Upload 15 files

README.md

@@ -0,0 +1,416 @@
+---
+license: cc-by-nc-4.0
+tags:
+- not-for-all-audiences
+- nsfw
+---
+<center>[<a href="https://huggingface.co/Undi95/Dawn-v2-70B">fp16</a> - <a href="https://huggingface.co/Undi95/Dawn-v2-70B-GGUF">gguf</a> - exl2 : <a href="https://huggingface.co/Undi95/Dawn-v2-70B-2.4bpw-h6-exl2">2.40bpw</a> - <a href="https://huggingface.co/Undi95/Dawn-v2-70B-2.55bpw-h6-exl2">2.55bpw</a>]</center>
+</br>
+<div style="width: 100%;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/Cxcfqi4WdtXCNLnaIqSRB.png" style="width: 75%; min-width: 200px; display: block; margin: auto;">
+</div>
+
+<!-- description start -->
+## Description
+
+This repo contains fp16 files of Dawn-70B, a merge I have done with the new [layer shuffle](https://github.com/cg123/mergekit/blob/main/mergekit/scripts/layershuffle.py) method from mergekit.
+
+[UtopiaXL](https://huggingface.co/Undi95/UtopiaXL-13B) was a huge success for me, I really liked it, so I took the same path to do this 70B: A good base, some psychologic data, some medical data, a little bit of this, of that, and LimaRP at the end as always.
+
+NOTE: This repo contain the file  [measurement.json](https://huggingface.co/Undi95/Dawn-v2-70B/blob/main/measurement.json) needed to do your own exl2 quant (I use [wikitext](https://huggingface.co/datasets/wikitext/resolve/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train/0000.parquet)).
+<!-- description end -->
+<!-- description start -->
+## Models and loras used
+
+- [Sao10K/Euryale-1.3-L2-70B](https://huggingface.co/Sao10K/Euryale-1.3-L2-70B)
+- [Xwin-LM/Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1)
+- [ehartford/Samantha-1.11-70b](https://huggingface.co/ehartford/Samantha-1.11-70b)
+- [NousResearch/Nous-Hermes-Llama2-70b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-70b)
+- [augtoma/qCammel-70-x](https://huggingface.co/augtoma/qCammel-70-x)
+- [jondurbin/airoboros-l2-c70b-3.1.2](https://huggingface.co/jondurbin/airoboros-l2-c70b-3.1.2)
+- [fangloveskari/ORCA_LLaMA_70B_QLoRA](https://huggingface.co/fangloveskari/ORCA_LLaMA_70B_QLoRA)
+- [Doctor-Shotgun/limarpv3-llama2-70b-qlora](https://huggingface.co/Doctor-Shotgun/limarpv3-llama2-70b-qlora)
+
+<!-- description end -->
+## The sauce
+```
+!mergekit-layershuffle ./Dawn-v2-70B \
+  --model Sao10K/Euryale-1.3-L2-70B --weight 0.3 \
+  --model Xwin-LM/Xwin-LM-70B-V0.1 --weight 0.2 \
+  --model ehartford/Samantha-1.11-70b --weight 0.1 \
+  --model NousResearch/Nous-Hermes-Llama2-70b --weight 0.05 \
+  --model augtoma/qCammel-70-x --weight 0.05 \
+  --model jondurbin/airoboros-l2-c70b-3.1.2 --weight 0.2 \
+  --model fangloveskari/ORCA_LLaMA_70B_QLoRA --weight 0.1 \
+  --write-yaml Dawn-v2-70B.yaml
+
+=========================
+
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range:
+    - 0
+    - 1
+    model: fangloveskari/ORCA_LLaMA_70B_QLoRA
+- sources:
+  - layer_range:
+    - 1
+    - 2
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 2
+    - 3
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 3
+    - 4
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 4
+    - 5
+    model: fangloveskari/ORCA_LLaMA_70B_QLoRA
+- sources:
+  - layer_range:
+    - 5
+    - 6
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 6
+    - 8
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 8
+    - 9
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 9
+    - 10
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 10
+    - 11
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 11
+    - 12
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 12
+    - 13
+    model: fangloveskari/ORCA_LLaMA_70B_QLoRA
+- sources:
+  - layer_range:
+    - 13
+    - 14
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 14
+    - 15
+    model: fangloveskari/ORCA_LLaMA_70B_QLoRA
+- sources:
+  - layer_range:
+    - 15
+    - 16
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 16
+    - 17
+    model: fangloveskari/ORCA_LLaMA_70B_QLoRA
+- sources:
+  - layer_range:
+    - 17
+    - 18
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 18
+    - 19
+    model: NousResearch/Nous-Hermes-Llama2-70b
+- sources:
+  - layer_range:
+    - 19
+    - 20
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 20
+    - 21
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 21
+    - 22
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 22
+    - 23
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 23
+    - 24
+    model: augtoma/qCammel-70-x
+- sources:
+  - layer_range:
+    - 24
+    - 25
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 25
+    - 27
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 27
+    - 28
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 28
+    - 29
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 29
+    - 30
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 30
+    - 32
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 32
+    - 33
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 33
+    - 34
+    model: augtoma/qCammel-70-x
+- sources:
+  - layer_range:
+    - 34
+    - 35
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 35
+    - 37
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 37
+    - 38
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 38
+    - 39
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 39
+    - 40
+    model: augtoma/qCammel-70-x
+- sources:
+  - layer_range:
+    - 40
+    - 41
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 41
+    - 42
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 42
+    - 43
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 43
+    - 44
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 44
+    - 45
+    model: NousResearch/Nous-Hermes-Llama2-70b
+- sources:
+  - layer_range:
+    - 45
+    - 46
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 46
+    - 48
+    model: ehartford/Samantha-1.11-70b
+- sources:
+  - layer_range:
+    - 48
+    - 49
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 49
+    - 50
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 50
+    - 51
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 51
+    - 54
+    model: fangloveskari/ORCA_LLaMA_70B_QLoRA
+- sources:
+  - layer_range:
+    - 54
+    - 55
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 55
+    - 56
+    model: fangloveskari/ORCA_LLaMA_70B_QLoRA
+- sources:
+  - layer_range:
+    - 56
+    - 58
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 58
+    - 59
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 59
+    - 60
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 60
+    - 62
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 62
+    - 63
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 63
+    - 64
+    model: fangloveskari/ORCA_LLaMA_70B_QLoRA
+- sources:
+  - layer_range:
+    - 64
+    - 65
+    model: NousResearch/Nous-Hermes-Llama2-70b
+- sources:
+  - layer_range:
+    - 65
+    - 66
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 66
+    - 67
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 67
+    - 68
+    model: augtoma/qCammel-70-x
+- sources:
+  - layer_range:
+    - 68
+    - 70
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 70
+    - 71
+    model: augtoma/qCammel-70-x
+- sources:
+  - layer_range:
+    - 71
+    - 72
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 72
+    - 73
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 73
+    - 75
+    model: jondurbin/airoboros-l2-c70b-3.1.2
+- sources:
+  - layer_range:
+    - 75
+    - 76
+    model: Sao10K/Euryale-1.3-L2-70B
+- sources:
+  - layer_range:
+    - 76
+    - 77
+    model: augtoma/qCammel-70-x
+- sources:
+  - layer_range:
+    - 77
+    - 78
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+- sources:
+  - layer_range:
+    - 78
+    - 79
+    model: NousResearch/Nous-Hermes-Llama2-70b
+- sources:
+  - layer_range:
+    - 79
+    - 80
+    model: Xwin-LM/Xwin-LM-70B-V0.1
+
+
+=========================
+
+=> Applying Doctor-Shotgun/limarpv3-llama2-70b-qlora x 0.35
+```
+<!-- prompt-template start -->
+## Prompt template: Alpaca
+
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+{prompt}
+
+### Response:
+
+```
+A big thanks to [Charles](https://huggingface.co/chargoddard) for adding the layer shuffle method to his tool [mergekit](https://github.com/cg123/mergekit/tree/main) and [Henky/KoboldAI](https://koboldai.org/) for the machine he let me use.
+
+If you want to support me, you can [here](https://ko-fi.com/undiai).

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./Dawn-v2-70B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "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": "4.35.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.0.dev0"
+}

huggingface-metadata.txt

@@ -0,0 +1,20 @@
+url: https://huggingface.co/Undi95/Dawn-v2-70B-f16
+branch: main
+download date: 2023-11-07 16:44:55
+sha256sum:
+    5bcd2e92a1a5e606b09379e916a48a91c2c32358bb8c338c988a116c65f4007f pytorch_model-00001-of-00015.bin
+    55dd224dfbbe4ae0a7da66f4923e351c07058aaccebd532e0f5473692067d898 pytorch_model-00002-of-00015.bin
+    6f36547b07184dc01c1d38d006c1ec6d82d891beb6e39e94dc35e40b7153ba3e pytorch_model-00003-of-00015.bin
+    5bf6508ae2d1adc7147999284151c3e691672025245babe0bce4480705e1e0fc pytorch_model-00004-of-00015.bin
+    588507b9793b33e4c489acfe65f2e6ce43bc92eb0ecbcaec8ef6dee9d480c05e pytorch_model-00005-of-00015.bin
+    65ee075742072a47c52cf51f8726420b97035061aec6a7d67c36a9a4cb85bce2 pytorch_model-00006-of-00015.bin
+    238b01c2e9924ebc949975fbd953fa438f0cc5c16ca4bd60b3e108fdf5a16e51 pytorch_model-00007-of-00015.bin
+    b5bb210c80973b35b38ffdbf74fd24fba106cf7c2915788f84942f1852aa782a pytorch_model-00008-of-00015.bin
+    cf84c1658663b31c2660e3e103eb1c25032d958ae4abc9afea199755a7286219 pytorch_model-00009-of-00015.bin
+    5c9386f98ed2fc6bec52d836e7240930dd1018663176cd13cf1aed7114366cc3 pytorch_model-00010-of-00015.bin
+    a947e4fdcd3c354abf196fa169f13a8b238592a1aff08b5e827e61b9ba5e8619 pytorch_model-00011-of-00015.bin
+    f2cbdd615e6aa0bc72c404f366b7fe50b14ce1b737c64208b4f3bc9fbae03f7a pytorch_model-00012-of-00015.bin
+    68ec5541ca583ae65de48aea68e495292d0d2aee5fa3c687d593ecddd22694ff pytorch_model-00013-of-00015.bin
+    85afdf352c069899fb7dbeaa6a15f5f49046845a1b73583b35d7d8ef6fad4577 pytorch_model-00014-of-00015.bin
+    1dd46e4a6e68ba58338bae525bec7a75af6e6de1c4716496d744fd06255131ac pytorch_model-00015-of-00015.bin
+    9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model

model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+    "metadata": {
+        "total_size": 137953296384
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00015-of-00015.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.60.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.60.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.60.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.61.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.input_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.62.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+        "model.layers.63.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.63.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.63.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.63.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.63.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.63.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.63.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.63.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.63.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.64.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.65.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.66.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.input_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.67.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.68.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.68.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.68.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.68.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.68.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.68.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.68.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.68.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.68.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+        "model.layers.69.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.69.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.69.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.69.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.69.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.69.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.69.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.69.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.69.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.70.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.70.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.70.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.70.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.70.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.70.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.70.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.70.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.70.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.71.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.72.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.input_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.73.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.74.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.74.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.74.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.74.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.74.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.74.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.74.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.74.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.74.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+        "model.layers.75.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.75.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.75.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.75.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.75.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.75.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.75.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.75.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.75.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.76.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.77.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.78.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.input_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.79.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+        "model.norm.weight": "model-00014-of-00015.safetensors"
+    }
+}

output-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c140e8cd552d73071000124056f9dc25ef006b9d831a88b10c5915f88410e47a
+size 8541816464

output-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0253e471b795daa45af6b29be520c9f427a004fb7e4ec6c8e2e6b97f7639ef6
+size 8510902224

output-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff9bcebe70014485ed6a90a7fc8848c5f9f33ad826e4f153d7b5b5e3b3e1c60
+size 8565458008

output-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dacc2cd9e43e785b2a55546789d546a2ce0b37ee9b259900ab8bdaa66fdfc19
+size 8558845640

output-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfced8faf9380eaa7f6c39a738b3915fb44c668ef5c8369a53fdc5eb93d8df1a
+size 5998794392

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}