初始化项目，由ModelHub XC社区提供模型

Model: NeverSleep/Noromaid-20b-v0.1.1
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+license: cc-by-nc-4.0
+---
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/VKX2Z2yjZX5J8kXzgeCYO.png)
+
+
+---
+
+# Disclaimer:
+## This is a ***TEST*** version, don't expect everything to work!!!
+
+You may use our custom **prompting format**(scroll down to download them!), or simple alpaca. **(Choose which fits best for you!)**
+
+---
+
+
+# This model is a collab between [IkariDev](https://huggingface.co/IkariDev) and [Undi](https://huggingface.co/Undi95)!
+
+Tired of the same merges everytime? Here it is, the Noromaid-20b-v0.1.1 model. Suitable for RP, ERP and general stuff.
+
+[Recommended settings - No settings yet(Please suggest some over in the Community tab!)]
+
+<!-- description start -->
+## Description
+
+<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
+
+This repo contains fp16 files of Noromaid-20b-v0.1.1.
+
+[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-20b-v0.1.1)
+
+<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)-->
+
+<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)-->
+
+<!-- [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)-->
+
+<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)-->
+
+<!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)-->
+
+[GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-20b-v0.1.1-GGUF)
+<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->
+
+## Ratings:
+
+Note: We have permission of all users to upload their ratings, we DONT screenshot random reviews without asking if we can put them here!
+
+No ratings yet!
+
+If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".
+
+<!-- description end -->
+<!-- prompt-template start -->
+## Prompt template: Custom format, or Alpaca
+
+### Custom format:
+UPDATED!! SillyTavern config files: [Context](https://files.catbox.moe/ifmhai.json), [Instruct](https://files.catbox.moe/ttw1l9.json).
+OLD SillyTavern config files: [Context](https://files.catbox.moe/x85uy1.json), [Instruct](https://files.catbox.moe/ttw1l9.json).
+
+### Alpaca:
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+{prompt}
+
+### Response:
+
+```
+
+## Training data used:
+- [no_robots dataset](https://huggingface.co/Undi95/Llama2-13B-no_robots-alpaca-lora) let the model have more human behavior, enhances the output.
+- [Aesir Private RP dataset] New data from a new and never used before dataset, add fresh data, no LimaRP spam, this is 100% new. Thanks to the [MinvervaAI Team](https://huggingface.co/MinervaAI) and, in particular, [Gryphe](https://huggingface.co/Gryphe) for letting us use it!
+
+## Others
+
+Undi: If you want to support me, you can [here](https://ko-fi.com/undiai).
+
+IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "./merge1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": false
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f77bd3e2f249ff073a62e7b416120cd3ddaa378bb82dfd6ba651b60d61202f
+size 4978265728

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a394e1e82230dae15c5c7b1273376f45e01b830d8a43de534b30a2015a2e71bd
+size 4970422160

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9810c4cd42084652a36ecf8d83f029266c5e63a411f6777fffd0434fdb310de
+size 4970422184

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3c1b00a1943f547fedfcdfc51518772658da1105150768d06661704a5e29fb
+size 4933701432

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37cf11f74924bfdb59c8dcb0f6d6ccfa312b6fb6086e9c7cb70f2902434b4f4e
+size 4933722144

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4412dd55aa090ad670e7d986340313fab9ad5b45863a0b9045df7d7efa7b422
+size 4933722136

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72867e39858e785cf4da4bb0f1313892984550175ebda46e803f93dbcd3c5be7
+size 4970422184

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9394514a0beb0d93e9cead7e27b516dc8fa799e80dffd5273dd066f314f330e
+size 4970432512

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873f7851f9c802a346cef0a1ae3945698da27df44ed1e5b0df4bf978021aa487
+size 327680128

model.safetensors.index.json

@@ -0,0 +1,568 @@
+{
+  "metadata": {
+    "total_size": 39988725760
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.norm.weight": "model-00008-of-00009.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}