初始化项目，由ModelHub XC社区提供模型

Model: OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k Source: Original Platform
2026-11-02 20:14:13 +08:00
commit cbda173131
30 changed files with 99645 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/Evaluation.txt
+++ b/Evaluation.txt
--- a/README.md
+++ b/README.md
@@ -0,0 +1,165 @@
+---
+language:
+- zh
+- en
+- fr
+- de
+- ja
+- ko
+- it
+- ru
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+inference: false
+model-index:
+- name: openbuddy-mixtral-7bx8-v18.1-32k
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 67.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 84.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 70.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 56.72
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 80.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 65.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k
+      name: Open LLM Leaderboard
+---
+
+
+# OpenBuddy - Open Multilingual Chatbot
+
+GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
+
+Website and Demo: [https://openbuddy.ai](https://openbuddy.ai)
+
+Evaluation result of this model: [Evaluation.txt](Evaluation.txt)
+
+![Demo](https://raw.githubusercontent.com/OpenBuddy/OpenBuddy/main/media/demo.png)
+
+# Copyright Notice
+
+Base model: https://huggingface.co/mistralai/Mixtral-8x7B-v0.1
+
+License: Apache 2.0
+
+## Disclaimer
+
+All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
+
+OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
+
+By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
+
+
+## 免责声明
+
+所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
+
+OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。
+
+使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OpenBuddy__openbuddy-mixtral-7bx8-v18.1-32k)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.95|
+|AI2 Reasoning Challenge (25-Shot)|67.66|
+|HellaSwag (10-Shot)              |84.30|
+|MMLU (5-Shot)                    |70.94|
+|TruthfulQA (0-shot)              |56.72|
+|Winogrande (5-shot)              |80.98|
+|GSM8k (5-shot)                   |65.13|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "openbuddy-mixtral-7bx8-v18.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "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": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 36608
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0.dev0"
+}
--- a/model-00001-of-00019.safetensors
+++ b/model-00001-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241618c152316fba876ece1fd8d95ad533668cbf046cb7dfe9f962239c390f14
+size 4930558320
--- a/model-00002-of-00019.safetensors
+++ b/model-00002-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1d8c004ca0ca664d243663ee68b6079a2879aceb51c7408c1acdc61a584a0e
+size 4983004016
--- a/model-00003-of-00019.safetensors
+++ b/model-00003-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c4b804bd87b7580d64c17b624e7065026771591e221f1ac7cf3d1280413a96
+size 4983004016
--- a/model-00004-of-00019.safetensors
+++ b/model-00004-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c397569224a0ddc6cb25a86724d221d63ee6a0d8d4c5be4ef606baa358554d8
+size 4899035200
--- a/model-00005-of-00019.safetensors
+++ b/model-00005-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ae0882cacadbdd868e9f9d38bdf8f8ec672522445a157ba23ea15e92b9ff39
+size 4983004016
--- a/model-00006-of-00019.safetensors
+++ b/model-00006-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e8e63c4e2c50482bf5210ebebba62a51cc09d07c63bd4f030219b71533ae39
+size 4983004016
--- a/model-00007-of-00019.safetensors
+++ b/model-00007-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ce46cc8d2cc41f3733a05641a1fa80d9e11d4d6d1da0ce29675938670d520c
+size 4899035248
--- a/model-00008-of-00019.safetensors
+++ b/model-00008-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0fbe35afc868bfd9dc0782310aaf13a09119b0d5afcbe073cd1a80659d89da
+size 4983004072
--- a/model-00009-of-00019.safetensors
+++ b/model-00009-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bef9f2c118ca6a8c1ca864d2f5f7256fcf87232a7fe9a08f9a68ad9d31ec0f
+size 4983004072
--- a/model-00010-of-00019.safetensors
+++ b/model-00010-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e47e2f22264ea1c6277c2a430a5f786986a1b24008ec7d3dae380fe5c766bc
+size 4899035248
--- a/model-00011-of-00019.safetensors
+++ b/model-00011-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6fc90dfdc4775a564a7fe0b3d32dcf77e03eb7737ac2ca7d7e2c4423032e2a
+size 4983004072
--- a/model-00012-of-00019.safetensors
+++ b/model-00012-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6c2147942253f8a643b4cdbe86fbaeb2f059591cebe90497cd49eed5b6ed26
+size 4983004072
--- a/model-00013-of-00019.safetensors
+++ b/model-00013-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6dfcd241458939e24b221adf83739c347decd2361a850816276fda4046990ce
+size 4983004072
--- a/model-00014-of-00019.safetensors
+++ b/model-00014-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f324b1e2026e16d6fded6b70bf86e7c2241c38b25b5bfa4a8d67315eaaba0bed
+size 4899035248
--- a/model-00015-of-00019.safetensors
+++ b/model-00015-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c1b9c098cd188549c1ad8ad84793678dc5e81232dd2b6097940a5f106a9b70
+size 4983004072
--- a/model-00016-of-00019.safetensors
+++ b/model-00016-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd65066020dd3702bbf55bf3e873ad90e691f2d2d0ed63c8c096e25c069a2b13
+size 4983004072
--- a/model-00017-of-00019.safetensors
+++ b/model-00017-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8840a82f9a3c997bfda5b0fbf674aa669472b380003e1fca9144472fe82dc4d
+size 4899035248
--- a/model-00018-of-00019.safetensors
+++ b/model-00018-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c31e73f707583a7e25740cd5cae69e8d68d1bfb7b1b063fa2b0fede38b3699
+size 4983004072
--- a/model-00019-of-00019.safetensors
+++ b/model-00019-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc9b6299db4eb8ff041d886a21910d3ff4e1d11e36dffd8479e83ae558be591
+size 4259427832
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ba60ff0b938f10957218729b4a76b348048c84bdb52fb23902ab3961c424ff
+size 549353
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if loop.last %}{{ 'Assistant: ' + message['content']}}{% else %}{{ 'Assistant: ' + message['content'] + eos_token + '\n' }}{% endif %}{% elif message['role'] == 'system' %}{{ message['content'] + '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ 'Assistant:' }}{% endif %}"
+}
				`@@ -0,0 +1 @@`
				`{"framework":"Pytorch","task":"text-generation"}`