Upload folder using huggingface_hub

README.md

@@ -0,0 +1,133 @@
+---
+license: cc-by-4.0
+datasets:
+- Open-Orca/OpenOrca
+- Intel/orca_dpo_pairs
+language:
+- en
+tags:
+- xDAN-AI
+- OpenOrca
+- DPO
+- Self-Think
+---
+
+<div style="display: flex; justify-content: center; align-items: center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/643197ac288c9775673a01e9/tVAcwKkIH5vkfzqgqHeHi.png" style="width: 45%;">
+</div
+>
+
+
+<p align="center">
+  <big><b>Top 1 Performer on MT-bench🏆</b
+></big>
+</p>
+
+<p align="center">
+  <strong>**The first top model which is performance at Humanalities, Coding and Writing with 7b. **</strong>
+</p>
+
+<p
+ align="center"
+  <a href="The TOP1 MT-Bench Model">xDAN-AI</a> •
+>
+  <a href="https://discord.gg/7NrMX5AK">Discord</a> •
+  <a href="https://twitter.com/shootime007">Twitter</a> •
+  <a href="https://huggingface.co/xDAN-AI">Huggingface</a>
+</p>
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/643197ac288c9775673a01e9/QANDZApzpTHM6sBsjmdew.png" alt="Image" width="50%">
+</p>
+
+
+
+## Outperformer GPT3.5turbo & Claude-v1
+
+![image/png
+](https://cdn-uploads.huggingface.co/production/uploads/643197ac288c9775673a01e9/c9btBdopOpM06VuBsvRxq.png)
+
+## Touch nearby GPT4 on MT-Bench
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/643197ac288c9775673a01e9/QhcLDoOGZznkvy0v4FsUY.png)
+
+
+**########## First turn ##########**
+| model              | turn | score    | size
+|--------------------|------|----------|--------
+| gpt-4              | 1    | 8.95625  |  -
+| **xDAN-L1-Chat-RL-v1** | 1    | **8.87500**  |  **7b**
+| xDAN-L2-Chat-RL-v2 | 1    | 8.78750  |  30b
+| claude-v1          | 1    | 8.15000  |  -
+| gpt-3.5-turbo      | 1    | 8.07500  |  20b
+| vicuna-33b-v1.3    | 1    | 7.45625  |  33b
+| wizardlm-30b       | 1    | 7.13125  |  30b
+| oasst-sft-7-llama-30b | 1 | 7.10625  |  30b
+| Llama-2-70b-chat   | 1    | 6.98750  |  70b
+
+
+########## Second turn ##########
+| model              | turn | score     | size
+|--------------------|------|-----------|--------
+| gpt-4              | 2    | 9.025000  |  -
+| xDAN-L2-Chat-RL-v2 | 2    | 8.087500  |  30b
+| **xDAN-L1-Chat-RL-v1** | 2   | **7.825000**  |   **7b**
+| gpt-3.5-turbo      | 2    | 7.812500  |  20b
+| claude-v1          | 2    | 7.650000  |  -
+| wizardlm-30b       | 2    | 6.887500  |  30b
+| vicuna-33b-v1.3    | 2    | 6.787500  |  33b
+| Llama-2-70b-chat   | 2    | 6.725000  |  70b
+
+########## Average turn##########
+| model              | score     | size
+|--------------------|-----------|--------
+| gpt-4              | 8.990625  |  -
+| xDAN-L2-Chat-RL-v2 | 8.437500  |  30b
+| **xDAN-L1-Chat-RL-v1** | **8.350000**  |  **7b**
+| gpt-3.5-turbo      | 7.943750  |  20b
+| claude-v1          | 7.900000  |  -
+| vicuna-33b-v1.3    | 7.121875  |  33b
+| wizardlm-30b       | 7.009375  |  30b
+| Llama-2-70b-chat   | 6.856250  |  70b
+
+
+## LM-Evaluation-Harness
+
+| Task         | Score  |
+|--------------|--------|
+| Average | 68.38  |
+| ARC     | 66.3  |
+| HellaSwag        | 85.81  |
+| MMLU    | 63.21  |
+| TruthfulQA   | 56.7   |
+| Winogrande         | 78.85  |
+| GSM8K   | 59.44  |
+
+
+
+
+### Prompt Template(Alpaca)
+You are a helpful assistant named DAN. You are an expert in worldly knowledge, skilled in employing a probing questioning strategy, 
+and you carefully consider each step before providing answers. 
+\n\n### Instruction:\n{instruction}\n\n### Response:
+
+
+### Dataset:
+1. Selected from OpenOrca
+2. Intel Orca-DPO-Pairs
+3. Privately Crafted Dataset
+
+### Training:
+1. SFT with Mixed dataset from OpenOrca & Intel
+2. The DPO-v2 dataset  
+3. The DPO-v2 Trainer
+
+## Created By xDAN-AI at 2023-12-15
+## Eval by FastChat: https://github.com/lm-sys/FastChat.git
+
+ 
+## Disclaimer
+We employ rigorous data compliance validation algorithms throughout the training of our language model to ensure the highest level of compliance. However, due to the intricate nature of data and the wide range of potential usage scenarios for the model, we cannot guarantee that it will consistently produce accurate and sensible outputs. Users should be aware of the possibility of the model generating problematic results. Our organization disclaims any responsibility for risks or issues arising from misuse, improper guidance, unlawful usage, misinformation, or subsequent concerns regarding data security.
+
+## About xDAN-AI
+xDAN-AI represents the forefront of Silicon-Based Life Factory technology. For comprehensive information and deeper insights into our cutting-edge technology and offerings, please visit our website: https://www.xdan.ai.

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "xDAN-AI/xDAN-L1-Chat-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a307814660c91ec79856c4173c36ec55f996234ba4ab467a82f1bfe25ea0cb
+size 926941888

model-00002-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e200e47428a0d926131e8859c5088492fa12e4230f17e138528e13b849613986
+size 872449040

model-00003-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0604b828b8630360ef792cb0ce402e78cfe83c3bc13e19980d8ad8c6d098f11
+size 872449040

model-00004-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eea35c11dd08dd5c0adb22409321b2ef8b27348436e6452ed11f8b1d0c365c4
+size 872449040

model-00005-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf324bc0a538ebb36c71c712a483299d227d10cf139573b3b66e48a2ce9eb82
+size 872449040

model-00006-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12e2d8ca79334f1ab74eaf530d9a3a72cb8b265b66dfc7a431b06f81a7b94c1
+size 872449040

model-00007-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1615ee6e8fe82031db9de898f414502bacc1412bfb908ccdb94294bf254cf39c
+size 872449040

model-00008-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7eb1ac1de06ed4526c0944be5d6fbb200b207f01d86669e39143f6a5ee9d76c
+size 872449040

model-00009-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82cc11213e23ba6fec7e4e845d855435afdffeba0443735648dc5dc3cddbd970
+size 872449040

model-00010-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2654bff8d04483f0001c21f36adbf497b355b8dc890fb09ff5da565faf5c8aad
+size 872449040

model-00011-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da290ec3b38f97c75ef844afa47ced3b415ef03c605b5154747c79f7e71c9cd
+size 872449056

model-00012-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81cc81b55f5e6f80cad6aa0e64c2aa77b8bd8f5b003bc0442c75ae25d1b881d9
+size 872449048

model-00013-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4eef0a1ff4f8029d27eaa8cb0d8a7866a3193b24436add8a63b8dd3c1284752
+size 872449048

model-00014-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf91f999869d58c7bd1c4742cb07526b9c18143636442c5ee56a2d9ebb47ab1
+size 872449048

model-00015-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6290f0a75cbcfb03427c375b8c33514f5e4d50f53f3f7f85c9a976f44113a778
+size 872449048

model-00016-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2cef2ceb449f5a4bce7fcda752858e7778ac4fd207561a007d9eb6b78b99e4
+size 872449048

model-00017-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0683d84f3bb21b8570f1a8e09684d816c2b281d3b1fc613ff6b5a3670d46ab9c
+size 872449048

model-00018-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614635564b26e4422eed341acca60e860d5c8ba3d3d253aca5edc0c6eccd2250
+size 872449048

model-00019-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d3bb7fe5c8d757b90279cbd2e21994eaf3fa940960874491f329b20e0c2d44
+size 872449048

model-00020-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b523241fca07cf9dc88727ec3f36b61f2d630f60eab5b546dd0014e98a968b5f
+size 872449048

model-00021-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aaffb24c91839e0d5d86010baa437479f6bb116a4d95494412e4edb8a63fb26
+size 872449048

model-00022-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152a12815e74cb552fb2fa6b6551819a616824ec57c6f58d62a7ffee295801d9
+size 872449048

model-00023-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87fbd0d7912d688d170c918d17096d4eb90034b8570c6336067cc3f0bb648760
+size 872449048

model-00024-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6411dc7d1e4b7e92026f9fe80a3894303798c6f63eed43c174daf29d98edb1e2
+size 872449048

model-00025-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c9d3207bc33e96f9fe1bb18c818137dbc6ddd589f43c18fdcd076dfdf30c95
+size 872449048

model-00026-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9877545d6e7f68027d6551b61cc77922051e8767236087a60c9360c844750297
+size 872449048

model-00027-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc103014cf5ae9e810140de2c1244a8f4e476e8367b3712e71458560ffe3767
+size 872449048

model-00028-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01d5dc3065cb6bfd24c826fa9730e52c3e037cd1222760fd60b97046a5ff96e
+size 872449048

model-00029-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369238dc9585bcef18b1119a2a24bc2fbc09c4fa6bcf859eb651f5c2ab6079b3
+size 872449048

model-00030-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59224c4cf6d13a8eb2c5a5c19cbc7d8fea77ec2579f4102459bcea9f3a94ff1b
+size 872449048

model-00031-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d8ee6da6259ed528e3aa0438e9d286a639d08f89dc58be4213b536a6e804c0
+size 872449048

model-00032-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32351ca8c2023aefc73ea5a672cab492df0c850725bd08d3c068eacd5df71760
+size 872449048

model-00033-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41adb0f48b3494a5408cb506c48de7dfef447f6b017e668f96cdf9fbd9293c74
+size 994099864

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 28966928384
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00033-of-00033.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00033.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00033.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00033.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00033.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00033.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00033.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00033.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00033.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00033.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00033.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00033.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00033.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00033.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00033.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00033.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00033.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00033.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00033.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00033.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00012-of-00033.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00012-of-00033.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00011-of-00033.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00012-of-00033.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00033.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00033.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00033.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00033.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00033.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00013-of-00033.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00013-of-00033.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00012-of-00033.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00013-of-00033.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00033.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00033.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00033.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00033.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00033.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00014-of-00033.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00014-of-00033.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00013-of-00033.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00014-of-00033.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00033.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00033.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00033.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00033.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00033.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00015-of-00033.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00015-of-00033.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00014-of-00033.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00015-of-00033.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00033.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00033.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00033.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00033.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00033.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00016-of-00033.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00016-of-00033.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00015-of-00033.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00016-of-00033.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00033.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00033.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00033.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00033.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00033.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00017-of-00033.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00017-of-00033.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00016-of-00033.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00017-of-00033.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00033.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00033.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00033.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00033.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00033.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00018-of-00033.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00018-of-00033.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00017-of-00033.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00018-of-00033.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00033.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00033.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00033.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00033.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00033.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00019-of-00033.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00019-of-00033.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00018-of-00033.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00019-of-00033.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00033.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00033.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00033.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00033.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00033.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00020-of-00033.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00020-of-00033.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00019-of-00033.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00020-of-00033.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00033.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00033.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00033.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00033.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00033.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00021-of-00033.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00021-of-00033.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00020-of-00033.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00021-of-00033.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00033.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00033.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00033.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00033.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00033.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00033.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00033.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00033.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00033.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00033.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00033.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00033.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00033.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00033.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00022-of-00033.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00022-of-00033.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00021-of-00033.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00022-of-00033.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00033.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00033.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00033.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00033.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00033.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00023-of-00033.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00023-of-00033.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00022-of-00033.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00023-of-00033.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00033.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00033.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00033.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00033.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00033.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00024-of-00033.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00024-of-00033.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00023-of-00033.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00024-of-00033.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00033.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00033.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00033.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00033.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00033.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00025-of-00033.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00025-of-00033.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00024-of-00033.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00025-of-00033.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00033.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00033.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00033.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00033.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00033.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00026-of-00033.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00026-of-00033.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00025-of-00033.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00026-of-00033.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00026-of-00033.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00033.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00033.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00033.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00033.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00027-of-00033.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00027-of-00033.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00026-of-00033.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00027-of-00033.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00027-of-00033.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00033.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00033.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00033.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00033.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00028-of-00033.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00028-of-00033.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00027-of-00033.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00028-of-00033.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00028-of-00033.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00033.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00033.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00033.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00033.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00029-of-00033.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00029-of-00033.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00028-of-00033.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00029-of-00033.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00029-of-00033.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00033.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00033.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00033.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00033.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00030-of-00033.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00030-of-00033.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00029-of-00033.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00030-of-00033.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00030-of-00033.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00033.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00033.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00033.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00033.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00031-of-00033.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00031-of-00033.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00030-of-00033.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00031-of-00033.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00031-of-00033.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00033.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00033.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00033.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00033.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00005-of-00033.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00005-of-00033.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00033.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00005-of-00033.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00033.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00033.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00033.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00033.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00033.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00032-of-00033.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00032-of-00033.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00031-of-00033.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00032-of-00033.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00032-of-00033.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00033.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00033.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00033.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00033.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00033-of-00033.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00033-of-00033.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00032-of-00033.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00033-of-00033.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00033-of-00033.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00033.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00033.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00033.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00033.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00006-of-00033.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00006-of-00033.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00033.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00006-of-00033.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00033.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00033.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00033.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00033.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00033.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00007-of-00033.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00007-of-00033.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00033.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00007-of-00033.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00033.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00033.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00033.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00033.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00033.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00008-of-00033.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00008-of-00033.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00033.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00008-of-00033.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00033.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00033.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00033.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00033.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00033.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00009-of-00033.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00009-of-00033.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00033.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00009-of-00033.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00033.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00033.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00033.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00033.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00033.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00010-of-00033.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00010-of-00033.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00033.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00010-of-00033.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00033.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00033.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00033.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00033.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00033.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00011-of-00033.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00011-of-00033.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00033.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00011-of-00033.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00033.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00033.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00033.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00033.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00033.safetensors",
+    "model.norm.weight": "model-00033-of-00033.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}