初始化项目，由ModelHub XC社区提供模型

Model: saishf/Kuro-Lotus-10.7B Source: Original Platform
2026-05-05 23:39:00 +08:00
commit 759d929555
20 changed files with 91475 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 +1,163 @@
+---
+license: cc-by-nc-4.0
+tags:
+- mergekit
+- merge
+base_model:
+- BlueNipples/SnowLotus-v2-10.7B
+- Himitsui/KuroMitsu-11B
+model-index:
+- name: Kuro-Lotus-10.7B
+  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: 68.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B
+      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: 87.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B
+      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: 66.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B
+      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: 58.27
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B
+      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: 84.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B
+      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: 66.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B
+      name: Open LLM Leaderboard
+---
+# merge
+
+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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [BlueNipples/SnowLotus-v2-10.7B](https://huggingface.co/BlueNipples/SnowLotus-v2-10.7B)
+* [Himitsui/KuroMitsu-11B](https://huggingface.co/Himitsui/KuroMitsu-11B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: Himitsui/KuroMitsu-11B
+        layer_range: [0, 48]
+      - model: BlueNipples/SnowLotus-v2-10.7B
+        layer_range: [0, 48]
+merge_method: slerp
+base_model: Himitsui/KuroMitsu-11B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0.6, 0.7, 0.8, 0.9, 1]
+    - filter: mlp
+      value: [0.4, 0.3, 0.2, 0.1, 0]
+    - value: 0.5
+dtype: bfloat16
+
+```
+# [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_saishf__Kuro-Lotus-10.7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.90|
+|AI2 Reasoning Challenge (25-Shot)|68.69|
+|HellaSwag (10-Shot)              |87.51|
+|MMLU (5-Shot)                    |66.64|
+|TruthfulQA (0-shot)              |58.27|
+|Winogrande (5-shot)              |84.21|
+|GSM8k (5-shot)                   |66.11|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Himitsui/KuroMitsu-11B",
+  "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": 8192,
+  "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": "4.37.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: Himitsui/KuroMitsu-11B
+        layer_range: [0, 48]
+      - model: BlueNipples/SnowLotus-v2-10.7B
+        layer_range: [0, 48]
+merge_method: slerp
+base_model: Himitsui/KuroMitsu-11B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0.6, 0.7, 0.8, 0.9, 1]
+    - filter: mlp
+      value: [0.4, 0.3, 0.2, 0.1, 0]
+    - value: 0.5
+dtype: bfloat16
--- a/model-00001-of-00011.safetensors
+++ b/model-00001-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf18aa1ab8a64f70235028980a8d5646d3d44f8e4d91525038d644f9715ad005
+size 1889603656
--- a/model-00002-of-00011.safetensors
+++ b/model-00002-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5724c78dee2ef36d684177a71c7927305d2f815c0813dfdb5c78b479ef076c25
+size 1988178440
--- a/model-00003-of-00011.safetensors
+++ b/model-00003-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc6155d31438a8ba98ea892ea0060a47b9ba3cff3de6d94c63212cc8cdeb122
+size 1979789752
--- a/model-00004-of-00011.safetensors
+++ b/model-00004-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796d50a1224a201e7d76eaee9060e1c6634cd396f0801eb86de1db1cba28fcba
+size 1946243984
--- a/model-00005-of-00011.safetensors
+++ b/model-00005-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47cd5b34aff78f10605af8d78a9b739e717ab75b7cd658cbf3ec88a778fc33ec
+size 1979781456
--- a/model-00006-of-00011.safetensors
+++ b/model-00006-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c624aac23f0e0a3a10d075f6818ee4d69d94d479f8813302da5bda9be3259ac
+size 1946243984
--- a/model-00007-of-00011.safetensors
+++ b/model-00007-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c7d9a156567fcf6810b9e5ce1e5ebe9d27617a259edf81b9cf05fa3a7a3634
+size 1979781456
--- a/model-00008-of-00011.safetensors
+++ b/model-00008-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0f2a9ee6d3b3d8585d00a8f0696d74c838a6d0bc2b3663658a640ee7bf957e
+size 1946243984
--- a/model-00009-of-00011.safetensors
+++ b/model-00009-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683495ff2068a38cdada3fc3dc40d0a300b054a6a4f2478613c50d01d4182d2d
+size 1979781456
--- a/model-00010-of-00011.safetensors
+++ b/model-00010-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aed42bc3c784c9e2d7541fccc70ca9fa06c479509317bcbb3840dfc61bcfef9
+size 1937838640
--- a/model-00011-of-00011.safetensors
+++ b/model-00011-of-00011.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb518e067c8ec2857f2a59b58add7c303ed410f9d274622dffb9ca6c4262b00a
+size 1889611952
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "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",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}