初始化项目，由ModelHub XC社区提供模型

Model: Epiculous/Violet_Twilight-v0.2 Source: Original Platform
2026-06-25 12:45:45 +08:00
commit 8a227d0931
13 changed files with 417962 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 +1,198 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ru
+- zh
+- ja
+license: apache-2.0
+tags:
+- merge
+datasets:
+- Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
+- anthracite-org/stheno-filtered-v1.1
+- PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
+- Gryphe/Sonnet3.5-Charcard-Roleplay
+- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
+- anthracite-org/kalo-opus-instruct-22k-no-refusal
+- anthracite-org/nopm_claude_writing_fixed
+- anthracite-org/kalo_opus_misc_240827
+pipeline_tag: text-generation
+model-index:
+- name: Violet_Twilight-v0.2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 45.32
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 23.94
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 2.72
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 2.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 13.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 23.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Epiculous/Violet_Twilight-v0.2
+      name: Open LLM Leaderboard
+---
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64adfd277b5ff762771e4571/P962FQhRG4I8nbU_DJolY.png)
+
+Now for something a bit different, Violet_Twilight-v0.2! This model is a SLERP merge of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2!
+
+# Quants!
+<strong>full</strong> / [exl2](https://huggingface.co/Epiculous/Violet_Twilight-v0.2-exl2) / [gguf](https://huggingface.co/Epiculous/Violet_Twilight-v0.2-GGUF)
+
+## Prompting
+The v0.2 models are trained on ChatML, the prompting structure goes a little something like this:
+
+```
+<|im_start|>user
+Hi there!<|im_end|>
+<|im_start|>assistant
+Nice to meet you!<|im_end|>
+<|im_start|>user
+Can I ask a question?<|im_end|>
+<|im_start|>assistant
+```
+
+### Context and Instruct
+The v0.2 models are trained on ChatML, please use that Context and Instruct template.
+
+### Current Top Sampler Settings
+[Smooth Creativity](https://files.catbox.moe/0ihfir.json): Credit to Juelsman for researching this one!<br/>
+[Variant Chimera](https://files.catbox.moe/h7vd45.json): Credit to Numbra!<br/>
+[Spicy_Temp](https://files.catbox.moe/9npj0z.json) <br/>
+[Violet_Twilight-Nitral-Special](https://files.catbox.moe/ot54u3.json) <br/>
+
+## Merging
+The following config was used to merge Azure Dusk and Crimson Dawn
+```yaml
+slices:
+  - sources:
+      - model: Epiculous/Azure_Dusk-v0.2
+        layer_range: [0, 40]
+      - model: Epiculous/Crimson_Dawn-V0.2
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: Epiculous/Azure_Dusk-v0.2
+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: bfloat16
+
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Epiculous__Violet_Twilight-v0.2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.53|
+|IFEval (0-Shot)    |45.32|
+|BBH (3-Shot)       |23.94|
+|MATH Lvl 5 (4-Shot)| 2.72|
+|GPQA (0-shot)      | 2.13|
+|MuSR (0-shot)      |13.61|
+|MMLU-PRO (5-shot)  |23.45|
+
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Epiculous__Violet_Twilight-v0.2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.53|
+|IFEval (0-Shot)    |45.32|
+|BBH (3-Shot)       |23.94|
+|MATH Lvl 5 (4-Shot)| 2.72|
+|GPQA (0-shot)      | 2.13|
+|MuSR (0-shot)      |13.61|
+|MMLU-PRO (5-shot)  |23.45|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Epiculous/Azure_Dusk-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 15,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 131072
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: Epiculous/Azure_Dusk-v0.2
+        layer_range: [0, 40]
+      - model: Epiculous/Crimson_Dawn-V0.2
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: Epiculous/Azure_Dusk-v0.2
+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
+dtype: bfloat16
--- a/model-00001-of-00005.safetensors
+++ b/model-00001-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014d4dfd2bc7a2ea66ff1834818754a2eac50607a9d85091bb040b4d00cb9d6b
+size 4865489336
--- a/model-00002-of-00005.safetensors
+++ b/model-00002-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd55fb2f5ca34d47cfb0a6fdf4d169a76d2940aaaddf0be1a831e9cf81a96cc
+size 4907529456
--- a/model-00003-of-00005.safetensors
+++ b/model-00003-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2d0c36c7cf2eaa54e7cf7f44ff705c974bae28c28fed1c3d67371d5b49996a
+size 4907529464
--- a/model-00004-of-00005.safetensors
+++ b/model-00004-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e18eb35efec62edce9d213b11c3ddf90e35ee4ef5e162f7f9c9eca18582190b
+size 4907529456
--- a/model-00005-of-00005.safetensors
+++ b/model-00005-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce7b0e47626e088dca8cb4da85c8f1b15f09962cd4462fb52ccd7d352a98b7b
+size 4907529392
--- 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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "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