初始化项目，由ModelHub XC社区提供模型

Model: giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1 Source: Original Platform
2026-05-27 11:48:19 +08:00
commit 0b368970e5
11 changed files with 91546 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 +1,251 @@
+---
+base_model:
+- mistralai/Mistral-7B-v0.1
+- berkeley-nest/Starling-LM-7B-alpha
+- mlabonne/AlphaMonarch-7B
+- cognitivecomputations/WestLake-7B-v2-laser
+- senseable/garten2-7b
+
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: cc-by-nc-4.0
+
+model-index:
+- name: Starling_Monarch_Westlake_Garten-7B-v0.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: EQ-Bench
+      type: eq-bench
+      config: EQ-Bench
+      split: v2.1
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 80.01
+      name: self-reported
+    source:
+      url: https://github.com/EQ-bench/EQ-Bench
+      name: EQ-Bench v2.1
+  - 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: 71.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1
+      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: 88.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1
+      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: 65.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1
+      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: 67.92
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1
+      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: 82.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1
+      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: 71.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1
+      name: Open LLM Leaderboard
+---
+# Starling_Monarch_Westlake_Garten-7B-v0.1
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/655a9883cbbaec115c3fd6b3/Chyn1eXYC0LSY6yVdeRBV.png" alt="drawing" width="800"/>
+
+After experimenting with density for a previous merge (containing similar models), I decided to experiment with weight gradients. My thought that was that if the merge was done with care and attention, I'd be able to create something greater than the sum of its parts. 
+Hoping that, through a merge of really good models, I'd be able to create something greater than the sum of its parts. 
+
+I came across the EQ-Bench Benchmark [(Paper)](https://arxiv.org/abs/2312.06281) as part of my earlier testing. It is a very light and quick benchmark that yields powerful insights into how well the model performs in emotional intelligence related prompts.
+As part of this process, I tried to figure out if there was a way to determine an optimal set of gradient weights that would lead to the most successful merge as measured against EQ-Bench. At first, my goal was to simply exceed WestLake-7B, but then I kept pushing to see what I could come up with.
+Too late in the process, I learned that [dare_ties](https://arxiv.org/abs/2311.03099) has a random element to it. Valuable information for next time, I guess. After concluding that project, I began collecting more data, this time setting a specified seed in mergekit for reproducibility. As I was collecting data, I hit the goal I had set for myself.
+This model is *not* a result of the above work but is the genesis of how this model came to be.
+
+I present, **Starling_Monarch_Westlake_Garten-7B-v0.1**, the **only 7B model to score > 80** on the EQ-Bench v2.1 benchmark found [here](https://github.com/EQ-bench/EQ-Bench), outscoring larger models like [abacusai/Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1) and [cognitivecomputations/dolphin-2.2-70b](https://huggingface.co/cognitivecomputations/dolphin-2.2-70b)
+
+It also surpasses its components in the GSM8K benchmark, with a score of 71.95. I'll be looking to bring out more logic and emotion in the next evolution of this model.
+
+It also earned 8.109 on MT-Bench[(paper)](https://arxiv.org/abs/2306.05685), outscoring Chat-GPT 3.5 and Claude v1. 
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
+The seed for this merge is 176
+### Models Merged
+
+The following models were included in the merge:
+* [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha)
+* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
+* [cognitivecomputations/WestLake-7B-v2-laser](https://huggingface.co/cognitivecomputations/WestLake-7B-v2-laser)
+* [senseable/garten2-7b](https://huggingface.co/senseable/garten2-7b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: mistralai/Mistral-7B-v0.1
+    # No parameters necessary for base model
+
+  - model: cognitivecomputations/WestLake-7B-v2-laser
+    parameters:
+      density: 0.58
+      weight:  [0.3877, 0.1636, 0.186, 0.0502]
+
+
+
+  - model: senseable/garten2-7b
+    parameters:
+      density: 0.58
+      weight:  [0.234, 0.2423, 0.2148, 0.2775]
+
+
+
+  - model: berkeley-nest/Starling-LM-7B-alpha
+    parameters:
+      density: 0.58
+      weight:  [0.1593, 0.1573, 0.1693, 0.3413]
+
+
+
+  - model: mlabonne/AlphaMonarch-7B
+    parameters:
+      density: 0.58
+      weight:  [0.219, 0.4368, 0.4299, 0.331]
+
+
+
+merge_method: dare_ties
+base_model: mistralai/Mistral-7B-v0.1
+parameters:
+  int8_mask: true
+dtype: bfloat16
+
+```
+
+
+
+
+### Table of Benchmarks
+
+## Open LLM Leaderboard
+
+|                                                         | Average | ARC   | HellaSwag | MMLU  | TruthfulQA | Winogrande | GSM8K |
+|---------------------------------------------------------|---------|-------|-----------|-------|------------|------------|-------|
+| giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1     | 74.9    | 71.76 | 88.15     | 65.07 | 67.92      | 84.53      | 71.95 |
+| mlabonne/AlphaMonarch-7B                                | 75.99   | 73.04 | 89.18     | 64.4  | 77.91      | 84.69      | 66.72 |
+| senseable/WestLake-7B-v2                                | 74.68   | 73.04 | 88.65     | 64.71 | 67.06      | 86.98      | 67.63 |
+| berkeley-nest/Starling-LM-7B-alpha                      | 67.13   | 63.82 | 84.9      | 63.64 | 46.39      | 80.58      | 62.4  |
+| senseable/garten2-7b                                    | 72.65   | 69.37 | 87.54     | 65.44 | 59.5       | 84.69      | 69.37 |
+
+
+
+## Yet Another LLM Leaderboard benchmarks
+
+|                                          Model                                                                                  |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
+|---------------------------------------------------------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
+|[giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1](https://huggingface.co/giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1)|  44.99|  76.93|     68.04|   47.71|  59.42|
+|[mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)                                                      |  45.37|  77   |     78.39|   50.2 |  62.74|
+|[berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha)                                  |  42.06|  72.72|     47.33|   42.53| 51.16 |
+
+## Misc. Benchmarks
+
+|                                                         | MT-Bench                                    | EQ-Bench v2.1                                                                   |
+|---------------------------------------------------------|---------------------------------------------|---------------------------------------------------------------------------------|
+| giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1     | 8.109375                                    | 80.01 (3 Shot, ChatML, ooba)                                                            |
+| mlabonne/AlphaMonarch-7B                                | 8.23750                                     | 76.08                                                                           |
+| senseable/WestLake-7B-v2                                |    X                                        | 78.7                                                                            |
+| berkeley-nest/Starling-LM-7B-alpha                      | 8.09                                        | 68.69 (1 Shot, ChatML, ooba)                                                                            |
+| senseable/garten2-7b                                    |    X                                        | 75.03                                                                           |
+| claude-v1                                               | 7.900000                                    | 76.83                                                                           |
+| gpt-3.5-turbo                                           | 7.943750                                    | 71.74                                                                           |
+|                                                         | [(Paper)](https://arxiv.org/abs/2306.05685) | [(Paper)](https://arxiv.org/abs/2312.06281) [Leaderboard](https://eqbench.com/) |
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-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": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,37 @@
+models:
+  - model: mistralai/Mistral-7B-v0.1
+    # No parameters necessary for base model
+
+  - model: cognitivecomputations/WestLake-7B-v2-laser
+    parameters:
+      density: 0.58
+      weight:  [0.3877, 0.1636, 0.186, 0.0502]
+
+
+
+  - model: senseable/garten2-7b
+    parameters:
+      density: 0.58
+      weight:  [0.234, 0.2423, 0.2148, 0.2775]
+
+
+
+  - model: berkeley-nest/Starling-LM-7B-alpha
+    parameters:
+      density: 0.58
+      weight:  [0.1593, 0.1573, 0.1693, 0.3413]
+
+
+
+  - model: mlabonne/AlphaMonarch-7B
+    parameters:
+      density: 0.58
+      weight:  [0.219, 0.4368, 0.4299, 0.331]
+
+
+
+merge_method: dare_ties
+base_model: mistralai/Mistral-7B-v0.1
+parameters:
+  int8_mask: true
+dtype: bfloat16
--- a/model-00001-of-00002.safetensors
+++ b/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442d0b935aad2a6b5f77f9fe5793f682ed95210ecc4d7b00da2b04cc957f3290
+size 9942981696
--- a/model-00002-of-00002.safetensors
+++ b/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4befda3c5175896b53d252d1b941d7f96bc00024a9e8afd5b63ca1103926bc64
+size 4540516344
--- 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
+}