初始化项目，由ModelHub XC社区提供模型

Model: dddsaty/Merge_Sakura_Solar Source: Original Platform
2026-05-28 06:56:17 +08:00
commit 6e41bc7d04
11 changed files with 91344 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 +1,25 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+- en
+pipeline_tag: text-generation
+---
+
+**Explanation**
+- Merged three models using [mergekit](https://github.com/arcee-ai/mergekit) (dare_ties)
+
+**Models**
+- [Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
+- [Sakura-SOLRCA-Math-Instruct-DPO-v2](https://huggingface.co/kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2)
+- [Sakura-SOLRCA-Instruct-DPO](https://huggingface.co/kyujinpy/Sakura-SOLRCA-Instruct-DPO)
+
+**Score**
+|Average|ARC|HellaSwag|MMLU|TruthfulQA|Winogrande|GSM8K|
+|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+|74.03|70.73|88.51|66.03|72.21|82.72|63.99|
+
+**Original Author's HuggingFace profile**
+- [kyujinpy](https://huggingface.co/kyujinpy)
+
+**License**
+- Following the license written at the author's space
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "kyujinpy/Sakura-SOLAR-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,41 @@
+models:
+  - model: kyujinpy/Sakura-SOLAR-Instruct
+    parameters:
+      density: 1.0
+      weight: 1.0
+  - model: kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
+    parameters:
+      density: 0.5
+      weight: [0.33, 0.4, 0.33]
+  - model: kyujinpy/Sakura-SOLRCA-Instruct-DPO
+    parameters:
+      density: [0.33, 0.45, 0.66]
+      weight: 0.66
+merge_method: dare_ties
+base_model: kyujinpy/Sakura-SOLAR-Instruct
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+tokenizer_source : union
+
+#slices:
+#  - sources:
+#      - model: upstage/SOLAR-10.7B-Instruct-v1.0
+#        layer_range: [0, 48]
+#      - model: beomi/OPEN-SOLAR-KO-10.7B
+#        layer_range: [0, 48]
+## or, the equivalent models: syntax:
+## models:
+##   - model: psmathur/orca_mini_v3_13b
+##   - model: garage-bAInd/Platypus2-13B
+#merge_method: slerp
+#base_model: upstage/SOLAR-10.7B-Instruct-v1.0
+#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 # fallback for rest of tensors
+#dtype: float16
--- a/model-00001-of-00003.safetensors
+++ b/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e1d1a6068bcc4e27e2b49e296316dca427cd80a738dbd63c90d9300e09127a1
+size 9993313696
--- a/model-00002-of-00003.safetensors
+++ b/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749b9913b9f5238acd7183b5441a8163706edf7a9ca6c6c007eb6fa56eb57c4f
+size 9781500368
--- a/model-00003-of-00003.safetensors
+++ b/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b827f583a15d9049ec795f8cd949d384fb47dbaba598b7a7410d5ff4cb3cdfd
+size 1688284776
--- 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": "</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_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,47 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}