Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- RJuro/munin-neuralbeagle-7b
+- timpal0l/BeagleCatMunin
+- birgermoell/Munin-NeuralBeagle-NorskGPT
+- teknium/OpenHermes-2.5-Mistral-7B
+base_model:
+- RJuro/munin-neuralbeagle-7b
+- timpal0l/BeagleCatMunin
+- birgermoell/Munin-NeuralBeagle-NorskGPT
+- teknium/OpenHermes-2.5-Mistral-7B
+---
+
+# MOE-SWE-DAN-NO-CODE
+
+MOE-SWE-DAN-NO-CODE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [RJuro/munin-neuralbeagle-7b](https://huggingface.co/RJuro/munin-neuralbeagle-7b)
+* [timpal0l/BeagleCatMunin](https://huggingface.co/timpal0l/BeagleCatMunin)
+* [birgermoell/Munin-NeuralBeagle-NorskGPT](https://huggingface.co/birgermoell/Munin-NeuralBeagle-NorskGPT)
+* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
+
+## 🧩 Configuration
+
+```yaml
+base_model: RJuro/munin-neuralbeagle-7b
+dtype: float16
+gate_mode: cheap_embed
+experts:
+  - source_model: RJuro/munin-neuralbeagle-7b
+    positive_prompts: ["You are a helpful Danish assistant."]
+  - source_model: timpal0l/BeagleCatMunin
+    positive_prompts: ["You are a helpful Swedish assistant."]
+  - source_model: birgermoell/Munin-NeuralBeagle-NorskGPT 
+    positive_prompts: ["You are a helpful Norwegian assistant."]
+  - source_model: teknium/OpenHermes-2.5-Mistral-7B
+    positive_prompts: ["You are a helpful coding assistant."]
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "merge-crew/MOE-SWE-DAN-NO-CODE"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "RJuro/munin-neuralbeagle-7b",
+  "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": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+
+  models:
+  - model: danish-foundation-models/munin-7b-alpha
+    # No parameters necessary for base model
+  - model: mlabonne/NeuralBeagle14-7B
+    parameters:
+      density: 0.1
+      weight: 0.6
+  merge_method: dare_ties
+  base_model: danish-foundation-models/munin-7b-alpha
+  parameters:
+    int8_mask: true
+  dtype: bfloat16

mergekit_moe_config.yml

@@ -0,0 +1,13 @@
+
+base_model: RJuro/munin-neuralbeagle-7b
+dtype: float16
+gate_mode: cheap_embed
+experts:
+  - source_model: RJuro/munin-neuralbeagle-7b
+    positive_prompts: ["You are a helpful Danish assistant."]
+  - source_model: timpal0l/BeagleCatMunin
+    positive_prompts: ["You are a helpful Swedish assistant."]
+  - source_model: birgermoell/Munin-NeuralBeagle-NorskGPT 
+    positive_prompts: ["You are a helpful Norwegian assistant."]
+  - source_model: teknium/OpenHermes-2.5-Mistral-7B
+    positive_prompts: ["You are a helpful coding assistant."]

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b5874fca91d7568fbf576944cae994bbef67e2e6ed5fcb5572a646860ad432f
+size 1946219040

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b9ec78b4b930bc40fb56cec005676ee1ad69586024c2a0cc40cdb4780fd7b3
+size 1933849888

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34704de5c80484c8e93e3f5504944a2169e77ceb2654457477b0a24eea293b2a
+size 1946243920

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e49d3f58407be928e9a7bd22790e09ab41601b88f71a57469e406723f72341
+size 1996490936

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f679e310ac18d9d29d69bc1812222d8af63947fc18e8943e62f63a0f45eb554
+size 1889587064

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0beb281489d08fb533129ddc040512a895a4578545136c446c329af1dc3c9148
+size 1996490936

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2bb60bf51749064f4552f1f992314da0322a4d36c39a5ef9866d71ec573f86
+size 1946243960

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70522c846de79bf99d502ad897f656a57c84714c7c305d0213c3a55512465507
+size 1996490952

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd7cf9e09832624736adcaae2a9be5f8d4a01dfc5a64b991c6c5e52da5cc18a
+size 1979781456

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36bdc627a601a07fb57456c9dd6dc88616a15ebb2634a1a517b1fda94610147
+size 1996490952

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357640e402f848fed5c5a3181f83329e182a5afbec54780319ca38dac511af1a
+size 1889628568

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd13b2ca67dff02a25bbba3d01a21cfdfbb66be6d731bd6d2575e736cedc0a6
+size 1996490952

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad625fbac462f39d8f36c63ed1bc06d9738bdf90a69c6a8a2ee6e4885c890a3
+size 1979781456

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ad108525793b1043d338a78aef911d3f092afe0dc2d14f4b9cd10d84347a4c
+size 1996490952

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360028648cc12c6ef105415add6b70ea3dc4340743dfa09f9eae84357163024b
+size 906012472

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8087bb44f9f0882651b2767a36671cc983dcda68791aba1aa252f1f6233773b
+size 1996490944

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798cd9ee7ec43ec01496beac5b9c0021f43ec83f530e65992710b66eec32f8b1
+size 1996490936

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c48d21c34972aaf3f95c4b47f489761535880284705bea1fc63bcdeb5fc7368
+size 1996490936

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54337f1c646358ee14a77ed097daeb5b8dfda0f383e751b11093c71eb185e88
+size 1996490944

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03cff5a0af7c54a35fbbcef6457f64c73345dff5503cd5cb91b1d2314665d11
+size 1996490952

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef5240212fcf8c2608c8ce5d4244dd1bd40b02d8db59a725fb427d475cc0e44
+size 1996490952

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb9739c1e205e49698fe1729bb881ee06f30d17797d0613d0c5c5885e3ddec8
+size 1996490952

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0500f97eb42f23c9a0e4bde961283d42b0c569d02aeb3ade91af2dcba4dd8d3
+size 1996490952

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8151a347b189303e704a0a48204c448b95f194b8fb42507444584d74e5054078
+size 1996490936

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c15ab3200b927296dda403dc649ebb3bd11df9593c03e62b55d632b4fb3bf04b
+size 1996490936

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2274faac53605b3a973f477858968fd3552225d49bd11d6d584c4b35b9e91a62
+size 1996490936

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d429245d866485d98a2e10d6ef83511f5d5b96bd559e7e2d21a8fe3b9c652e96
+size 1996490952

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c48f448ed5fd27c4d5bcbd603a4d873f4d5e0a56dcf30b83f6565591958c48
+size 1996490952

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ba9953ba08052d7f15ef86524f911396466790f83c2815a9b77cd8ad3f3b1d
+size 1996490952

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890c38e41162bac9b752077795938b8a8c6e3b73211d9966ca529e9ec5fe5633
+size 1996490952

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7147cc0650a2cf6f6feea4f5b8211bb68d7877ac91e81307fb115e15ab3728
+size 1996757384

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8654b21b2d011d83745caef0f01abacddaaab9d8918261e6c5f66bac56b5b56
+size 1979723896

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d547dbc9cb777b975800497233aedf15eff02558787f2ea57117fc1b6fb2eb
+size 470815920

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00025.safetensors", "model.norm.weight": "model-00001-of-00025.safetensors", "lm_head.weight": "model-00001-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}