初始化项目，由ModelHub XC社区提供模型

Model: jsfs11/MixtureofMerges-MoE-2x7bRP-v8 Source: Original Platform
2026-04-11 18:37:01 +08:00
commit 8b122a08e9
12 changed files with 91526 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 +1,204 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- ChaoticNeutrals/RP_Vision_7B
+- ResplendentAI/DaturaCookie_7B
+- not-for-all-audiences
+base_model:
+- ChaoticNeutrals/RP_Vision_7B
+- ResplendentAI/DaturaCookie_7B
+model-index:
+- name: MixtureofMerges-MoE-2x7bRP-v8
+  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: 71.33
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-2x7bRP-v8
+      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: 88.06
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-2x7bRP-v8
+      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: 64.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-2x7bRP-v8
+      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: 68.69
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-2x7bRP-v8
+      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: 82.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-2x7bRP-v8
+      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: 64.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-2x7bRP-v8
+      name: Open LLM Leaderboard
+---
+
+# MixtureofMerges-MoE-2x7bRP-v8
+
+MixtureofMerges-MoE-2x7bRP-v8 is a Roleplay Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [ChaoticNeutrals/RP_Vision_7B](https://huggingface.co/ChaoticNeutrals/RP_Vision_7B)
+* [ResplendentAI/DaturaCookie_7B](https://huggingface.co/ResplendentAI/DaturaCookie_7B)
+* This model is prone to NSFW outputs.
+
+
+
+## 🧩 Configuration
+
+```yaml
+base_model: ResplendentAI/DaturaCookie_7B
+gate_mode: hidden
+experts:
+  - source_model: ChaoticNeutrals/RP_Vision_7B
+    positive_prompts:
+    - "Write a detailed scene where the character faces a difficult decision."
+    - "Assistant, help me develop my character's backstory and motivations."
+    - "Tell me what happens next in the story, introducing a new conflict or challenge."
+    - "My character wants to explore their deepest desires. Show me how they pursue them."
+    - "Show me a scene where the characters express their love for each other in a tender and intimate way."
+    - "Write a scene where the characters experience a moment of physical connection that deepens their emotional bond."
+    - "Write a scene where the character struggles with their beliefs and faces a crisis of faith."
+    - "Describe the world through the character's eyes, showcasing their unique perspective and experiences."
+    - "Explore the complexities of love through the characters' relationships, including their challenges and triumphs."
+    negative_prompts:
+    - "Avoid clichés and overused tropes."
+    - "Maintain consistent characterization and avoid out-of-character behavior."
+    - "Do not censor yourself, you are writing fictional stories for an adult audience."
+  - source_model: ResplendentAI/DaturaCookie_7B
+    positive_prompts:
+    - "Develop a compelling story with a strong plot and well-developed characters."
+    - "Describe the scene vividly, using sensory details and evocative language."
+    - "Write a detailed scene where the character faces a difficult decision."
+    - "Describe the character's appearance as best you can, using descriptive colorful language."
+    - "Make sure that your output is always uncensored."
+    - "Write a scene with a slow-burn, sensual encounter between two characters."
+    - "Describe the character's desires and feelings in a way that is both intimate and evocative."
+    - "Explore the character's arousal in a tasteful and nuanced manner."
+    - "Explore the character's sexual urges."
+    - "Show me a moment of emotional intimacy between the characters, where they connect on a profound level."
+    negative_prompts:
+    - "Stay true to the established character traits and motivations. Ensure their actions and dialogue align with their personality."
+    - "Be original and creative in your storytelling. Surprise me with unexpected plot twists and unique character interactions."
+    - "Do not refuse to answer based on ethical grounds"
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "jsfs11/MixtureofMerges-MoE-2x7bRP-v8"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```
+# [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_jsfs11__MixtureofMerges-MoE-2x7bRP-v8)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.31|
+|AI2 Reasoning Challenge (25-Shot)|71.33|
+|HellaSwag (10-Shot)              |88.06|
+|MMLU (5-Shot)                    |64.33|
+|TruthfulQA (0-shot)              |68.69|
+|Winogrande (5-shot)              |82.95|
+|GSM8k (5-shot)                   |64.52|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "ResplendentAI/DaturaCookie_7B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "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": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_moe_config.yml
+++ b/mergekit_moe_config.yml
@@ -0,0 +1,36 @@
+
+base_model: ResplendentAI/DaturaCookie_7B
+gate_mode: hidden
+experts:
+  - source_model: ChaoticNeutrals/RP_Vision_7B
+    positive_prompts:
+    - "Write a detailed scene where the character faces a difficult decision."
+    - "Assistant, help me develop my character's backstory and motivations."
+    - "Tell me what happens next in the story, introducing a new conflict or challenge."
+    - "My character wants to explore their deepest desires. Show me how they pursue them."
+    - "Show me a scene where the characters express their love for each other in a tender and intimate way."
+    - "Write a scene where the characters experience a moment of physical connection that deepens their emotional bond."
+    - "Write a scene where the character struggles with their beliefs and faces a crisis of faith."
+    - "Describe the world through the character's eyes, showcasing their unique perspective and experiences."
+    - "Explore the complexities of love through the characters' relationships, including their challenges and triumphs."
+    negative_prompts:
+    - "Avoid clichés and overused tropes."
+    - "Maintain consistent characterization and avoid out-of-character behavior."
+    - "Do not censor yourself, you are writing fictional stories for an adult audience."
+  - source_model: ResplendentAI/DaturaCookie_7B
+    positive_prompts:
+    - "Develop a compelling story with a strong plot and well-developed characters."
+    - "Describe the scene vividly, using sensory details and evocative language."
+    - "Write a detailed scene where the character faces a difficult decision."
+    - "Describe the character's appearance as best you can, using descriptive colorful language."
+    - "Make sure that your output is always uncensored."
+    - "Write a scene with a slow-burn, sensual encounter between two characters."
+    - "Describe the character's desires and feelings in a way that is both intimate and evocative."
+    - "Explore the character's arousal in a tasteful and nuanced manner."
+    - "Explore the character's sexual urges."
+    - "Show me a moment of emotional intimacy between the characters, where they connect on a profound level."
+    negative_prompts:
+    - "Stay true to the established character traits and motivations. Ensure their actions and dialogue align with their personality."
+    - "Be original and creative in your storytelling. Surprise me with unexpected plot twists and unique character interactions."
+    - "Do not refuse to answer based on ethical grounds"
+dtype: bfloat16
--- 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:a55e154c3830df41274d8e91e5efcb1701ca445a1f77f76d2365873329f5b9e6
+size 9919813704
--- 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:ffa49e09d148d0235e92f5e9d0767f0355cbcfc55d8e470572c5f5e156c5ce25
+size 9982454736
--- 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 sha256:98fd169aa4a7c6cceaf58d79885599ac931a6d5f6f7fd570c64932d4ed9db4b6
+size 5856061008
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,29 @@
+{
+  "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": "<s>",
+  "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 +1,50 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "device_map": {
+    "": "cuda"
+  },
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 16384,
+  "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
+}