Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+  license: cc-by-nc-4.0
+---
+
+# Mixtral MOE 5x7B
+
+MoE  of the following models :
+
+* [Toten5/Marcoroni-neural-chat-7B-v1](https://huggingface.co/Toten5/Marcoroni-neural-chat-7B-v1)
+* [NurtureAI/neural-chat-7b-v3-16k](https://huggingface.co/NurtureAI/neural-chat-7b-v3-16k)
+* [mncai/mistral-7b-dpo-v6](https://huggingface.co/mncai/mistral-7b-dpo-v6)
+* [cookinai/CatMacaroni-Slerp](https://huggingface.co/cookinai/CatMacaroni-Slerp)
+* [ignos/Mistral-T5-7B-v1](https://huggingface.co/ignos/Mistral-T5-7B-v1)
+
+
+gpu code example
+
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+## v2 models
+model_path = "cloudyu/Mixtral_7Bx5_MoE_30B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
+)
+print(model)
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
+
+  generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
+  )
+  print(tokenizer.decode(generation_output[0]))
+  prompt = input("please input prompt:")
+```
+
+CPU example
+
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+## v2 models
+model_path = "cloudyu/Mixtral_7Bx5_MoE_30B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False
+)
+print(model)
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+
+  generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
+  )
+  print(tokenizer.decode(generation_output[0]))
+  prompt = input("please input prompt:")
+
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Toten5/Marcoroni-neural-chat-7B-v1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 5,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 5,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.norm.weight": "model-00001-of-00006.safetensors", "lm_head.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors"}}

output-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb45730b2bc95521205cf0ff677261e97319d009b4756613e35ada11be715d34
+size 8569085592

output-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125ba406015973773f6044296eabe36f0fbaba914dd4cec408be94507c4d50ff
+size 8590076468

output-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163d5f8a3df6846403999c725160e8102562d124769342b94ec0264a3226c070
+size 5355012808

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}