Upload folder using huggingface_hub

.gitattributes

@@ -4,3 +4,6 @@ model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
 model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
 model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
 model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,62 +1,56 @@
 ---
-license: apache-2.0
 tags:
-- moe
-- frankenmoe
 - merge
 - mergekit
 - lazymergekit
-- Crystalcareai/CrystalMistral
-- Crystalcareai/CrystalMistral
+- eren23/dpo-binarized-NeuralTrix-7B
+- eren23/dpo-binarized-NeuralTrix-7B
 base_model:
-- Crystalcareai/CrystalMistral
-- Crystalcareai/CrystalMistral
+- eren23/dpo-binarized-NeuralTrix-7B
+- eren23/dpo-binarized-NeuralTrix-7B
 ---
 
-# CrystalMistral-13b
+# Crystalmistral-13b
 
-CrystalMistral-13b is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [Crystalcareai/CrystalMistral](https://huggingface.co/Crystalcareai/CrystalMistral)
-* [Crystalcareai/CrystalMistral](https://huggingface.co/Crystalcareai/CrystalMistral)
+Crystalmistral-13b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [eren23/dpo-binarized-NeuralTrix-7B](https://huggingface.co/eren23/dpo-binarized-NeuralTrix-7B)
+* [eren23/dpo-binarized-NeuralTrix-7B](https://huggingface.co/eren23/dpo-binarized-NeuralTrix-7B)
 
 ## 🧩 Configuration
 
 ```yaml
-base_model: Crystalcareai/CrystalMistral
-gate_mode: random
-dtype: bfloat16 
-experts_per_token: 2
-experts:
-  - source_model: Crystalcareai/CrystalMistral
-    positive_prompts:
-      - "You are an helpful general-purpose assistant."
-
-  - source_model: Crystalcareai/CrystalMistral
-    positive_prompts:
-      - "You are an expert in providing detailed technical explanations."
-
+slices:
+  - sources:
+      - model: eren23/dpo-binarized-NeuralTrix-7B
+        layer_range: [0, 32]
+  - sources:
+      - model: eren23/dpo-binarized-NeuralTrix-7B
+        layer_range: [0, 32]
+merge_method: passthrough
+dtype: float16
 ```
 
 ## 💻 Usage
 
 ```python
-!pip install -qU transformers bitsandbytes accelerate
+!pip install -qU transformers accelerate
 
 from transformers import AutoTokenizer
 import transformers
 import torch
 
-model = "Crystalcareai/CrystalMistral-13b"
+model = "Crystalcareai/Crystalmistral-13b"
+messages = [{"role": "user", "content": "What is a large language model?"}]
 
 tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 pipeline = transformers.pipeline(
     "text-generation",
     model=model,
-    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+    torch_dtype=torch.float16,
+    device_map="auto",
 )
 
-messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
-prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
 ```

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "Crystalcareai/Crystalmistral-13B",
+  "_name_or_path": "eren23/dpo-binarized-NeuralTrix-7B",
   "architectures": [
-    "MixtralForCausalLM"
+    "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
@@ -11,20 +11,16 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 32768,
-  "model_type": "mixtral",
+  "model_type": "mistral",
   "num_attention_heads": 32,
-  "num_experts_per_tok": 2,
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 64,
   "num_key_value_heads": 8,
-  "num_local_experts": 2,
-  "output_router_logits": false,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "router_aux_loss_coef": 0.001,
-  "sliding_window": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 32000
 }

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+slices:
+  - sources:
+      - model: eren23/dpo-binarized-NeuralTrix-7B
+        layer_range: [0, 32]
+  - sources:
+      - model: eren23/dpo-binarized-NeuralTrix-7B
+        layer_range: [0, 32]
+merge_method: passthrough
+dtype: float16

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916f357b0ffc62c4318aa57b8b5c7e775fe75e6ee79417da4f42c39bcb862a21
+size 9909394184

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2626ff07643c1d820c6875844a34db4d7ddedd44740ba50e5ace4119dbf06bb1
+size 9976577160

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389b0ee24203f9783a4370c89c65ada949c77aa71079b7c1ffcb942b2675e072
+size 8556727736

model.safetensors.index.json

@@ -1,426 +1 @@
-{
-  "metadata": {
-    "total_size": 25758277632
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00006-of-00006.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.block_sparse_moe.experts.0.w2.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.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.block_sparse_moe.experts.1.w2.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.gate.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.block_sparse_moe.experts.0.w2.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.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.block_sparse_moe.experts.1.w2.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.gate.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-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.0.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.block_sparse_moe.experts.0.w2.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.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.block_sparse_moe.experts.1.w2.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.gate.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.20.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.block_sparse_moe.experts.0.w1.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.0.w3.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.block_sparse_moe.experts.1.w1.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.1.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.block_sparse_moe.experts.0.w2.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.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.block_sparse_moe.experts.1.w2.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.gate.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00005-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.0.w2.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.block_sparse_moe.experts.0.w3.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.1.w2.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.block_sparse_moe.experts.0.w2.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.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.block_sparse_moe.experts.1.w2.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.gate.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.block_sparse_moe.experts.0.w2.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.w1.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.block_sparse_moe.experts.1.w2.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.gate.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.norm.weight": "model-00006-of-00006.safetensors"
-  }
-}
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.42.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", "lm_head.weight": "model-00002-of-00003.safetensors", "model.norm.weight": "model-00002-of-00003.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors"}}

special_tokens_map.json

@@ -13,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -29,12 +27,11 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<s>",
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",