Upload folder using huggingface_hub

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+tags:
+- moe
+- merge
+- mergekit
+- NotAiLOL/Med-Yi-1.5-9B
+- NotAiLOL/Yi-1.5-dolphin-9B
+- NotAiLOL/Yi-1.5-9B-coder
+- NotAiLOL/Math-Yi-1.5-9B
+base_model:
+- NotAiLOL/Med-Yi-1.5-9B
+- NotAiLOL/Yi-1.5-dolphin-9B
+- NotAiLOL/Yi-1.5-9B-coder
+- NotAiLOL/Math-Yi-1.5-9B
+---
+
+# Eclipse-Yi-1.5-4x9b-MoE
+
+Eclipse-Yi-1.5-4x9b-MoE is a Mixture of Experts (MoE) made with the following models:
+* [NotAiLOL/Med-Yi-1.5-9B](https://huggingface.co/NotAiLOL/Med-Yi-1.5-9B)
+* [NotAiLOL/Yi-1.5-dolphin-9B](https://huggingface.co/NotAiLOL/Yi-1.5-dolphin-9B)
+* [NotAiLOL/Yi-1.5-9B-coder](https://huggingface.co/NotAiLOL/Yi-1.5-9B-coder)
+* [NotAiLOL/Math-Yi-1.5-9B](https://huggingface.co/NotAiLOL/Math-Yi-1.5-9B)
+
+## 🧩 Configuration
+
+```yaml
+base_model: 01-ai/Yi-1.5-9B
+gate_mode: hidden
+dtype: bfloat16
+experts:
+    - source_model: NotAiLOL/Med-Yi-1.5-9B
+      positive_prompts:
+      - "explain"
+      - "write"
+    - source_model: NotAiLOL/Yi-1.5-dolphin-9B
+      positive_prompts:
+      - "chat"
+      - "assistant"
+      - "tell me"
+      - "explain"
+      - "I want"
+    - source_model: NotAiLOL/Yi-1.5-9B-coder
+      positive_prompts:
+      - "chat"
+      - "assistant"
+      - "tell me"
+      - "explain"
+      - "I want"
+    - source_model: NotAiLOL/Math-Yi-1.5-9B
+      positive_prompts:
+      - "reason"
+      - "math"
+      - "mathematics"
+      - "solve"
+      - "count"
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "NotAiLOL/Eclipse-Yi-1.5-4x9b-MoE"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.bfloat16, "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": "01-ai/Yi-1.5-9B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

mergekit_moe_config.yml

@@ -0,0 +1,30 @@
+
+base_model: 01-ai/Yi-1.5-9B
+gate_mode: hidden
+dtype: bfloat16
+experts:
+    - source_model: NotAiLOL/Med-Yi-1.5-9B
+      positive_prompts:
+      - "explain"
+      - "write"
+    - source_model: NotAiLOL/Yi-1.5-dolphin-9B
+      positive_prompts:
+      - "chat"
+      - "assistant"
+      - "tell me"
+      - "explain"
+      - "I want"
+    - source_model: NotAiLOL/Yi-1.5-9B-coder
+      positive_prompts:
+      - "chat"
+      - "assistant"
+      - "tell me"
+      - "explain"
+      - "I want"
+    - source_model: NotAiLOL/Math-Yi-1.5-9B
+      positive_prompts:
+      - "reason"
+      - "math"
+      - "mathematics"
+      - "solve"
+      - "count"

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90eec1afa8d9d1033452c6655e1c96c301440cb672ebe0f08eeb42006d37c148
+size 4974519024

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6817e7384d81e467b0e70cdbf8eaa0ee1a3f5ee9f5cfd3279970160789771696
+size 4976633792

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffcacc598837bb5d867582d77afb60cec71be4eaf066a18fa9e73d7933801dd9
+size 4991296952

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3a684e6c5a15f0f24e46d60e5bded3ef91cef220d28ee4fb46d1c3e91619fc
+size 4991296984

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bd37d52bfe8eb38f5507fc4e327d267bfaa4880bbdcfcc5e7eafc467eb799b
+size 4976633872

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22fd21c1296ca49a0f220b1e84b19fa2b0c48076bc2fd3f1e822601389456664
+size 4991296984

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27db5794aa54e4b818b90843cb1e624f15bb44162caf14705198dc578795cb51
+size 4991296984

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9deae584301d0c7d2ae0bbb1ffefeb8db2755f3a6385fe811c924c414026c03
+size 4991305288

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5520de732ed1462b085eacf51d212e07633c7c4e7c4dc7df948cb1fe189f6c7d
+size 4976625568

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85923246d8f32f53dc6cbf299f0c2b09bbedb83f6a2eca4e28dd219c68d83c32
+size 4991296984

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308e92b71f8241718c5dd2469113775391b3843c7a298cb3d5743b8f5a8765f0
+size 4991296984

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82aea7b49a64ddd25844fde2763af1fed7f6e8b06c80215343a0bb1efec0aae
+size 1773699176

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 56617082880}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00012.safetensors", "model.norm.weight": "model-00012-of-00012.safetensors", "lm_head.weight": "model-00012-of-00012.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|startoftext|>",
+  "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|startoftext|>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}