初始化项目，由ModelHub XC社区提供模型

Model: FallenMerick/Chewy-Lemon-Cookie-11B Source: Original Platform
2026-05-18 05:05:00 +08:00
commit 506aa2eac5
15 changed files with 91485 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+Chewy-Lemon-Cookie.png filter=lfs diff=lfs merge=lfs -text
--- a/Chewy-Lemon-Cookie.png
+++ b/Chewy-Lemon-Cookie.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9b74df4a6bdbdc9986ecf1d2878ed2f9741aa258c508f5c88d2457c6ad2ccd
+size 1545081
--- a/README.md
+++ b/README.md
@@ -0,0 +1,186 @@
+---
+language:
+- en
+license: cc-by-4.0
+library_name: transformers
+tags:
+- mergekit
+- merge
+- mistral
+- text-generation
+- roleplay
+base_model:
+- SanjiWatsuki/Kunoichi-7B
+- SanjiWatsuki/Silicon-Maid-7B
+- KatyTheCutie/LemonadeRP-4.5.3
+- Sao10K/Fimbulvetr-11B-v2
+model-index:
+- name: Chewy-Lemon-Cookie-11B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 48.75
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FallenMerick/Chewy-Lemon-Cookie-11B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 33.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FallenMerick/Chewy-Lemon-Cookie-11B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 4.61
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FallenMerick/Chewy-Lemon-Cookie-11B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.91
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FallenMerick/Chewy-Lemon-Cookie-11B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 15.95
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FallenMerick/Chewy-Lemon-Cookie-11B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 25.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FallenMerick/Chewy-Lemon-Cookie-11B
+      name: Open LLM Leaderboard
+---
+
+![cute](https://huggingface.co/FallenMerick/Chewy-Lemon-Cookie-11B/resolve/main/Chewy-Lemon-Cookie.png)
+
+# Chewy-Lemon-Cookie-11B
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+GGUF quants:
+* https://huggingface.co/backyardai/Chewy-Lemon-Cookie-11B-GGUF
+* https://huggingface.co/mradermacher/Chewy-Lemon-Cookie-11B-GGUF
+* https://huggingface.co/mradermacher/Chewy-Lemon-Cookie-11B-i1-GGUF
+
+## Merge Details
+### Merge Method
+
+This model was merged using the following methods:
+* passthrough
+* [task arithmetic](https://arxiv.org/abs/2212.04089)
+
+### Models Merged
+
+The following models were included in the merge:
+* [SanjiWatsuki/Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B)
+* [SanjiWatsuki/Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B)
+* [KatyTheCutie/LemonadeRP-4.5.3](https://huggingface.co/KatyTheCutie/LemonadeRP-4.5.3)
+* [Sao10K/Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
+
+### Configuration
+
+The following YAML configurations were used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: SanjiWatsuki/Kunoichi-7B
+      layer_range: [0, 24]
+  - sources:
+    - model: SanjiWatsuki/Silicon-Maid-7B
+      layer_range: [8, 24]
+  - sources:
+    - model: KatyTheCutie/LemonadeRP-4.5.3
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+name: Big-Lemon-Cookie-11B-BF16
+
+---
+
+models:
+  - model: Big-Lemon-Cookie-11B-BF16
+    parameters:
+      weight: 0.85
+  - model: Sao10K/Fimbulvetr-11B-v2
+    parameters:
+      weight: 0.15
+merge_method: task_arithmetic
+base_model: Big-Lemon-Cookie-11B-BF16
+dtype: bfloat16
+name: Chewy-Lemon-Cookie-11B
+```
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_FallenMerick__Chewy-Lemon-Cookie-11B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.91|
+|IFEval (0-Shot)    |48.75|
+|BBH (3-Shot)       |33.01|
+|MATH Lvl 5 (4-Shot)| 4.61|
+|GPQA (0-shot)      | 3.91|
+|MuSR (0-shot)      |15.95|
+|MMLU-PRO (5-shot)  |25.19|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Chewy-Lemon-Cookie-11B",
+  "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": 8192,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,27 @@
+slices:
+  - sources:
+    - model: SanjiWatsuki/Kunoichi-7B
+      layer_range: [0, 24]
+  - sources:
+    - model: SanjiWatsuki/Silicon-Maid-7B
+      layer_range: [8, 24]
+  - sources:
+    - model: KatyTheCutie/LemonadeRP-4.5.3
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+name: Big-Lemon-Cookie-11B-BF16
+
+---
+
+models:
+  - model: Big-Lemon-Cookie-11B-BF16
+    parameters:
+      weight: 0.85
+  - model: Sao10K/Fimbulvetr-11B-v2
+    parameters:
+      weight: 0.15
+merge_method: task_arithmetic
+base_model: Big-Lemon-Cookie-11B-BF16
+dtype: bfloat16
+name: Chewy-Lemon-Cookie-11B
--- a/model-00001-of-00005.safetensors
+++ b/model-00001-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e891c18863cbf74ae88c80112678d68986e8b2d837855008d2f2ecf3f320c3
+size 4886547008
--- a/model-00002-of-00005.safetensors
+++ b/model-00002-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9279f61488a52dd0f6c9ed67bc1e3465b4c89f037074deed7e70ce8ef1438ce8
+size 4915916176
--- a/model-00003-of-00005.safetensors
+++ b/model-00003-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f63825b720dbfcd685b3f54250175c4f86c0ede54b773a60e12c5e3175c4bae
+size 4915916176
--- a/model-00004-of-00005.safetensors
+++ b/model-00004-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d684d5d1f8bca8339fbf49311aa4698cef70336b69e13b77754e9d6d066a53a
+size 4999819328
--- a/model-00005-of-00005.safetensors
+++ b/model-00005-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbb76eb8aa89ef84c8a4a92568fdf1a925cacb0fbb096fc66dd1723f7b3b277
+size 1744900144
--- 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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}