初始化项目，由ModelHub XC社区提供模型

Model: saishf/Fimbulvetr-Kuro-Lotus-10.7B Source: Original Platform
2026-05-14 18:07:44 +08:00
commit 846b026f53
20 changed files with 91489 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 +1,177 @@
+---
+license: cc-by-nc-4.0
+library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- Sao10K/Fimbulvetr-10.7B-v1
+- saishf/Kuro-Lotus-10.7B
+model-index:
+- name: Fimbulvetr-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: 69.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fimbulvetr-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: 87.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fimbulvetr-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: 66.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fimbulvetr-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: 60.95
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fimbulvetr-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: 84.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fimbulvetr-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: 66.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fimbulvetr-Kuro-Lotus-10.7B
+      name: Open LLM Leaderboard
+---
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63df7c44f0c75dfb876272c0/knwDeWu0JVdH5EPB1knvh.png)
+
+--------------------------------------------
+* This model is a merge of my personal favourite models, i couldn't decide between them so why not have both? Without MOE cause gpu poor :3
+
+* With my own tests it gives kuro-lotus like results without the requirement for a highly detailed character card and stays coherent when roping up to 8K context.
+
+* I personally use the "Universal Light" preset in silly tavern, with "alpaca" the results can be short but are longer with "alpaca roleplay".
+
+* "Universal Light" preset can be extremely creative but sometimes likes to act for user with some cards, for those i like just the "default" but any preset seems to work!
+
+  
+# 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:
+* [Sao10K/Fimbulvetr-10.7B-v1](https://huggingface.co/Sao10K/Fimbulvetr-10.7B-v1)
+* [saishf/Kuro-Lotus-10.7B](https://huggingface.co/saishf/Kuro-Lotus-10.7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: saishf/Kuro-Lotus-10.7B
+        layer_range: [0, 48]
+      - model: Sao10K/Fimbulvetr-10.7B-v1
+        layer_range: [0, 48]
+merge_method: slerp
+base_model: saishf/Kuro-Lotus-10.7B
+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__Fimbulvetr-Kuro-Lotus-10.7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.73|
+|AI2 Reasoning Challenge (25-Shot)|69.54|
+|HellaSwag (10-Shot)              |87.87|
+|MMLU (5-Shot)                    |66.99|
+|TruthfulQA (0-shot)              |60.95|
+|Winogrande (5-shot)              |84.14|
+|GSM8k (5-shot)                   |66.87|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "saishf/Kuro-Lotus-10.7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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": false,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: saishf/Kuro-Lotus-10.7B
+        layer_range: [0, 48]
+      - model: Sao10K/Fimbulvetr-10.7B-v1
+        layer_range: [0, 48]
+merge_method: slerp
+base_model: saishf/Kuro-Lotus-10.7B
+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 sha256:45e47324d9dfe779d2b2181ecf82a3ab71cc552cbd195631a42817dfb438036b
+size 1898000688
--- 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 sha256:69cd37dd82cb754e4e821a2082f0f28ef1a6c5c72fbee17d7660a59fc978bd9e
+size 1979781416
--- 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:aaeefda4c8a1f84932022a33a6aa806fd82e24958817807ef5b76c7368350bc8
+size 1988186784
--- 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 sha256:8281f6b12f3fe52e5a11895d57d28233f4ffd1dcc763d328a584fec3078745b2
+size 1937846944
--- 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 sha256:3b21143b75718314a7b5a31db82a24fe7599df58695656dff4315f7db13eb0d6
+size 1988178496
--- 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 sha256:06ae3aa334d6cc19ec22552c6c21ad4a9aafb363eb4a34002fb28218316a3ebd
+size 1937846944
--- 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:d65a1d88b421a04dbbb8b816f486c5958a8f6dbe31e845c07199d41e729f6a86
+size 1988178496
--- 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 sha256:4584db0da41b4585fdcd6a13e20bc8beadf9f0cb828498922ca7e40d7dfe00bf
+size 1937846944
--- 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:e8ac7218780e6d166bca8dbaa559fd7dafff2d51580db06f86f8436dba03c3b1
+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 sha256:77b6f56e25fc9a260e030b436eebb9ca1e2a320cfcb03731ce682a8e8c4aaa91
+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:cccccf8404ef90a8144e77e098ebda91ffb76edb70bb521b5fb9d5af05db61b3
+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
+}