Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+  license: cc-by-nc-4.0
+---
+
+# Yi based  MOE  2x34B with mixtral architecture 
+
+Highest score Model ranked by Open LLM Leaderboard (2024-01-11)
+* [Average Score 76.72](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+
+This is an English & Chinese MoE Model , slightly different with [cloudyu/Mixtral_34Bx2_MoE_60B](https://huggingface.co/cloudyu/Mixtral_34Bx2_MoE_60B), and also based on
+* [jondurbin/bagel-dpo-34b-v0.2]
+* [SUSTech/SUS-Chat-34B]
+
+
+gpu code example
+
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+## v2 models
+model_path = "cloudyu/Yi-34Bx2-MoE-60B"
+
+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/Yi-34Bx2-MoE-60B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+        model_path, torch_dtype=torch.bfloat16, device_map='cpu'
+)
+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 +1,34 @@
+{
+  "_name_or_path": "jondurbin/nontoxic-bagel-34b-v0.2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 200000,
+  "model_type": "mixtral",
+  "num_attention_heads": 56,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.norm.weight": "model-00001-of-00013.safetensors", "lm_head.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.56.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.57.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.58.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.59.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors"}}

output-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9432efb50ecd2e9b6307249fa30630e865988827a22b3935c544fc2b87334c
+size 8589555568

output-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07da3affd70b0d8a31c3080607058ddfaa0fe609502fe33add6efabdf85ff3e2
+size 8583698336

output-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ab89b3b26b99f61fe93e949138a8a93fa6070856d2b9efc2678a666c300cbc
+size 3975865808

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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": "<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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 200000,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}