diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..11a2c1b15df4e0b92041491f7812bd7bfd81144b --- /dev/null +++ b/README.md @@ -0,0 +1,107 @@ +--- +license: apache-2.0 +--- + + + +

+🏠 WizardLM-2 Release Blog

+

+🤗 HF Repo •🐱 Github Repo • 🐦 Twitter • 📃 [WizardLM] • 📃 [WizardCoder] • 📃 [WizardMath]
+

+

+ 👋 Join our Discord +

+ +## See [here](https://huggingface.co/lucyknada/microsoft_WizardLM-2-7B) for the WizardLM-2-7B re-upload. + +## News 🔥🔥🔥 [2024/04/15] + +We introduce and opensource WizardLM-2, our next generation state-of-the-art large language models, +which have improved performance on complex chat, multilingual, reasoning and agent. +New family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B. + +- WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works +and consistently outperforms all the existing state-of-the-art opensource models. +- WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size. +- WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models. + +For more details of WizardLM-2 please read our [release blog post](https://web.archive.org/web/20240415221214/https://wizardlm.github.io/WizardLM2/) and upcoming paper. + + +## Model Details + +* **Model name**: WizardLM-2 8x22B +* **Developed by**: WizardLM@Microsoft AI +* **Model type**: Mixture of Experts (MoE) +* **Base model**: [mistral-community/Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1) +* **Parameters**: 141B +* **Language(s)**: Multilingual +* **Blog**: [Introducing WizardLM-2](https://web.archive.org/web/20240415221214/https://wizardlm.github.io/WizardLM2/) +* **Repository**: [https://github.com/nlpxucan/WizardLM](https://github.com/nlpxucan/WizardLM) +* **Paper**: WizardLM-2 (Upcoming) +* **License**: Apache2.0 + + +## Model Capacities + + +**MT-Bench** + +We also adopt the automatic MT-Bench evaluation framework based on GPT-4 proposed by lmsys to assess the performance of models. +The WizardLM-2 8x22B even demonstrates highly competitive performance compared to the most advanced proprietary models. +Meanwhile, WizardLM-2 7B and WizardLM-2 70B are all the top-performing models among the other leading baselines at 7B to 70B model scales. + +

+MTBench +

+ + +**Human Preferences Evaluation** + +We carefully collected a complex and challenging set consisting of real-world instructions, which includes main requirements of humanity, such as writing, coding, math, reasoning, agent, and multilingual. +We report the win:loss rate without tie: + +- WizardLM-2 8x22B is just slightly falling behind GPT-4-1106-preview, and significantly stronger than Command R Plus and GPT4-0314. +- WizardLM-2 70B is better than GPT4-0613, Mistral-Large, and Qwen1.5-72B-Chat. +- WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta. + +

+Win +

+ + + + + +## Method Overview +We built a **fully AI powered synthetic training system** to train WizardLM-2 models, please refer to our [blog](https://web.archive.org/web/20240415221214/https://wizardlm.github.io/WizardLM2/) for more details of this system. + +

+Method +

+ + + + + +## Usage + +❗Note for model system prompts usage: + + +WizardLM-2 adopts the prompt format from Vicuna and supports **multi-turn** conversation. The prompt should be as following: + +``` +A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, +detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello. +USER: Who are you? ASSISTANT: I am WizardLM....... +``` + + Inference WizardLM-2 Demo Script + +We provide a WizardLM-2 inference demo [code](https://github.com/nlpxucan/WizardLM/tree/main/demo) on our github. + + + + diff --git a/model-00008-of-00059.safetensors b/model-00008-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..284f1d47c7f9caf81f4464c1b0b07e3dcea64d2e --- /dev/null +++ b/model-00008-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dffba340034dd20eb1f80f0722cd37e00f1a68007e323fab54d9849fa9097a34 +size 135 diff --git a/model-00009-of-00059.safetensors b/model-00009-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb9288e3ea4b1a39962ba1765df405aedd0894ef --- /dev/null +++ b/model-00009-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2beb8fa3863ab86881651d1fd1b0bfe34321306d1a98511643fcec1cf8cd1d8d +size 135 diff --git a/model-00010-of-00059.safetensors b/model-00010-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e00acac28384fc8fc84c474c78009f8d54e56b93 --- /dev/null +++ b/model-00010-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0741138979b1575e6365228083af3bd4080e81bfdd5ef4953818ace65899498b +size 135 diff --git a/model-00011-of-00059.safetensors b/model-00011-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a630ac9c62015ae6fe36051708272475516fc5b --- /dev/null +++ b/model-00011-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e76b8ce0860d896353bd8241e303560940fa0ebb6ad9b9165edf8469613ecb2 +size 135 diff --git a/model-00012-of-00059.safetensors b/model-00012-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68cd85c0eac5076e190439ab60d84bca07a5b095 --- /dev/null +++ b/model-00012-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5d137861e3b0bef9f372c930153ce0065d6c2924fe06c7ff413498b9ce35928 +size 135 diff --git a/model-00013-of-00059.safetensors b/model-00013-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..81dfb47bb535eff43e176dc80e02fac6c8b2a6ec --- /dev/null +++ b/model-00013-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd3ae4aca2230da7193bd84b24cae36da3d12a9a3a5b3ba1d54f3f4320798de +size 135 diff --git a/model-00014-of-00059.safetensors b/model-00014-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..513ed1af6c4b66e348171b467ca613e030cdfdd0 --- /dev/null +++ b/model-00014-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73df3713b6021bcc1a8ae4c86eaf7e69445777ecfe159cc1aaf7d10a254df66 +size 135 diff --git a/model-00015-of-00059.safetensors b/model-00015-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76c311d533664f0e94f4845763addc0e85e382de --- /dev/null +++ b/model-00015-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:941dfa462ee9d41e17177cd41d1eec91d6cfb755dd62b2069003e8c8040194fc +size 135 diff --git a/model-00016-of-00059.safetensors b/model-00016-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76077ca3cb05343fae710cca4c781ecab8148ad1 --- /dev/null +++ b/model-00016-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50e42138b1a66fac7f587d13ec647a309d48297fb88b359893ab9f606f643e83 +size 135 diff --git a/model-00017-of-00059.safetensors b/model-00017-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0fd8854d337364e4821c2d4a17dd0fdec2f81e4c --- /dev/null +++ b/model-00017-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db989a36c3c73e4485f41c60a712a9c13fb89c56e267000a8d4b6fb1520558ec +size 135 diff --git a/model-00018-of-00059.safetensors b/model-00018-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33d8ef27fd121272ea972f0c4a77b00033b8bad2 --- /dev/null +++ b/model-00018-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c0414ce99be6a2410318666c65453f2d9dc255f8979f28bbf34de0904a30837 +size 135 diff --git a/model-00019-of-00059.safetensors b/model-00019-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ebccc7ef6118b8eab7324f1877d2df997e16d150 --- /dev/null +++ b/model-00019-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4315bdc13dedb31a6b4efa929a84f8f3c91a5dd55e4a7bc54b4070c4ced07c +size 135 diff --git a/model-00020-of-00059.safetensors b/model-00020-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..082afba4b210c929eb6308eef92c4cb99c90d379 --- /dev/null +++ b/model-00020-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51602b3a621eab1516dec031bb77033ee51620e79de125783b4e88e12b9c6265 +size 135 diff --git a/model-00021-of-00059.safetensors b/model-00021-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9dada7eb36dd0e8fbf6ac4a5cee7835c03769489 --- /dev/null +++ b/model-00021-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d896016355935a87c83c84eb57062da23f6b08385fc684119ec9c87960a0a0 +size 135 diff --git a/model-00022-of-00059.safetensors b/model-00022-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce3eb128618a55bf423acc47a434c294307c88f8 --- /dev/null +++ b/model-00022-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bfa535ee228f25a32c082760231de113c41bd4b124503d2beba8685e6f723fb +size 135 diff --git a/model-00023-of-00059.safetensors b/model-00023-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21ecde9fd0394306783d63ba365c07675c7125c6 --- /dev/null +++ b/model-00023-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:779da18e1537244ab3eee357f0852b9967e2d5b6a7a1eed9fcbc098e420ea46a +size 135 diff --git a/model-00024-of-00059.safetensors b/model-00024-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0633bac37522a96802561ee1f8a1da8e9ba5f088 --- /dev/null +++ b/model-00024-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd7ff67b4ef53423ed6e1ffd6a7593d4212d8b181eff7b63bc738b7fc854441 +size 135 diff --git a/model-00025-of-00059.safetensors b/model-00025-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7015b9b007452d29e0e66ef87cc9c5cc59d9d57c --- /dev/null +++ b/model-00025-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cce1f2fbb178559cbe49271f51e1b2d17031b9b553c7fe15683627fa8450470 +size 135 diff --git a/model-00026-of-00059.safetensors b/model-00026-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c76668e782b57461db69eec2cce99d2cfe205b18 --- /dev/null +++ b/model-00026-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5db519f0305cc78226d132758ac341f790a2b529f03877eebc9b52d0fbe0ae5 +size 135 diff --git a/model-00027-of-00059.safetensors b/model-00027-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7bec2a3faa54b2666f14a2f2fb9199d739f9e97 --- /dev/null +++ b/model-00027-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803ba7494e7a7ac758fe36a44cc9bafb4d73b2b3f061d5c9c5bacce0b0a5737b +size 135 diff --git a/model-00028-of-00059.safetensors b/model-00028-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..818917f3ef859778d6541b65a972e7dc0bbbca50 --- /dev/null +++ b/model-00028-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657bf21404a5494fa8787c9f5f067f65097cff73df6f5c061b7c1dbb93f6e917 +size 135 diff --git a/model-00029-of-00059.safetensors b/model-00029-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..246f18b99d34da3453eeb8656b21128b57d2dbc5 --- /dev/null +++ b/model-00029-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9848fcc6a2e066aa09390e49056423d28db95979a9dc6f111324158d0d68d9f6 +size 135 diff --git a/model-00030-of-00059.safetensors b/model-00030-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..175f26cdba93afb1eecba033e0ae236cbee97ad9 --- /dev/null +++ b/model-00030-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc96f503ba8bb7f55b886f20402073380a5dd7f27cd12e1697ed35181aaec2a7 +size 135 diff --git a/model-00031-of-00059.safetensors b/model-00031-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..662653f28b2b54d772dd7a065c603d0d4f2e6e12 --- /dev/null +++ b/model-00031-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc304b0a0c71fc37a31b8c06b496dacdd25b262233495ede0f93668f68a4f9a +size 135 diff --git a/model-00032-of-00059.safetensors b/model-00032-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0965f3217e6337cbb9bc7119144f9d8adc533568 --- /dev/null +++ b/model-00032-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f70709f287f5618e11bbbf246000e80a2a8264a4497300051d2dac4d6934b412 +size 135 diff --git a/model-00033-of-00059.safetensors b/model-00033-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3dcf5b3c0c523ea00e899f011b7bd5bdcc48ee4 --- /dev/null +++ b/model-00033-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53eb21d769607eda95c118e5b9e5042b508262a8d7fba86d58f9cef0642d431e +size 135 diff --git a/model-00034-of-00059.safetensors b/model-00034-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b0c6279ae1e8ea43a61e82d58b1a44f4bc55bc4d --- /dev/null +++ b/model-00034-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef492c42e01cbbc1d30df3d4f6052e52036e4ae41fb3a7ea6f7dc7b9cfdda6ea +size 135 diff --git a/model-00035-of-00059.safetensors b/model-00035-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b16cd55a35eb06385dfa04016865245998dee5cd --- /dev/null +++ b/model-00035-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:848a7b43aa60c89bf4d714abf87d8200d8fcecddc33403bf50beab6ded55997a +size 135 diff --git a/model-00036-of-00059.safetensors b/model-00036-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3add04d660692bbd44e8d731eb7f6912fdad5e3 --- /dev/null +++ b/model-00036-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcdb69a4fbf897b4a154ee2895f6831d285ba751c4fa316cf9f961d5522c6a74 +size 135 diff --git a/model-00037-of-00059.safetensors b/model-00037-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbe030029e66c6200aa6b20fb6e850dc91babbe0 --- /dev/null +++ b/model-00037-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7e2d451ab5dc1556cbbaf899030cd0740ac9dd657b4d12985f7d91ecf2ed04e +size 135 diff --git a/model-00038-of-00059.safetensors b/model-00038-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2238068297f333d2fe24ffd863796ebebb345a94 --- /dev/null +++ b/model-00038-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:905c14bc2e3862a9738d9f245ffaa89c7e6ca16c9fdc59408544d0ba51bee0c1 +size 135 diff --git a/model-00039-of-00059.safetensors b/model-00039-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff497a5ff38f45a2904deca0138f5d374cceae33 --- /dev/null +++ b/model-00039-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:962b88806b392888bc40a287f2100da3b8bb7a2b5b5f31cc89be8e4248947e11 +size 135 diff --git a/model-00040-of-00059.safetensors b/model-00040-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ae7075b40fa9a4f10da8585e09402b03934e675 --- /dev/null +++ b/model-00040-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a4565671348df6334c5d9a5d38de6ffd5416d975879fab428e1ff5b9757df50 +size 135 diff --git a/model-00041-of-00059.safetensors b/model-00041-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9822963819ee0ee074006abf1d27e0f854828187 --- /dev/null +++ b/model-00041-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b95b1b245070b239a8c2bb05c41d1495bf2ff65c4c09d4f0b392dabeb4244d7 +size 135 diff --git a/model-00042-of-00059.safetensors b/model-00042-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f7a8352fbdb8331f53cb8a86fa7fd107f574864 --- /dev/null +++ b/model-00042-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7542a10051eb27ba6856d2e326a5d7276ff7a0de6a754e2e2787afdcb4c152 +size 135 diff --git a/model-00043-of-00059.safetensors b/model-00043-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..606211d7911218bd88b0092cf873a96fab7d88ac --- /dev/null +++ b/model-00043-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:211921479db91ffd541118eac3dad74fe428e1c92d04ff25562efef0074a5201 +size 135 diff --git a/model-00044-of-00059.safetensors b/model-00044-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a436fa24a8e10ec7a9bce4cca9342f0bdef9f34 --- /dev/null +++ b/model-00044-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc87154228c7047da938a82a4662685178bee1e61a43b7948e7bfb1b5be07ac8 +size 135 diff --git a/model-00045-of-00059.safetensors b/model-00045-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5fe3d2c677a3f0eca180471398b8eb7e738cd3fb --- /dev/null +++ b/model-00045-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7151026c85dc9191342fc0ad95d2f0cee38e58e3a4b11aa81c1f0f31bac90b +size 135 diff --git a/model-00046-of-00059.safetensors b/model-00046-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e6711466ff10e00ba7800602ed073c0ea4205c7d --- /dev/null +++ b/model-00046-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907a57a30b50a1233561b1de4d592dcd6e6d10a7dde012dd52588be034c89a5e +size 135 diff --git a/model-00047-of-00059.safetensors b/model-00047-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34ec03a929edcf761898f2708d2cab7bc4502659 --- /dev/null +++ b/model-00047-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c5cf002ff9a62a313e55c2b928c86c15612d5413bf6713dba12c21df0725d3 +size 135 diff --git a/model-00048-of-00059.safetensors b/model-00048-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5208ba39cf45d87f18bba36be0e9a8e34dbfc4b --- /dev/null +++ b/model-00048-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7acb5fe7aad9c0f7c5e4eee9498a6f7bc0caee9a57401ab9e5d400cf6bc9ccba +size 135 diff --git a/model-00049-of-00059.safetensors b/model-00049-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b73c4a5e73d98a3c6bb65b6a4f0524201bf0872 --- /dev/null +++ b/model-00049-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b67ed0e09f1e68b42510da79de5c9ed564f8df257e741e95cc60d2acb9e6441 +size 135 diff --git a/model-00050-of-00059.safetensors b/model-00050-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2870b27f1c8b49f82501d811a80595c136a59683 --- /dev/null +++ b/model-00050-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2019f0f77e04b2889a28de2339e96282a730f8aa3144865ec26b2bcb28454136 +size 135 diff --git a/model-00051-of-00059.safetensors b/model-00051-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1741161161c5e06940f42c1f7fb93a448c14b43c --- /dev/null +++ b/model-00051-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7004d8a5fc31993c6cad3595a87485cfcd4b76197f1e3101faace304ccbee470 +size 135 diff --git a/model-00052-of-00059.safetensors b/model-00052-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7bfc757c67b68b61ed72e84d09124c69ad74f738 --- /dev/null +++ b/model-00052-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62b18a103e08ea01e13b2b1dd9dae5c298407de4dfdd46e75ecd8ec397b24a36 +size 135 diff --git a/model-00053-of-00059.safetensors b/model-00053-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ffd0ac42d9de089c1d50331892621a18f8193f62 --- /dev/null +++ b/model-00053-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826bf1ed1bb920a332eb34680c16406e04bf486b17adfabbd23ca6624762ba5d +size 135 diff --git a/model-00054-of-00059.safetensors b/model-00054-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..556d1cb9b1aaefdeb2e1873207d03e45704fa1f7 --- /dev/null +++ b/model-00054-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4f85d37238d4ff3224c0117d1bffaeaf102c71b8ae812a09bd3d31b72dbeca +size 135 diff --git a/model-00055-of-00059.safetensors b/model-00055-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..766ee610a1fa940ab02ccb7203a7b88992adc177 --- /dev/null +++ b/model-00055-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca5076dba941db57235c956ebe8b17e7d16dd9d41e165d27fb214c95a3831991 +size 135 diff --git a/model-00056-of-00059.safetensors b/model-00056-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cdcaa9e3f3d766d53f5bec18c39a194a92e3d49c --- /dev/null +++ b/model-00056-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c2fabf9671a8da3ab89152450807e775cdd3906578a39fa43c3e53e6e650178 +size 135 diff --git a/model-00057-of-00059.safetensors b/model-00057-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f2cc655296d680ac2124d20933f9e9672d85eac --- /dev/null +++ b/model-00057-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5987e5a3e16e83ec6043f3687e5424a050e5ee95ebfc52706fea25d2f1799e51 +size 135 diff --git a/model-00058-of-00059.safetensors b/model-00058-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d64867388048ac26dae888b23906d36393a140e4 --- /dev/null +++ b/model-00058-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:940760247fa1a79d2ca22ea6b23b795535498a837ce43abb4521a76beab57773 +size 135 diff --git a/model-00059-of-00059.safetensors b/model-00059-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6012bce9243e59f9d02cbcf322635cee0b0fcc66 --- /dev/null +++ b/model-00059-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0f7233f4d5b118839d82c966e59c5d46d1de3e4fa4200ed2172c1c051a56b9 +size 134 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..805c18819ee3c4a51164b634df4f4033c74583ad --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1746 @@ +{ + "metadata": { + "total_size": 281241268224 + }, + "weight_map": { + "lm_head.weight": "model-00059-of-00059.safetensors", + "model.embed_tokens.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00059.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00059.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00059.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00059.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00059.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00059.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00059.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00059.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00059.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00059.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00059.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00059.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.gate.weight": "model-00011-of-00059.safetensors", + "model.layers.10.input_layernorm.weight": "model-00012-of-00059.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00059.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00059.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00059.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00059.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00059.safetensors", + "model.layers.11.input_layernorm.weight": "model-00013-of-00059.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00059.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00059.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00059.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00059.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00059.safetensors", + "model.layers.12.input_layernorm.weight": "model-00014-of-00059.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00059.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00059.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00059.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00059.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.gate.weight": "model-00014-of-00059.safetensors", + "model.layers.13.input_layernorm.weight": "model-00015-of-00059.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00059.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00059.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00059.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00059.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.gate.weight": "model-00015-of-00059.safetensors", + "model.layers.14.input_layernorm.weight": "model-00016-of-00059.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00059.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00059.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00059.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00059.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.gate.weight": "model-00016-of-00059.safetensors", + "model.layers.15.input_layernorm.weight": "model-00017-of-00059.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00059.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00059.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00059.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00059.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.gate.weight": "model-00017-of-00059.safetensors", + "model.layers.16.input_layernorm.weight": "model-00018-of-00059.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00059.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00059.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00059.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00059.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.gate.weight": "model-00018-of-00059.safetensors", + "model.layers.17.input_layernorm.weight": "model-00019-of-00059.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00059.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00059.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00059.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00059.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.gate.weight": "model-00019-of-00059.safetensors", + "model.layers.18.input_layernorm.weight": "model-00020-of-00059.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00059.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00059.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00059.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00059.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.gate.weight": "model-00020-of-00059.safetensors", + "model.layers.19.input_layernorm.weight": "model-00021-of-00059.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00059.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00059.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00059.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00059.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00059.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00059.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00059.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00059.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00059.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00059.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.gate.weight": "model-00021-of-00059.safetensors", + "model.layers.20.input_layernorm.weight": "model-00022-of-00059.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00059.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00059.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00059.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00059.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.gate.weight": "model-00022-of-00059.safetensors", + "model.layers.21.input_layernorm.weight": "model-00023-of-00059.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00059.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00059.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00059.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00059.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.gate.weight": "model-00023-of-00059.safetensors", + "model.layers.22.input_layernorm.weight": "model-00024-of-00059.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00059.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00059.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00059.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00059.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00059.safetensors", + "model.layers.23.input_layernorm.weight": "model-00025-of-00059.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00059.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00059.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00025-of-00059.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00059.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.gate.weight": "model-00026-of-00059.safetensors", + "model.layers.24.input_layernorm.weight": "model-00026-of-00059.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00026-of-00059.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00059.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00026-of-00059.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00059.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00026-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.gate.weight": "model-00027-of-00059.safetensors", + "model.layers.25.input_layernorm.weight": "model-00027-of-00059.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00027-of-00059.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00027-of-00059.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00027-of-00059.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00059.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00027-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.26.block_sparse_moe.gate.weight": "model-00028-of-00059.safetensors", + "model.layers.26.input_layernorm.weight": "model-00029-of-00059.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00029-of-00059.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00028-of-00059.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00028-of-00059.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00028-of-00059.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00028-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.27.block_sparse_moe.gate.weight": "model-00029-of-00059.safetensors", + "model.layers.27.input_layernorm.weight": "model-00030-of-00059.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00030-of-00059.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00029-of-00059.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00029-of-00059.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00029-of-00059.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00029-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.28.block_sparse_moe.gate.weight": "model-00030-of-00059.safetensors", + "model.layers.28.input_layernorm.weight": "model-00031-of-00059.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00031-of-00059.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00030-of-00059.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00030-of-00059.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00030-of-00059.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00030-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.29.block_sparse_moe.gate.weight": "model-00031-of-00059.safetensors", + "model.layers.29.input_layernorm.weight": "model-00032-of-00059.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00032-of-00059.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00031-of-00059.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00031-of-00059.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00031-of-00059.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00031-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00059.safetensors", + "model.layers.3.input_layernorm.weight": "model-00005-of-00059.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00059.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00059.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00059.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00059.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.gate.weight": "model-00032-of-00059.safetensors", + "model.layers.30.input_layernorm.weight": "model-00033-of-00059.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00033-of-00059.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00032-of-00059.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00032-of-00059.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00032-of-00059.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00032-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.gate.weight": "model-00033-of-00059.safetensors", + "model.layers.31.input_layernorm.weight": "model-00034-of-00059.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00034-of-00059.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00033-of-00059.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00033-of-00059.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00033-of-00059.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00033-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.gate.weight": "model-00034-of-00059.safetensors", + "model.layers.32.input_layernorm.weight": "model-00035-of-00059.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00035-of-00059.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00034-of-00059.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00034-of-00059.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00034-of-00059.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00034-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.gate.weight": "model-00035-of-00059.safetensors", + "model.layers.33.input_layernorm.weight": "model-00036-of-00059.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00036-of-00059.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00035-of-00059.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00035-of-00059.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00035-of-00059.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00035-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.gate.weight": "model-00036-of-00059.safetensors", + "model.layers.34.input_layernorm.weight": "model-00037-of-00059.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00037-of-00059.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00036-of-00059.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00036-of-00059.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00036-of-00059.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00036-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.gate.weight": "model-00037-of-00059.safetensors", + "model.layers.35.input_layernorm.weight": "model-00038-of-00059.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00038-of-00059.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00037-of-00059.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00037-of-00059.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00037-of-00059.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00037-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.gate.weight": "model-00038-of-00059.safetensors", + "model.layers.36.input_layernorm.weight": "model-00039-of-00059.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00039-of-00059.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00038-of-00059.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00038-of-00059.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00038-of-00059.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00038-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.gate.weight": "model-00039-of-00059.safetensors", + "model.layers.37.input_layernorm.weight": "model-00040-of-00059.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00040-of-00059.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00039-of-00059.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00039-of-00059.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00039-of-00059.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00039-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.gate.weight": "model-00040-of-00059.safetensors", + "model.layers.38.input_layernorm.weight": "model-00041-of-00059.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00041-of-00059.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00040-of-00059.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00040-of-00059.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00040-of-00059.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00040-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.gate.weight": "model-00041-of-00059.safetensors", + "model.layers.39.input_layernorm.weight": "model-00042-of-00059.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00042-of-00059.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00041-of-00059.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00041-of-00059.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00041-of-00059.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00041-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00059.safetensors", + "model.layers.4.input_layernorm.weight": "model-00006-of-00059.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00059.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00059.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00059.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00059.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.4.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.4.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.4.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.5.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.5.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.5.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.6.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.6.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.6.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.7.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.7.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.7.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.gate.weight": "model-00042-of-00059.safetensors", + "model.layers.40.input_layernorm.weight": "model-00043-of-00059.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00043-of-00059.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00042-of-00059.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00042-of-00059.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00042-of-00059.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00042-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.4.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.4.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.4.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.5.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.5.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.5.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.6.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.6.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.6.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.7.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.7.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.7.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.gate.weight": "model-00043-of-00059.safetensors", + "model.layers.41.input_layernorm.weight": "model-00044-of-00059.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00044-of-00059.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00043-of-00059.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00043-of-00059.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00043-of-00059.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00043-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.4.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.4.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.4.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.5.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.5.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.5.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.6.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.6.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.6.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.7.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.7.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.7.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.gate.weight": "model-00044-of-00059.safetensors", + "model.layers.42.input_layernorm.weight": "model-00045-of-00059.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00045-of-00059.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00044-of-00059.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00044-of-00059.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00044-of-00059.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00044-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.4.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.4.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.4.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.5.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.5.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.5.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.6.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.6.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.6.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.7.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.7.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.7.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.gate.weight": "model-00045-of-00059.safetensors", + "model.layers.43.input_layernorm.weight": "model-00046-of-00059.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00046-of-00059.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00045-of-00059.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00045-of-00059.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00045-of-00059.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00045-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.4.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.4.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.4.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.5.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.5.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.5.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.6.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.6.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.6.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.7.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.7.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.7.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.gate.weight": "model-00046-of-00059.safetensors", + "model.layers.44.input_layernorm.weight": "model-00047-of-00059.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00047-of-00059.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00046-of-00059.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00046-of-00059.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00046-of-00059.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00046-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.4.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.4.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.4.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.5.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.5.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.5.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.6.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.6.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.6.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.7.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.7.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.7.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.gate.weight": "model-00047-of-00059.safetensors", + "model.layers.45.input_layernorm.weight": "model-00048-of-00059.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00048-of-00059.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00047-of-00059.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00047-of-00059.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00047-of-00059.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00047-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.4.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.4.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.4.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.5.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.5.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.5.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.6.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.6.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.6.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.7.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.7.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.7.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.gate.weight": "model-00048-of-00059.safetensors", + "model.layers.46.input_layernorm.weight": "model-00049-of-00059.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00049-of-00059.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00048-of-00059.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00048-of-00059.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00048-of-00059.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00048-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.4.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.4.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.4.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.5.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.5.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.5.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.6.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.6.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.6.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.7.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.7.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.7.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.gate.weight": "model-00049-of-00059.safetensors", + "model.layers.47.input_layernorm.weight": "model-00050-of-00059.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00050-of-00059.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00049-of-00059.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00049-of-00059.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00049-of-00059.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00049-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.4.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.4.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.4.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.5.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.5.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.5.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.6.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.6.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.6.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.7.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.7.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.7.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.gate.weight": "model-00050-of-00059.safetensors", + "model.layers.48.input_layernorm.weight": "model-00051-of-00059.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00051-of-00059.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00050-of-00059.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00050-of-00059.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00050-of-00059.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00050-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.4.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.4.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.4.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.5.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.5.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.5.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.6.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.6.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.6.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.7.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.7.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.7.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.gate.weight": "model-00051-of-00059.safetensors", + "model.layers.49.input_layernorm.weight": "model-00052-of-00059.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00052-of-00059.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00051-of-00059.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00051-of-00059.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00051-of-00059.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00051-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00059.safetensors", + "model.layers.5.input_layernorm.weight": "model-00007-of-00059.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00059.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00059.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00059.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00059.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.4.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.4.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.4.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.5.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.5.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.5.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.6.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.6.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.6.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.7.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.7.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.7.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.gate.weight": "model-00053-of-00059.safetensors", + "model.layers.50.input_layernorm.weight": "model-00053-of-00059.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00053-of-00059.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00052-of-00059.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00053-of-00059.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00052-of-00059.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00052-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.4.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.4.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.4.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.5.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.5.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.5.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.6.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.6.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.6.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.7.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.7.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.7.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.gate.weight": "model-00054-of-00059.safetensors", + "model.layers.51.input_layernorm.weight": "model-00054-of-00059.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00054-of-00059.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00053-of-00059.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00054-of-00059.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00053-of-00059.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00054-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.4.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.4.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.4.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.5.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.5.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.5.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.6.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.6.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.6.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.7.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.7.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.7.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.gate.weight": "model-00055-of-00059.safetensors", + "model.layers.52.input_layernorm.weight": "model-00055-of-00059.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00055-of-00059.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00055-of-00059.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00055-of-00059.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00054-of-00059.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00055-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.4.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.4.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.4.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.5.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.5.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.5.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.6.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.6.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.6.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.7.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.7.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.7.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.53.block_sparse_moe.gate.weight": "model-00056-of-00059.safetensors", + "model.layers.53.input_layernorm.weight": "model-00057-of-00059.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00057-of-00059.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00056-of-00059.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00056-of-00059.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00056-of-00059.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00056-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.4.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.4.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.4.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.5.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.5.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.5.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.6.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.6.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.6.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.7.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.7.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.7.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.54.block_sparse_moe.gate.weight": "model-00057-of-00059.safetensors", + "model.layers.54.input_layernorm.weight": "model-00058-of-00059.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00058-of-00059.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00057-of-00059.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00057-of-00059.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00057-of-00059.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00057-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.4.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.4.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.4.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.5.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.5.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.5.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.6.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.6.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.6.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.7.w1.weight": "model-00059-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.7.w2.weight": "model-00059-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.7.w3.weight": "model-00059-of-00059.safetensors", + "model.layers.55.block_sparse_moe.gate.weight": "model-00058-of-00059.safetensors", + "model.layers.55.input_layernorm.weight": "model-00059-of-00059.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00059-of-00059.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00058-of-00059.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00058-of-00059.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00058-of-00059.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00058-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00059.safetensors", + "model.layers.6.input_layernorm.weight": "model-00008-of-00059.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00059.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00059.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00059.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00059.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00059.safetensors", + "model.layers.7.input_layernorm.weight": "model-00009-of-00059.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00059.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00059.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00059.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00059.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00059.safetensors", + "model.layers.8.input_layernorm.weight": "model-00010-of-00059.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00059.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00059.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00059.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00059.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.gate.weight": "model-00010-of-00059.safetensors", + "model.layers.9.input_layernorm.weight": "model-00011-of-00059.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00059.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00059.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00059.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00059.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00059.safetensors", + "model.norm.weight": "model-00059-of-00059.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e --- /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": "", + "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..263bf6dee5ede2d79f05a9e53c4ce424e732aebc --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3daefa6fd9ee26430a71ad6009f05c4c4ec086746b2dcc3d04649f631d3654f +size 131 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fd92a7b4ef5fd2a5b85ed21c2458d3f79ce9ba90 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "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 + } + }, + "additional_special_tokens": [], + "bos_token": "", + "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{{ messages[0]['content'].strip() }}{% else %}{% set loop_messages = messages %}{{ 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions.' }}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ ' USER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% else %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ '\nUSER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' ASSISTANT:' }}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +}