初始化项目，由ModelHub XC社区提供模型

Model: AI-B/UTENA-7B-V3
Source: Original Platform

.gitattributes

@@ -0,0 +1,8 @@
+model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,24 @@
+This is free and unencumbered software released into the public domain.
+ 
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+ 
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+ 
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, 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.
+ 
+For more information, please refer to <https://unlicense.org>

README.md

@@ -0,0 +1,157 @@
+---
+license: unlicense
+tags:
+- merge
+- mergekit
+- lazymergekit
+- AI-B/UTENA-7B-UNA-V2
+- AI-B/UTENA-7B-NSFW-V2
+model-index:
+- name: UTENA-7B-V3
+  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: 65.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 85.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 64.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 53.64
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 80.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 54.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      name: Open LLM Leaderboard
+---
+
+# UTENA-7B-V3
+
+UTENA-7B-V3 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [AI-B/UTENA-7B-UNA-V2](https://huggingface.co/AI-B/UTENA-7B-UNA-V2)
+* [AI-B/UTENA-7B-NSFW-V2](https://huggingface.co/AI-B/UTENA-7B-NSFW-V2)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: AI-B/UTENA-7B-UNA-V2
+        layer_range: [0, 32]
+      - model: AI-B/UTENA-7B-NSFW-V2
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: AI-B/UTENA-7B-UNA-V2
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+ 
+```
+
+## Quanitized Models
+
+[UTENA-7B-V3-GGUF](https://huggingface.co/s3nh/UTENA-7B-V3-GGUF)
+# [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_AI-B__UTENA-7B-V3)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.42|
+|AI2 Reasoning Challenge (25-Shot)|65.96|
+|HellaSwag (10-Shot)              |85.70|
+|MMLU (5-Shot)                    |64.72|
+|TruthfulQA (0-shot)              |53.64|
+|Winogrande (5-shot)              |80.27|
+|GSM8k (5-shot)                   |54.21|
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "AI-B/UTENA-7B-V3",
+  "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": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: AI-B/UTENA-7B-UNA-V2
+        layer_range: [0, 32]
+      - model: AI-B/UTENA-7B-NSFW-V2
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: AI-B/UTENA-7B-UNA-V2
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbb775c6116ca52cf4012e3287841114a16858d6b385602ca6d9200bd306927
+size 1889595352

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ca0e1c443b6cd5a05fa9a21097a0030887bbf58557c82b741120a150f0592a
+size 1979789712

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464fb08d80120f41a7539651d7e733338f73d3b5b920bd1e938ba3156e049ca9
+size 1988186784

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e3fbaedd29184f53702783c7968ae58cbf031488c987d652d3abb54645b460
+size 1937846944

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c935d87e3e78fa85fdba34d1822b7305188b332d4a2182e4f2f935b7f6654119
+size 1988178496

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbb559d0aa550a9d9dc62ba2ba59f23ae07d9908ef38b3aa4fff07872df4dd0
+size 1998655576

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:588139d1ba1ced6da67ed4679e2d5db9fdc7de1f35b7dd530b7e0c504049abfd
+size 1946235664

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1ef09f2dd79ec6753032f79807814b27989d978de782605aacf3ff8eee5b07
+size 755009456

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_config.json

@@ -0,0 +1,46 @@
+{
+  "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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}