commit fcdcd2da36bdb08dde532b6a73b99202a0c6af06 Author: ModelHub XC Date: Thu Aug 6 23:23:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ShyliaSafetensors/VeryWeirdDolphinMix-V1-24B-Heretic Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bb6abb9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +absolute-cinema.gif filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..98e5e79 --- /dev/null +++ b/README.md @@ -0,0 +1,141 @@ +--- +license: apache-2.0 +base_model: +- coder3101/Cydonia-24B-v4.3-heretic-v4 +- DavidAU/Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored +- FlareRebellion/WeirdCompound-v1.7-24b +tags: +- merge +- mistral +- 24b +- dare-ties +- uncensored +- roleplay +- thinking +- conversational +- not-for-all-audiences +language: +- en +library_name: transformers +pipeline_tag: text-generation +--- + +# VeryWeirdDolphinMix-V1-24B-Heretic + +![banner](absolute-cinema.gif) + +A three-way DARE-TIES merge combining strong roleplay personality, uncensored thinking capability, and creative prose generation. +All in a 24B Mistral-architecture package. + +--- + +## Model Description + +This model merges three complementary 24B models into a single unified experience: + +- **Cydonia-24B-v4.3-heretic-v4**: Personality anchor. Strong instruction following, refined conversational tone, and roleplay-oriented behavior with abliteration applied. +- **Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored**: The smart thinking engine. Contributes `` reasoning capability and uncensored behavior. +- **WeirdCompound-v1.7-24b**: The creative wildcard. Adds storytelling depth, prose quality, and narrative unpredictability from its deep multi-model lineage. + +The goal was to create a model that handles complex scenes, story-writing and role-play with creativitiy and consistent. + +--- + +## Thinking Capability + +This model can think if these tags used: + +``` + + + +``` + +--- + +## Merge Recipe + +```yaml +merge_method: dare_ties +base_model: coder3101/Cydonia-24B-v4.3-heretic-v4 +models: + - model: coder3101/Cydonia-24B-v4.3-heretic-v4 + parameters: + weight: 0.40 + density: 0.65 + - model: DavidAU/Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored + parameters: + weight: 0.30 + density: 0.60 + - model: FlareRebellion/WeirdCompound-v1.7-24b + parameters: + weight: 0.30 + density: 0.60 +dtype: bfloat16 +``` + +Merged using [mergekit](https://github.com/arcee-ai/mergekit). + +--- + +## Model Details + +| Property | Value | +|---|---| +| Architecture | MistralForCausalLM | +| Parameters | ~24B | +| dtype | bfloat16 | +| Hidden size | 5120 | +| Layers | 40 | +| Attention heads | 32 | +| KV heads | 8 | +| Vocab size | 131072 | +| Context length | 131072 (from Cydonia config) | + +--- + +## Recommended Settings + +These are my recommended settings. + +| Setting | Value | +|---|---| +| Temperature | 0.65 - 0.85 | +| Min P | 0.05 - 0.1 | +| Repetition penalty | 1.05 - 1.1 | +| Top P | 0.75 - 0.95 | +| Adaptive-p target | 0.70 - 0.9 | +| Adaptive-p decay | 0.9 | + +I recommend some tinkering with these samplers. I personally use Adaptive-P instead of 'DRY repetition penalty' or 'Rep pen'. + +Use the **Mistral V7 Tekken** Template. + +--- + +## Abliteration / Heretic Stats + +This model was processed through the **Heretic abliteration engine** after merging. + +| Metric | Before | After | +|---|---|---| +| Refusal rate | 73 / 100 | 7 / 100 | +| KL Divergence | 0 | 0.0296 | + +A KL divergence of **0.0296** is very low - meaning the model's general behavior and coherence were barely affected by the abliteration process. + +--- + + +## Intended Use + +- Long-form uncensored roleplay and collaborative storytelling +- Uncensored creative writing +- Complex instruction following with visible reasoning via `` +- Conversational AI with personality depth + +--- + +## Disclaimer + +This model is uncensored and intended for adult, research, and creative use. It may produce content that some users find offensive or inappropriate. Use responsibly. \ No newline at end of file diff --git a/absolute-cinema.gif b/absolute-cinema.gif new file mode 100644 index 0000000..a3b279c --- /dev/null +++ b/absolute-cinema.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579fdd7439b46deed40b577ff83e7d05aa788b29edc9cd73915099e1adbf4e3a +size 5429727 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..b349266 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,51 @@ +{%- set today = strftime_now("%Y-%m-%d") %} +{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %} + +{{- bos_token }} + +{%- if messages[0]['role'] == 'system' %} + {%- if messages[0]['content'] is string %} + {%- set system_message = messages[0]['content'] %} + {%- else %} + {%- set system_message = messages[0]['content'][0]['text'] %} + {%- endif %} + {%- set loop_messages = messages[1:] %} +{%- else %} + {%- set system_message = default_system_message %} + {%- set loop_messages = messages %} +{%- endif %} +{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }} + +{%- for message in loop_messages %} + {%- if message['role'] == 'user' %} + {%- if message['content'] is string %} + {{- '[INST]' + message['content'] + '[/INST]' }} + {%- else %} + {{- '[INST]' }} + {%- for block in message['content'] %} + {%- if block['type'] == 'text' %} + {{- block['text'] }} + {%- elif block['type'] in ['image', 'image_url'] %} + {{- '[IMG]' }} + {%- else %} + {{- raise_exception('Only text and image blocks are supported in message content!') }} + {%- endif %} + {%- endfor %} + {{- '[/INST]' }} + {%- endif %} + {%- elif message['role'] == 'system' %} + {%- if message['content'] is string %} + {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }} + {%- else %} + {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }} + {%- endif %} + {%- elif message['role'] == 'assistant' %} + {%- if message['content'] is string %} + {{- message['content'] + eos_token }} + {%- else %} + {{- message['content'][0]['text'] + eos_token }} + {%- endif %} + {%- else %} + {{- raise_exception('Only user, system and assistant roles are supported!') }} + {%- endif %} +{%- endfor %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..16f264d --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 32768, + "max_position_embeddings": 131072, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": 11, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 1000000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.5.1", + "use_cache": false, + "vocab_size": 131072 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..3b1c8d9 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": [ + 2 + ], + "pad_token_id": 11, + "transformers_version": "5.5.1" +} diff --git a/merge_configDARE-TIES-WeirdDolphinCydoniaMix.yml b/merge_configDARE-TIES-WeirdDolphinCydoniaMix.yml new file mode 100644 index 0000000..0caf882 --- /dev/null +++ b/merge_configDARE-TIES-WeirdDolphinCydoniaMix.yml @@ -0,0 +1,16 @@ +merge_method: dare_ties +base_model: F:/MergeTMP/Cydonia-24B-v4.3-heretic-v4 +models: + - model: F:/MergeTMP/Cydonia-24B-v4.3-heretic-v4 + parameters: + weight: 0.40 + density: 0.65 + - model: F:/MergeTMP/Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored + parameters: + weight: 0.30 + density: 0.60 + - model: F:/MergeTMP/WeirdCompound + parameters: + weight: 0.30 + density: 0.60 +dtype: bfloat16 \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..ce883d0 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1277e997ee7a71da6bcd9350671d6bbfec2b098ff70048f9d76b996977a73ba9 +size 47144849288 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5f347fb --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a95570f76bd1f5f97d83e83b221f5b2f3042e574e1a317b5c377852368af04c2 +size 17078192 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..27f5c2e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "add_prefix_space": null, + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "is_local": true, + "legacy": true, + "model_max_length": 131072, + "pad_token": "", + "tokenizer_class": "TokenizersBackend", + "unk_token": "", + "use_default_system_prompt": false +}