,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000,
+ "router_aux_loss_coef": 0.001,
+ "router_jitter_noise": 0.0,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.40.0.dev0",
+ "use_cache": false,
+ "vocab_size": 32006
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..16dd90acbcc482b30661bf1c48c719fec177f4a8
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "do_sample": true,
+ "eos_token_id": 2,
+ "transformers_version": "4.40.0.dev0"
+}
diff --git a/pytorch_model-00001-of-00059.bin b/pytorch_model-00001-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..006fe19be0a1b4d07642a752dfb8677904a76dff
--- /dev/null
+++ b/pytorch_model-00001-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46b584e4bed539b994ff81aa72eaafb355bba15768a90f63f9c6d5202db31bf
+size 4998743615
diff --git a/pytorch_model-00002-of-00059.bin b/pytorch_model-00002-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c3a9d7953638d60e14127a79ec774e9a387ba6c0
--- /dev/null
+++ b/pytorch_model-00002-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dbce1b96c749f09d9f6d8cb6ad8511cb6e2c4ce1d9a880e6f65d20fa73b3b6e
+size 4806805715
diff --git a/pytorch_model-00003-of-00059.bin b/pytorch_model-00003-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1dc3da4f7af00be25943bee2792a3b586ef8c54d
--- /dev/null
+++ b/pytorch_model-00003-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2bf47c99b9ca63f70c6e47779b46868d45d79ea86312729d6824ac1e85becd3
+size 4806805727
diff --git a/pytorch_model-00004-of-00059.bin b/pytorch_model-00004-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..783704986c805ffc97f882466ec8c9130091036d
--- /dev/null
+++ b/pytorch_model-00004-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5cb92beac72b5c1e8654bec552a6edc7cb1f6aae06a3650b37e6da4329c21d
+size 4806805715
diff --git a/pytorch_model-00005-of-00059.bin b/pytorch_model-00005-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..13674a80d81d68f86d3f4d7d883084611218ebe8
--- /dev/null
+++ b/pytorch_model-00005-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa02dcf479f5cfe58b1473ba8a943f1e632dc25fa2ef7500d3abd3906d01e0c9
+size 4806805715
diff --git a/pytorch_model-00006-of-00059.bin b/pytorch_model-00006-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d7588ae1f3f5bb6b0f14e444e48779f0ee24ce64
--- /dev/null
+++ b/pytorch_model-00006-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cacc00c49398efbc1d91e231d21a14fe426f99ac315f13b66c1c5088129a18d9
+size 4806805703
diff --git a/pytorch_model-00007-of-00059.bin b/pytorch_model-00007-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4ae6bd1f5e8410b5487f404da215e57168d39d17
--- /dev/null
+++ b/pytorch_model-00007-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db57c56fed1941914fa5f44b5bbed5961d9e360b927401f5b9627383b79eeae
+size 4806805691
diff --git a/pytorch_model-00008-of-00059.bin b/pytorch_model-00008-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..53ef3a7cc87eab81162bc107a34b1307bb0ec466
--- /dev/null
+++ b/pytorch_model-00008-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301ec6b1a437c29a82691bd26420314d6c8a785a57065746112d2d7f6f976184
+size 4806805679
diff --git a/pytorch_model-00009-of-00059.bin b/pytorch_model-00009-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f42dc520ea63df6f5ba5c660aaf6f4d2749a8edb
--- /dev/null
+++ b/pytorch_model-00009-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4e9eb3523b5072ea1af6becad7db33a4ae7a5c3b81209189fd953e6e8aec64
+size 4806805667
diff --git a/pytorch_model-00010-of-00059.bin b/pytorch_model-00010-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4f249f64ee5b66623db7abe63e7cc648d04f64fd
--- /dev/null
+++ b/pytorch_model-00010-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94d2e0b703a2c8055176e2810215f1a21406b184bebd2b100c70ba89205031d
+size 4806805655
diff --git a/pytorch_model-00011-of-00059.bin b/pytorch_model-00011-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7c8dc55c25bbd03cb2d6db105f5d0fa922b03a73
--- /dev/null
+++ b/pytorch_model-00011-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a18cb26163ceef3c67ed7a3c75df0a3d22c884628bfffc1bdd252cb97c7d2e
+size 4806805655
diff --git a/pytorch_model-00012-of-00059.bin b/pytorch_model-00012-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c39dec0cf696555f39cffd1d42df4b72ca7e67ef
--- /dev/null
+++ b/pytorch_model-00012-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f02a221bfb395020f37588517dbbacd89974edb1c5df62a1985fe522a606251
+size 4806805719
diff --git a/pytorch_model-00013-of-00059.bin b/pytorch_model-00013-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..273716c10a0207d83ecd71606195a9dc0adecc8f
--- /dev/null
+++ b/pytorch_model-00013-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1a6993c68d0fd031b19264222a23350ea04ae50d4dfd4286c696ad3953177d
+size 4806805719
diff --git a/pytorch_model-00014-of-00059.bin b/pytorch_model-00014-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..16e529f1b958ecf572cdd8fd0a6c2e51973bde7d
--- /dev/null
+++ b/pytorch_model-00014-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211cde478920eff63ac1f282d352afedf75644018c5f3cbf552d4a8ab283ff60
+size 4806805719
diff --git a/pytorch_model-00015-of-00059.bin b/pytorch_model-00015-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d2a685b7c69a4517280fa2dd95122686a86533ff
--- /dev/null
+++ b/pytorch_model-00015-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9e61391b511fefae9a1eca28e9616bdc1a3a0c3470fa9e007c90bdae80aa2b
+size 4806805719
diff --git a/pytorch_model-00016-of-00059.bin b/pytorch_model-00016-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a39dca4eb0971022a2be0fdf76546707d1717c86
--- /dev/null
+++ b/pytorch_model-00016-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200c89ba4229910671305f68d6ab38403db8e725d0cc63adb7e9772733025939
+size 4806805719
diff --git a/pytorch_model-00017-of-00059.bin b/pytorch_model-00017-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2b2c0369604d7942d0fe96786ac61d710b738a77
--- /dev/null
+++ b/pytorch_model-00017-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be57aec6f6ba0d9bb77a52d804fbf20469eab44a9784f07626c78e213010d391
+size 4806805719
diff --git a/pytorch_model-00018-of-00059.bin b/pytorch_model-00018-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9beb467a1d5e706d214d9c76b5d266a66fc6f353
--- /dev/null
+++ b/pytorch_model-00018-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad971808cc6e0cfffed82754a8d6392ad927cad9f2b26f49dbfd746a06af43f
+size 4806805719
diff --git a/pytorch_model-00019-of-00059.bin b/pytorch_model-00019-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5d1d471b1f483ce3b3bcdf2bb3027266b3adcaa6
--- /dev/null
+++ b/pytorch_model-00019-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f27d9bacc357f5e52f4d10b5590d6110eb82cc0947ee44e5c18a9bd1ee3764
+size 4806805719
diff --git a/pytorch_model-00020-of-00059.bin b/pytorch_model-00020-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0ba26af1db4d057e5a4cb0e48dd2b0f511c1624e
--- /dev/null
+++ b/pytorch_model-00020-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e707b7befb0c5fc4c252f672d9d4d937664cc928cf119ec1d0de57b09da35fea
+size 4806805719
diff --git a/pytorch_model-00021-of-00059.bin b/pytorch_model-00021-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..62200a3e2691601d0e5216e4f9767d4c0c9b14ef
--- /dev/null
+++ b/pytorch_model-00021-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e988aa6edd55b99c4215bed3d0ebabd0298ee9fe995c0ca21984a7921908671
+size 4806805719
diff --git a/pytorch_model-00022-of-00059.bin b/pytorch_model-00022-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..79be0e072cfb2a11a143364621e26645b4b6c0f5
--- /dev/null
+++ b/pytorch_model-00022-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01eaef2169c838ae885f5262ef4abbe38e828c4e4163e7cc3c6bb51677f0e6d0
+size 4806805719
diff --git a/pytorch_model-00023-of-00059.bin b/pytorch_model-00023-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0badba111cedcd894e32802b081977e94338dc97
--- /dev/null
+++ b/pytorch_model-00023-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f02730873296941df96ec2a3039630dd0d3813e2d87d697e2de531cc504402
+size 4806805719
diff --git a/pytorch_model-00024-of-00059.bin b/pytorch_model-00024-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a0a89caf77900f4959d2b1f18f0c979cb7dc9c23
--- /dev/null
+++ b/pytorch_model-00024-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d082027a707d845b4ab9d84beb30e884055d828a36d90bb11fda76f8c023e7
+size 4932536209
diff --git a/pytorch_model-00025-of-00059.bin b/pytorch_model-00025-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..04e9f34c6d1e9d43f05aef6a2008507693e0964d
--- /dev/null
+++ b/pytorch_model-00025-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea862b2f0025d6b9d8771992875e8bfcdb60c5e83d3e58f678aa9f8054a4a74
+size 4995549411
diff --git a/pytorch_model-00026-of-00059.bin b/pytorch_model-00026-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..51ae84ef941f957bede2cfef083c6d6d591e19b2
--- /dev/null
+++ b/pytorch_model-00026-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2879babf6d84897b283b69426b558f991a2056b89fda22b789492811c9099ad7
+size 4995549411
diff --git a/pytorch_model-00027-of-00059.bin b/pytorch_model-00027-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fc55adcbf78712bc47f57ac6fee7efd7af93b6d3
--- /dev/null
+++ b/pytorch_model-00027-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630e8e8084e6a251e3401e54150a951fd79dc100d9cfd85a90ebbcfcb427e1ee
+size 4932634851
diff --git a/pytorch_model-00028-of-00059.bin b/pytorch_model-00028-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fb7cdac7ad1f1fa70ad76901b96ac3126e794c6d
--- /dev/null
+++ b/pytorch_model-00028-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f229347ab31aa3fb68dfbf09699ed3bd168a1745239cc1415078fb62dab548
+size 4806780467
diff --git a/pytorch_model-00029-of-00059.bin b/pytorch_model-00029-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..247f3c983f3702479e6033dd0171a5db06d00ce9
--- /dev/null
+++ b/pytorch_model-00029-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec37a2981f8c246647b60678a16bb2822fe4303a461c8ce665b79dfce789f70e
+size 4806805767
diff --git a/pytorch_model-00030-of-00059.bin b/pytorch_model-00030-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ce1790454d03fb2c49c248b4eed764aa4fde3c5f
--- /dev/null
+++ b/pytorch_model-00030-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a458bcdd3dbbb34e327fc833aa94deda181d5294de7269095432c51d37895fc1
+size 4806805779
diff --git a/pytorch_model-00031-of-00059.bin b/pytorch_model-00031-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..20bd8ea7a6381f6a1727d67eaaee93c6f54a7618
--- /dev/null
+++ b/pytorch_model-00031-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f0b0cafa293be34163ba9d94249a4e3c83dc0faaef66901944f181e36636df
+size 4806805791
diff --git a/pytorch_model-00032-of-00059.bin b/pytorch_model-00032-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..68a1d3d1b0142de33707a3ed311addcc19369904
--- /dev/null
+++ b/pytorch_model-00032-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c693a71cf9115b1e9de4ba5e8ae878a07e4a60dfb992950dde4a4ae6cedf08
+size 4806805779
diff --git a/pytorch_model-00033-of-00059.bin b/pytorch_model-00033-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d70026c6149109370a194cee9da536f6ec6be45e
--- /dev/null
+++ b/pytorch_model-00033-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28f5f75da74fa1f38bba5629f4fbbe814e045104cf236730cbc480a2eea2771
+size 4806805779
diff --git a/pytorch_model-00034-of-00059.bin b/pytorch_model-00034-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4401382c408b565600b50fa8aba6a285c3d6af0f
--- /dev/null
+++ b/pytorch_model-00034-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6cfa0affd66af2d5381dc177e46d662979239b61cd298e9b7ed59fc67c08156
+size 4806805767
diff --git a/pytorch_model-00035-of-00059.bin b/pytorch_model-00035-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eff495480be7d8cbf642d4b6c1ce324b2f4af8b9
--- /dev/null
+++ b/pytorch_model-00035-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad87980fa49e8b3dc9db6c9994768abe195d03b57894d952d8af562330e464b
+size 4806805755
diff --git a/pytorch_model-00036-of-00059.bin b/pytorch_model-00036-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f93eeaf890f0d09db3a880812ea2121653028ffb
--- /dev/null
+++ b/pytorch_model-00036-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ab476cfef34f7fe638d9eeb18ef87b3bb7964b6ebcf3d16b278b127ccafff9
+size 4806805743
diff --git a/pytorch_model-00037-of-00059.bin b/pytorch_model-00037-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3fd846d485df0f4b40303a55993c9cd95641c164
--- /dev/null
+++ b/pytorch_model-00037-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428b87be281268e591f2cc7234892cf11f5bc622a79ca2e04103e799cf77a9ea
+size 4806805731
diff --git a/pytorch_model-00038-of-00059.bin b/pytorch_model-00038-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..34a5dbf7040a29f1a7a572f27468efdc916061c6
--- /dev/null
+++ b/pytorch_model-00038-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794cab6abc0a61dcba6802d416d61a9df6c90c9d7cb3d3b2e325e1255a2a6690
+size 4806805719
diff --git a/pytorch_model-00039-of-00059.bin b/pytorch_model-00039-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1dda5f78293b8961900474b74ede99dfac4ab356
--- /dev/null
+++ b/pytorch_model-00039-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61111a45e6136b204a75a327d484048e342270921f309834bf72070caa2e4fc1
+size 4806805719
diff --git a/pytorch_model-00040-of-00059.bin b/pytorch_model-00040-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3c848f5431472f4341b7ba37add4c779ad836f2d
--- /dev/null
+++ b/pytorch_model-00040-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394f6a2316437124e90eabcc3f4474e734dfd22082a07d94fc948d7c18f0f5c5
+size 4806805719
diff --git a/pytorch_model-00041-of-00059.bin b/pytorch_model-00041-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a1238cf8cbd9a408b4cad9b757bfc579c30853d2
--- /dev/null
+++ b/pytorch_model-00041-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b486915b630ae6ee28d0c2ac2553715af4975ce953ac800e04c54a2c166b22a
+size 4806805719
diff --git a/pytorch_model-00042-of-00059.bin b/pytorch_model-00042-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2ac7ef90275a0fc722005976db2620e1a78673ec
--- /dev/null
+++ b/pytorch_model-00042-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97094da41546cfabea5f6f1fe9d2b3c6dec3819684ab8a068aee2215c123479
+size 4806805719
diff --git a/pytorch_model-00043-of-00059.bin b/pytorch_model-00043-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1780dc0bfae5724cc409deab826e829a8586f136
--- /dev/null
+++ b/pytorch_model-00043-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3a1c7ee12e6b669c8ac0e64af35b746d5a45c25490bd004d2a334c6bfdd34a
+size 4806805719
diff --git a/pytorch_model-00044-of-00059.bin b/pytorch_model-00044-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e9df4db4d18b8124fc8868d8dc2fcfd1f6dbf94d
--- /dev/null
+++ b/pytorch_model-00044-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb95bac224ba7e802d63d2deb63808d5d4484b37fc9df3ce20a332a7b6af9d5
+size 4806805719
diff --git a/pytorch_model-00045-of-00059.bin b/pytorch_model-00045-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d24abe65d6bb83f6c2f08cfb906cae1fe9b42b9a
--- /dev/null
+++ b/pytorch_model-00045-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0910c243fbeb2946b4d247322147e59c2cff0d75862cb1c7f9d5efa99c57ec
+size 4806805719
diff --git a/pytorch_model-00046-of-00059.bin b/pytorch_model-00046-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..873f6158cd47ec76a1f2edcf23322ddccacfba01
--- /dev/null
+++ b/pytorch_model-00046-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b7e4d02ebae3fb89dab0ddc2e8e9c7d402198d96467a21905315dd45b19cb2
+size 4806805719
diff --git a/pytorch_model-00047-of-00059.bin b/pytorch_model-00047-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a10a7bd09eef461aaaf03c4c2fa650ee2defd85a
--- /dev/null
+++ b/pytorch_model-00047-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e77d6df8fa88ac080f22b4f157091f4f8c67bd129640ef37fb8408a6b534d81
+size 4806805719
diff --git a/pytorch_model-00048-of-00059.bin b/pytorch_model-00048-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3d8c380d1ccc14373a1b6ec91a77d6165912892d
--- /dev/null
+++ b/pytorch_model-00048-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7493982049c8354268464168c52b8fa7b5f8ac533cf8d1813010aa60d4467cb1
+size 4806805719
diff --git a/pytorch_model-00049-of-00059.bin b/pytorch_model-00049-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..272a0ab8d2f3b69fd15bcae791be9ed94e93135e
--- /dev/null
+++ b/pytorch_model-00049-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbf72d745e961553e9e629007d5bd69e2def6ebc0e614fe44ce46774298e735
+size 4806805719
diff --git a/pytorch_model-00050-of-00059.bin b/pytorch_model-00050-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1bcdc9d59e58879acb7d51a6e7f625911d5040a6
--- /dev/null
+++ b/pytorch_model-00050-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a3b98948a5fa728936e12d79fd137274648813856f49be312efb287dfd8568
+size 4806805719
diff --git a/pytorch_model-00051-of-00059.bin b/pytorch_model-00051-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f04b25621aec81a7aa37dabd82735644284b387
--- /dev/null
+++ b/pytorch_model-00051-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707a1c9d07803b9a0725ec024423cfac82a2bb5a6ea67231fd3426c446763424
+size 4806805719
diff --git a/pytorch_model-00052-of-00059.bin b/pytorch_model-00052-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4e88e7567a56a333efced4a2f47d0eac36b4a6b1
--- /dev/null
+++ b/pytorch_model-00052-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bc36410bdf8537dfb8a0d83de9f00179e8032d6a3042753566bb9b17d1af46
+size 4932536209
diff --git a/pytorch_model-00053-of-00059.bin b/pytorch_model-00053-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..41878768863c5ec614072e28f0b976240015ffb9
--- /dev/null
+++ b/pytorch_model-00053-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078b67d3c94fc43b3982618ce2fff242ced16ee35f3787189b90b43151630bc3
+size 4995549411
diff --git a/pytorch_model-00054-of-00059.bin b/pytorch_model-00054-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d100769bf927975d03effc0ed36fb833dc930adb
--- /dev/null
+++ b/pytorch_model-00054-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a2f4221a5846b21a198b03221e139b77b195dcf1163d847c1fb0421d9a7862
+size 4995549411
diff --git a/pytorch_model-00055-of-00059.bin b/pytorch_model-00055-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..00ca184106a70373fc797cf3708366704b8dcb39
--- /dev/null
+++ b/pytorch_model-00055-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4968dfb1ec875a29969490fa6d1ec5dc489faa8f9ba3b4c26ec0d98f09a69dbb
+size 4932634851
diff --git a/pytorch_model-00056-of-00059.bin b/pytorch_model-00056-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c846eb16f9bf0f5d22c5700016ebb61f40c10097
--- /dev/null
+++ b/pytorch_model-00056-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becc908d6c42eb499a86060f2d04d263c7d58f1ba8e977271e9d3c1d7c27e370
+size 4806780467
diff --git a/pytorch_model-00057-of-00059.bin b/pytorch_model-00057-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b06e9ba6c4a0df33e0c6c602d355d020f4b138a1
--- /dev/null
+++ b/pytorch_model-00057-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9f2d1f90aebcc14a79f32bd4a8b026c02b6d00ce853f8da1ce44116fab5f2d
+size 4806805767
diff --git a/pytorch_model-00058-of-00059.bin b/pytorch_model-00058-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..aba49d638010d47fdc35f319dacb5df69e444bb0
--- /dev/null
+++ b/pytorch_model-00058-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f325f9e8e3a3473f7b53e3dfae0e115cc5e84f78c03dc42cf953f26b0b968ec
+size 4806805779
diff --git a/pytorch_model-00059-of-00059.bin b/pytorch_model-00059-of-00059.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f1c7f91059a2db7620406457faea344266da217
--- /dev/null
+++ b/pytorch_model-00059-of-00059.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75414048a5a92dce5f270a96940187306749930dfcb7b46f1c3280d23e5108b
+size 997309200
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..3e7d9d69ffb86c0b93468e054bdcfa99651f8502
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,1746 @@
+{
+ "metadata": {
+ "total_size": 281241415680
+ },
+ "weight_map": {
+ "lm_head.weight": "pytorch_model-00059-of-00059.bin",
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00059.bin",
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00059.bin",
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00027-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00028-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00029-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.28.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00030-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.29.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00031-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.30.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00032-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.31.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00033-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.block_sparse_moe.gate.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00034-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.block_sparse_moe.gate.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00035-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.block_sparse_moe.gate.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00036-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.block_sparse_moe.gate.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00037-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.block_sparse_moe.gate.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00038-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.block_sparse_moe.gate.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00039-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.block_sparse_moe.gate.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00040-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.block_sparse_moe.gate.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00041-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.block_sparse_moe.gate.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00042-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.block_sparse_moe.gate.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00043-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.block_sparse_moe.gate.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00044-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.block_sparse_moe.gate.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00045-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.block_sparse_moe.gate.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00046-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.block_sparse_moe.gate.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00047-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.block_sparse_moe.gate.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00048-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.block_sparse_moe.gate.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00049-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.block_sparse_moe.gate.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.48.input_layernorm.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00050-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.block_sparse_moe.gate.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.49.input_layernorm.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00051-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.block_sparse_moe.gate.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.input_layernorm.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00052-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.block_sparse_moe.gate.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.input_layernorm.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00053-of-00059.bin",
+ "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.block_sparse_moe.gate.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.input_layernorm.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00054-of-00059.bin",
+ "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00055-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.53.block_sparse_moe.gate.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.input_layernorm.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00056-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.54.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.54.block_sparse_moe.gate.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.input_layernorm.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00057-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00059-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00059-of-00059.bin",
+ "model.layers.55.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00059-of-00059.bin",
+ "model.layers.55.block_sparse_moe.gate.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.input_layernorm.weight": "pytorch_model-00059-of-00059.bin",
+ "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00059-of-00059.bin",
+ "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00058-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00059.bin",
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00059.bin",
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00059.bin",
+ "model.norm.weight": "pytorch_model-00059-of-00059.bin"
+ }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..40b1c6dadc2aed5b9e61dc7f9c7299e0aee16069
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "",
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..968c135a2d8cb980659c8d40ae92705bf9bde561
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,93 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32000": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32001": {
+ "content": "<|begin_func|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32002": {
+ "content": "<|end_func|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32003": {
+ "content": "<|begin_func_response|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32004": {
+ "content": "<|end_func_response|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32005": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "additional_special_tokens": [],
+ "bos_token": "",
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "",
+ "use_default_system_prompt": false,
+ "use_fast": true
+}