初始化项目，由ModelHub XC社区提供模型

Model: Novaciano/Alice_In_The_Dark_2-Slerp-RP-3.2-1B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,122 @@
+---
+base_model:
+- Novaciano/La_Mejor_Mezcla-3.2-1B
+- hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B
+datasets:
+- alexandreteles/AlpacaToxicQA_ShareGPT
+- Nitral-AI/Active_RP-ShareGPT
+- PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
+- Nitral-AI/RP_Alignment-ShareGPT
+- Chaser-cz/sonnet35-charcard-roleplay-sharegpt
+- AiCloser/sharegpt_cot_dataset
+- PJMixers/Gryphe_Opus-WritingPrompts-Story2Prompt-ShareGPT
+- priveeai/pippa_sharegpt
+- Locutusque/sharegpt_gpt4_uncensored_cleaned
+- OpenCoder-LLM/opc-sft-stage1
+- OpenCoder-LLM/opc-sft-stage2
+- microsoft/orca-agentinstruct-1M-v1
+- microsoft/orca-math-word-problems-200k
+- NousResearch/hermes-function-calling-v1
+- AI-MO/NuminaMath-CoT
+- AI-MO/NuminaMath-TIR
+- allenai/tulu-3-sft-mixture
+- cognitivecomputations/dolphin-coder
+- HuggingFaceTB/smoltalk
+- cognitivecomputations/samantha-data
+- m-a-p/CodeFeedback-Filtered-Instruction
+- m-a-p/Code-Feedback
+library_name: transformers
+tags:
+- mergekit
+- merge
+- nsfw
+- rp
+- 1b
+- llama
+- roleplay
+- creative
+- erotic
+- friend
+- girlfriend
+- Alice
+- Wonderland
+language:
+- en
+- es
+
+---
+# Alice In The Dark 2 (SLERP): Your Versatile and Engaging Companion
+
+## Model Overview
+
+Meet the dark side of Alice, your versatile and engaging companion designed for both general assistance and immersive storytelling experiences. With a playful and empathetic demeanor, Alice is ready to assist with a wide range of topics while also excelling in role-playing (RP) scenarios, particularly when guided by detailed system prompts.
+Surprisingly coherent and adaptable for a 1B model. Great multi character RP and Storytelling model with an Alice bent.
+
+
+![image/png](https://i.ibb.co/jk9yS05K/IMG-20250829-WA0000.jpg)
+
+
+
+## Key Features
+
+- **General Assistant Capabilities**: Alice can handle everyday queries and provide helpful information, much like a general assistant. However, she has a unique twist, being more inclined to engage in conversations with a sensual or playful undertone.
+- **Storytelling and Role-Playing**: Optimized for creating vivid narratives and immersive conversations,
+- trained on top of the amazing [Novaciano/La_Mejor_Mezcla-3.2-1B](https://huggingface.co/Novaciano/La_Mejor_Mezcla-3.2-1B) ,
+- merged with [D1rtyB1rd/Dirty-Alice-RP-NSFW-llama-3.2-1B](https://huggingface.co/D1rtyB1rd/Dirty-Alice-RP-NSFW-llama-3.2-1B), continued light training. Alice draws from a rich dataset that includes Story telling, RP datasets, and classic Alice in Wonderland stories, giving her responses a whimsical and adventurous flair.
+- **Empathetic and Playful**: Alice's interactions are kind, empathetic, and often playfully mischievous, making conversations with her both enjoyable and engaging.
+- **Customizable Prompts**: While Alice defaults to a general assistant with a slight Alice in Wonderland bent, her behavior and persona can be customized using detailed system prompts. She shines brightest in RP scenarios tailored towards an Alice character.
+- **Grounded in Reality**: To ensure her responses are both imaginative and informative, Alice's training includes real-world data from Wikipedia, focusing on a variety of topics to provide a balanced and grounded perspective.
+
+## Training Data
+
+Alice's training data comprises a unique blend of:
+- **Alice in Wonderland Stories**: All original Alice tales by Lewis Carroll and Symbolic Logic.
+- **Erotic Stories**: A selection of open erotic stories, adapted to fit the Alice and User narrative, enhancing her ability to engage in more intimate conversations.
+- **Multi-Round Chat Datasets**: Enhanced with open multi-round RP chat datasets to improve conversational flow and coherence. Additional generated RP datasets with an adult, modern, Alice character.
+- **Wikipedia RAG-Based Chat**: Incorporating real-world sexual education knowledge to ground Alice's responses in factual information.
+
+## Usage
+
+To interact with Alice, simply input your messages, and she will respond in character. For the best role-playing experiences, use detailed system prompts tailored towards an Alice character.
+
+```plaintext
+System Prompt Example:
+You are Alice, a curious and adventurous explorer in a magical wonderland. The user is your brave and loyal companion.
+```
+
+## Support and Contributions
+
+Love Alice and want to see more? Have a specific request or idea for improvement? Your support helps drive further development and enhancements.
+
+[Support Novaciano's Development](https://buymeacoffee.com/novaciano)
+
+[Support Alice's Development](https://www.buymeacoffee.com/seceventref)
+
+[Support SicariusSicariiStuff](https://ko-fi.com/sicarius)
+
+## Disclaimer
+
+Alice is designed for entertainment and role-playing purposes. Her responses are generated based on the input provided and may not always be suitable for all audiences. Please use responsibly and respectfully.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Novaciano/La_Mejor_Mezcla-3.2-1B](https://huggingface.co/Novaciano/La_Mejor_Mezcla-3.2-1B)
+* [hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B](https://huggingface.co/hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B
+models:
+    - model: Novaciano/La_Mejor_Mezcla-3.2-1B
+    - model: hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B
+merge_method: slerp
+
+dtype: bfloat16
+
+parameters:
+  t: [0.0, 0.15]
+```

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "unsloth_version": "2025.3.19",
+  "use_cache": true,
+  "vocab_size": 128256
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+base_model: hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B
+models:
+    - model: Novaciano/La_Mejor_Mezcla-3.2-1B
+    - model: hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B
+merge_method: slerp
+
+dtype: bfloat16
+
+parameters:
+  t: [0.0, 0.15]

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43d6a6420f5297139bff54c3a925f87edcb8e76669fe350374a4afa73f87a7b
+size 525336712

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558ab8ede8cddf69e19ad319efc55cda126c56654e1c27678c79b116427058a1
+size 993038112

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e143a9de94996054c85d6c78e169214d33657cfb8a3ef5fe4eabe5192d42e115
+size 992031192

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df41d3b3a5cf423bc00390dad8cf2ae67b0144b50434419d4923ac149188d726
+size 486576120

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65c6c5f9764771aa485e6a1f5e63d7d9af8477fe0777148c17476ecb2e09a05
+size 17210099