Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,2 @@
-*.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
+model-00001-of-00001.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+tags:
+- moe
+- merge
+- mergekit
+- lazymergekit
+- ahxt/LiteLlama-460M-1T
+- ahxt/LiteLlama-460M-1T
+- ahxt/LiteLlama-460M-1T
+- ahxt/LiteLlama-460M-1T
+- ahxt/LiteLlama-460M-1T
+- ahxt/LiteLlama-460M-1T
+---
+
+# KnowledgeNinja-LiteLlama-460Mx6MoE-1T
+
+KnowledgeNinja-LiteLlama-460Mx6MoE-1T is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
+* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
+* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
+* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
+* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
+* [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)
+
+## 🧩 Configuration
+
+```yaml
+base_model: ahxt/LiteLlama-460M-1T
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Accounting"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Finance"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Strategy"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Marketing"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Organizational Behaviour"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Economics"]
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T"
+
+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 +1,35 @@
+{
+  "_name_or_path": "ahxt/LiteLlama-460M-1T",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layernorm_epsilon": 1e-05,
+  "max_position_embeddings": 1024,
+  "model_type": "mixtral",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "num_local_experts": 6,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 50304
+}

mergekit_moe_config.yml

@@ -0,0 +1,18 @@
+
+base_model: ahxt/LiteLlama-460M-1T
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Accounting"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Finance"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Strategy"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Marketing"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Organizational Behaviour"]
+  - source_model: ahxt/LiteLlama-460M-1T
+    positive_prompts: ["Economics"]
+

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198b1c58280bf46417a4f4ec88313589b20c9d64e01b5c0fdc102525bb04d764
+size 3943641472

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "lm_head.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "#",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "\"",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "#",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "#",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}