初始化项目，由ModelHub XC社区提供模型

Model: AbacusResearch/jaLLAbi2-7b
Source: Original Platform

.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

README.md

@@ -0,0 +1,168 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- FelixChao/WestSeverus-7B-DPO-v2
+- bardsai/jaskier-7b-dpo-v5.6
+- AbacusResearch/haLLAwa3
+- cognitivecomputations/WestLake-7B-v2-laser
+model-index:
+- name: jaLLAbi2-7b
+  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: 71.67
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
+      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: 88.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
+      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: 64.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
+      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: 70.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
+      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: 83.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
+      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=AbacusResearch/jaLLAbi2-7b
+      name: Open LLM Leaderboard
+---
+
+# jaLLAbi2-7b
+
+jaLLAbi2-7b 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)
+* [bardsai/jaskier-7b-dpo-v5.6](https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6)
+* [AbacusResearch/haLLAwa3](https://huggingface.co/AbacusResearch/haLLAwa3)
+* [cognitivecomputations/WestLake-7B-v2-laser](https://huggingface.co/cognitivecomputations/WestLake-7B-v2-laser)
+
+## 🧩 Configuration
+
+\```yaml
+models:
+  - model: eren23/ogno-monarch-jaskier-merge-7b
+    # No parameters necessary for base model
+  - model: FelixChao/WestSeverus-7B-DPO-v2
+    #Emphasize the beginning of Vicuna format models
+    parameters:
+      weight: 0.2
+      density: 0.59
+  - model: bardsai/jaskier-7b-dpo-v5.6
+    parameters:
+      weight: 0.2
+      density: 0.55
+  # Vicuna format
+  - model: AbacusResearch/haLLAwa3
+    parameters:
+      weight: 0.3
+      density: 0.55
+  - model: cognitivecomputations/WestLake-7B-v2-laser
+    parameters:
+      weight: 0.3
+      density: 0.55
+
+merge_method: dare_ties
+base_model: eren23/ogno-monarch-jaskier-merge-7b
+parameters:
+  int8_mask: true
+dtype: bfloat16
+random_seed: 0
+\```
+# [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_AbacusResearch__jaLLAbi2-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.06|
+|AI2 Reasoning Challenge (25-Shot)|71.67|
+|HellaSwag (10-Shot)              |88.29|
+|MMLU (5-Shot)                    |64.92|
+|TruthfulQA (0-shot)              |70.16|
+|Winogrande (5-shot)              |83.35|
+|GSM8k (5-shot)                   |71.95|
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "eren23/ogno-monarch-jaskier-merge-7b",
+  "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": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,28 @@
+models:
+  - model: eren23/ogno-monarch-jaskier-merge-7b
+    # No parameters necessary for base model
+  - model: FelixChao/WestSeverus-7B-DPO-v2
+    #Emphasize the beginning of Vicuna format models
+    parameters:
+      weight: 0.2
+      density: 0.59
+  - model: bardsai/jaskier-7b-dpo-v5.6
+    parameters:
+      weight: 0.2
+      density: 0.55
+  # Vicuna format
+  - model: AbacusResearch/haLLAwa3
+    parameters:
+      weight: 0.3
+      density: 0.55
+  - model: cognitivecomputations/WestLake-7B-v2-laser
+    parameters:
+      weight: 0.3
+      density: 0.55
+
+merge_method: dare_ties
+base_model: eren23/ogno-monarch-jaskier-merge-7b
+parameters:
+  int8_mask: true
+dtype: bfloat16
+random_seed: 0

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28196f784223a6fb69e5044e8a64bf0ae7cd46173a35ede1adc55c49f8d52339
+size 1979773128

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485f966795ecae71f6a41c42f31d327561dcf526c5fa6e3898ca8f6c189c1767
+size 1996567640

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76230daacd5675f8ed6b611e9667a9fa7a1387c4a4a5c7744ec3fbde72c6c24d
+size 1895895376

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22242f9e6448c84d3864ccc8ee86ba2f9e1599a84778b676f072b654f05c242
+size 1744900168

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450e3a1caad332d04931812c6361092db7f024658f3a0894224ab4dcc9f40390
+size 1950412280

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42aa9ffd865042350579ae3a2bc3d690dfd7a9bf6906bc1b2d55cd1ff2b0701
+size 1979789776

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da0d4983c7b22ff9add5127c6d4e6eeee9e2b68c1d2be5532553ed3dcc177f9
+size 1946252288

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f9b607d90a84872d1fb0a25008d00017a48bfd4abdeefa45aa1c0448766b56
+size 989907328

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
+  }
+}

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
+}