初始化项目，由ModelHub XC社区提供模型

Model: jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES Source: Original Platform
2026-05-08 15:18:58 +08:00
commit 6983cd49a1
17 changed files with 91493 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/README.md
+++ b/README.md
@@ -0,0 +1,169 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- FelixChao/WestSeverus-7B-DPO-v2
+- CultriX/Wernicke-7B-v9
+- mlabonne/NeuralBeagle14-7B
+model-index:
+- name: RandomMergeNoNormWEIGHTED-7B-DARETIES
+  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: 73.38
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES
+      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: 88.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES
+      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: 64.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES
+      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: 71.5
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES
+      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: 83.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES
+      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: 70.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES
+      name: Open LLM Leaderboard
+---
+
+
+# RandomMergeNoNormWEIGHTED-7B-DARETIES
+
+RandomMergeNoNormWEIGHTED-7B-DARETIES is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [FelixChao/WestSeverus-7B-DPO-v2](https://huggingface.co/FelixChao/WestSeverus-7B-DPO-v2)
+* [CultriX/Wernicke-7B-v9](https://huggingface.co/CultriX/Wernicke-7B-v9)
+* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: FelixChao/WestSeverus-7B-DPO-v2
+    # No parameters necessary for base model
+  - model: FelixChao/WestSeverus-7B-DPO-v2
+    parameters:
+      density: [1, 0.7, 0.1]
+      weight: [0, 0.3, 0.7, 1]
+  - model: CultriX/Wernicke-7B-v9
+    parameters:
+      density: [1, 0.7, 0.3]
+      weight: [0, 0.25, 0.5, 1]
+  - model: mlabonne/NeuralBeagle14-7B
+    parameters:
+      density: 0.25
+      weight:
+        - filter: mlp
+          value: 0.5
+        - value: 0
+merge_method: ties
+base_model: FelixChao/WestSeverus-7B-DPO-v2
+parameters:
+  int8_mask: true
+  normalize: true
+  sparsify:
+    - filter: mlp
+      value: 0.5
+    - filter: self_attn
+      value: 0.5
+dtype: float16
+
+```
+# [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_jsfs11__RandomMergeNoNormWEIGHTED-7B-DARETIES)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.36|
+|AI2 Reasoning Challenge (25-Shot)|73.38|
+|HellaSwag (10-Shot)              |88.50|
+|MMLU (5-Shot)                    |64.94|
+|TruthfulQA (0-shot)              |71.50|
+|Winogrande (5-shot)              |83.58|
+|GSM8k (5-shot)                   |70.28|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FelixChao/WestSeverus-7B-DPO-v2",
+  "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,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,31 @@
+
+models:
+  - model: FelixChao/WestSeverus-7B-DPO-v2
+    # No parameters necessary for base model
+  - model: FelixChao/WestSeverus-7B-DPO-v2
+    parameters:
+      density: [1, 0.7, 0.1]
+      weight: [0, 0.3, 0.7, 1]
+  - model: CultriX/Wernicke-7B-v9
+    parameters:
+      density: [1, 0.7, 0.3]
+      weight: [0, 0.25, 0.5, 1]
+  - model: mlabonne/NeuralBeagle14-7B
+    parameters:
+      density: 0.25
+      weight:
+        - filter: mlp
+          value: 0.5
+        - value: 0
+merge_method: ties
+base_model: FelixChao/WestSeverus-7B-DPO-v2
+parameters:
+  int8_mask: true
+  normalize: true
+  sparsify:
+    - filter: mlp
+      value: 0.5
+    - filter: self_attn
+      value: 0.5
+dtype: float16
+
--- a/model-00001-of-00008.safetensors
+++ b/model-00001-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7d5766789e16aaf9dfd003377fdbcc3a2199b4a80e5f556f1cd54a4648bbd1
+size 1946219000
--- a/model-00002-of-00008.safetensors
+++ b/model-00002-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ac82150909923e1259a61a91d789d2d56b2f239e88910a21656ed67b8bc70d
+size 1946243880
--- a/model-00003-of-00008.safetensors
+++ b/model-00003-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6affb481f1d6aa11240379c85169360cd50a8c63918a601a6915eed39c2f85d
+size 1889587024
--- a/model-00004-of-00008.safetensors
+++ b/model-00004-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c095223218b217c077293aeef862022b1a2cd163b3f323741045f5994f740b
+size 1946243920
--- a/model-00005-of-00008.safetensors
+++ b/model-00005-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:521daa739e689f56bbd388294ea6331de3db40f7f673fa99e12420e7eb68df85
+size 1979781416
--- a/model-00006-of-00008.safetensors
+++ b/model-00006-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd40aeccaca5981973e2dd31ebd0df9ed286313bce3e362090a9cc59c859472
+size 1889628528
--- a/model-00007-of-00008.safetensors
+++ b/model-00007-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d807ad36061195b9bbf27805530d65b03718d63b5aedf2b563905691b38f4359
+size 1979781416
--- a/model-00008-of-00008.safetensors
+++ b/model-00008-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11bc53f797b15794132168d6e033756813af4e8ee75335cb71419fbb3a130b7
+size 906012456
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/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": "<unk>",
+    "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 +1,45 @@
+{
+  "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": 255,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}