From 9c868b6fa45013e68c7caf95bdde2c0055eea5b4 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 14 Jun 2026 05:16:19 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: BiMediX/BiMediX-Bi Source: Original Platform --- .gitattributes | 35 ++ README.md | 63 ++ config.json | 30 + generation_config.json | 7 + pytorch_model-00001-of-00019.bin | 3 + pytorch_model-00002-of-00019.bin | 3 + pytorch_model-00003-of-00019.bin | 3 + pytorch_model-00004-of-00019.bin | 3 + pytorch_model-00005-of-00019.bin | 3 + pytorch_model-00006-of-00019.bin | 3 + pytorch_model-00007-of-00019.bin | 3 + pytorch_model-00008-of-00019.bin | 3 + pytorch_model-00009-of-00019.bin | 3 + pytorch_model-00010-of-00019.bin | 3 + pytorch_model-00011-of-00019.bin | 3 + pytorch_model-00012-of-00019.bin | 3 + pytorch_model-00013-of-00019.bin | 3 + pytorch_model-00014-of-00019.bin | 3 + pytorch_model-00015-of-00019.bin | 3 + pytorch_model-00016-of-00019.bin | 3 + pytorch_model-00017-of-00019.bin | 3 + pytorch_model-00018-of-00019.bin | 3 + pytorch_model-00019-of-00019.bin | 3 + pytorch_model.bin.index.json | 1002 ++++++++++++++++++++++++++++++ special_tokens_map.json | 24 + tokenizer.model | 3 + tokenizer_config.json | 45 ++ 27 files changed, 1266 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 pytorch_model-00001-of-00019.bin create mode 100644 pytorch_model-00002-of-00019.bin create mode 100644 pytorch_model-00003-of-00019.bin create mode 100644 pytorch_model-00004-of-00019.bin create mode 100644 pytorch_model-00005-of-00019.bin create mode 100644 pytorch_model-00006-of-00019.bin create mode 100644 pytorch_model-00007-of-00019.bin create mode 100644 pytorch_model-00008-of-00019.bin create mode 100644 pytorch_model-00009-of-00019.bin create mode 100644 pytorch_model-00010-of-00019.bin create mode 100644 pytorch_model-00011-of-00019.bin create mode 100644 pytorch_model-00012-of-00019.bin create mode 100644 pytorch_model-00013-of-00019.bin create mode 100644 pytorch_model-00014-of-00019.bin create mode 100644 pytorch_model-00015-of-00019.bin create mode 100644 pytorch_model-00016-of-00019.bin create mode 100644 pytorch_model-00017-of-00019.bin create mode 100644 pytorch_model-00018-of-00019.bin create mode 100644 pytorch_model-00019-of-00019.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..64138dd --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +language: +- en +- ar +metrics: +- accuracy +pipeline_tag: text-generation +tags: +- medical +license: cc-by-nc-sa-4.0 +--- +## Model Card for BiMediX-Bilingual + +### Model Details +- **Name:** BiMediX +- **Version:** 1.0 +- **Type:** Bilingual Medical Mixture of Experts Large Language Model (LLM) +- **Languages:** English, Arabic +- **Model Architecture:** [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) +- **Training Data:** BiMed1.3M, a bilingual dataset with diverse medical interactions. + +### Intended Use +- **Primary Use:** Medical interactions in both English and Arabic. +- **Capabilities:** MCQA, closed QA and chats. + +## Getting Started + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +model_id = "BiMediX/BiMediX-Bi" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id) +text = "Hello BiMediX! I've been experiencing increased tiredness in the past week." +inputs = tokenizer(text, return_tensors="pt") +outputs = model.generate(**inputs, max_new_tokens=500) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +### Training Procedure +- **Dataset:** BiMed1.3M, 632 million healthcare specialized tokens. +- **QLoRA Adaptation:** Implements a low-rank adaptation technique, incorporating learnable low-rank adapter weights into the experts and the routing network. This results in training about 4% of the original parameters. +- **Training Resources:** The model underwent training on approximately 632 million tokens from the Arabic-English corpus, including 288 million tokens exclusively for English. + +### Model Performance +- **Benchmarks:** Outperforms the baseline model and Jais-30B in medical evaluations. + +| **Model** | **CKG** | **CBio** | **CMed** | **MedGen** | **ProMed** | **Ana** | **MedMCQA** | **MedQA** | **PubmedQA** | **AVG** | +|-----------------------------------|------------|-----------|-----------|-------------|-------------|---------|-------------|-----------|--------------|---------| +| Jais-30B | 57.4 | 55.2 | 46.2 | 55.0 | 46.0 | 48.9 | 40.2 | 31.0 | 75.5 | 50.6 | +| Mixtral-8x7B| 59.1 | 57.6 | 52.6 | 59.5 | 53.3 | 54.4 | 43.2 | 40.6 | 74.7 | 55.0 | +| **BiMediX (Bilingual)** | **70.6** | **72.2** | **59.3** | **74.0** | **64.2** | **59.6**| **55.8** | **54.0** | **78.6** | **65.4**| + +### Safety and Ethical Considerations +- **Potential issues**: hallucinations, toxicity, stereotypes. +- **Usage:** Research purposes only. + +### Accessibility +- **Availability:** [BiMediX GitHub Repository](https://github.com/mbzuai-oryx/BiMediX). +- arxiv.org/abs/2402.13253 + +### Authors +Sara Pieri, Sahal Shaji Mullappilly, Fahad Shahbaz Khan, Rao Muhammad Anwer Salman Khan, Timothy Baldwin, Hisham Cholakkal +**Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)** \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..8df5536 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "mistralai/Mixtral-8x7B-v0.1", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mixtral", + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": true, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.02, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.0", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a65f260 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "transformers_version": "4.37.0" +} diff --git a/pytorch_model-00001-of-00019.bin b/pytorch_model-00001-of-00019.bin new file mode 100644 index 0000000..37aeba1 --- /dev/null +++ b/pytorch_model-00001-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad342adb98aed82bdc4d5604d0c8a06b4095865f3c24072289beebb9a25a1df +size 4892821288 diff --git a/pytorch_model-00002-of-00019.bin b/pytorch_model-00002-of-00019.bin new file mode 100644 index 0000000..a954430 --- /dev/null +++ b/pytorch_model-00002-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb252da0231413672844511d6af7eefc0452497eb2d9946995fe7704f7c13045 +size 4983016612 diff --git a/pytorch_model-00003-of-00019.bin b/pytorch_model-00003-of-00019.bin new file mode 100644 index 0000000..68552dc --- /dev/null +++ b/pytorch_model-00003-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6cadd1c4c0d3117f7743f2b7e08f280f11a5c5a712fb881f1a0953c8d18e1cb +size 4983016696 diff --git a/pytorch_model-00004-of-00019.bin b/pytorch_model-00004-of-00019.bin new file mode 100644 index 0000000..6242495 --- /dev/null +++ b/pytorch_model-00004-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a999124b374a5f16aadc6662f32c1d7c8a7bc8c958742f7dca071499ac1df176 +size 4899046246 diff --git a/pytorch_model-00005-of-00019.bin b/pytorch_model-00005-of-00019.bin new file mode 100644 index 0000000..fc2264b --- /dev/null +++ b/pytorch_model-00005-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9beedfe055724d09a83d28131aa14f9bc8bb61c93658ce7e90d1654c60f0e509 +size 4983016648 diff --git a/pytorch_model-00006-of-00019.bin b/pytorch_model-00006-of-00019.bin new file mode 100644 index 0000000..1b0d99c --- /dev/null +++ b/pytorch_model-00006-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efb1318c0ad27b559de333c07254ec269f81fbe87d47e7df9c13e8b557634b94 +size 4983016612 diff --git a/pytorch_model-00007-of-00019.bin b/pytorch_model-00007-of-00019.bin new file mode 100644 index 0000000..8f3e42d --- /dev/null +++ b/pytorch_model-00007-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376d6839cbe1cb9cea919415c97fba86f51d85bb68bc21d103df069e81e391d5 +size 4899046246 diff --git a/pytorch_model-00008-of-00019.bin b/pytorch_model-00008-of-00019.bin new file mode 100644 index 0000000..28657d8 --- /dev/null +++ b/pytorch_model-00008-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ede8207345703b2404c001ce72d0bca982271a49187d658433681edfa8fdec5 +size 4983016736 diff --git a/pytorch_model-00009-of-00019.bin b/pytorch_model-00009-of-00019.bin new file mode 100644 index 0000000..eb49b65 --- /dev/null +++ b/pytorch_model-00009-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65908e7b7d7ce29052a6f4b3e8446f6389eaad8f51351afdf89332bf362a245b +size 4983016676 diff --git a/pytorch_model-00010-of-00019.bin b/pytorch_model-00010-of-00019.bin new file mode 100644 index 0000000..1508230 --- /dev/null +++ b/pytorch_model-00010-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2f12fbc6ee652d1eed0d42068b81503d645c2afe9daceafc7fb28c842de0fd +size 4899046246 diff --git a/pytorch_model-00011-of-00019.bin b/pytorch_model-00011-of-00019.bin new file mode 100644 index 0000000..287cf99 --- /dev/null +++ b/pytorch_model-00011-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a635716855d8aa972526333aa32b00618f36edad50e797f793ddaab827321691 +size 4983016700 diff --git a/pytorch_model-00012-of-00019.bin b/pytorch_model-00012-of-00019.bin new file mode 100644 index 0000000..62ebbba --- /dev/null +++ b/pytorch_model-00012-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828d358f058c95a3ab8ee96d8a689136b90095c2066b6684de9244964041b8b9 +size 4983016700 diff --git a/pytorch_model-00013-of-00019.bin b/pytorch_model-00013-of-00019.bin new file mode 100644 index 0000000..e187ded --- /dev/null +++ b/pytorch_model-00013-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb610d40e391928cf9278d0b7d444770c7953db2b08544df53d8ec754b020de3 +size 4983016676 diff --git a/pytorch_model-00014-of-00019.bin b/pytorch_model-00014-of-00019.bin new file mode 100644 index 0000000..5f065e7 --- /dev/null +++ b/pytorch_model-00014-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61bd5453685b3410500e360ce5de691a6b7ee6e6cf41c6528f424e7d8a0692b +size 4899046246 diff --git a/pytorch_model-00015-of-00019.bin b/pytorch_model-00015-of-00019.bin new file mode 100644 index 0000000..f3cd7a4 --- /dev/null +++ b/pytorch_model-00015-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762687faff8d43ae482dab2bcc2f645921bfe5ec0b99c7bf81424649e292043e +size 4983016736 diff --git a/pytorch_model-00016-of-00019.bin b/pytorch_model-00016-of-00019.bin new file mode 100644 index 0000000..7c9f627 --- /dev/null +++ b/pytorch_model-00016-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b036f338812e3ff3e8c73f9c9106af3e95bcd7c024532a21da255a03c9ab508 +size 4983016676 diff --git a/pytorch_model-00017-of-00019.bin b/pytorch_model-00017-of-00019.bin new file mode 100644 index 0000000..b713685 --- /dev/null +++ b/pytorch_model-00017-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45df28159bdfafb0aa3137a9bb379f7d761c4b0edd65efe6eca8bf418bc7959d +size 4899046246 diff --git a/pytorch_model-00018-of-00019.bin b/pytorch_model-00018-of-00019.bin new file mode 100644 index 0000000..2b8db8d --- /dev/null +++ b/pytorch_model-00018-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60bb42ddb8ac954aeff7b16b40c3e6a1251299d1b8a6c66004b8b22105078f4 +size 4983016712 diff --git a/pytorch_model-00019-of-00019.bin b/pytorch_model-00019-of-00019.bin new file mode 100644 index 0000000..3afe11c --- /dev/null +++ b/pytorch_model-00019-of-00019.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba088f5a08a3ad6f73ecfe678a3e82e3c0dbc064dc80a4993fabb0782b72e8f1 +size 4221689154 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..c105000 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,1002 @@ +{ + "metadata": { + "total_size": 93405585408 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00019-of-00019.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00007-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.28.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00017-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00019-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin", + "model.norm.weight": "pytorch_model-00019-of-00019.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..72ecfee --- /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 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3930c93 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,45 @@ +{ + "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": true, + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}