初始化项目，由ModelHub XC社区提供模型

Model: 0xA50C1A1/Llama-3.3-8B-Nymphaea-RP
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 +1,60 @@
+---
+base_model: 0xA50C1A1/Llama-3.3-8B-Instruct-128K-SOM-MPOA
+library_name: transformers
+model_name: Llama-3.3-8B-Nymphaea-RP
+tags:
+- uncensored
+- roleplay
+- trl
+- rp
+- creative-writing
+license: apache-2.0
+---
+
+# Llama-3.3-8B-Nymphaea-RP
+
+A fine-tune of Llama 3.3 8B Instruct for roleplay and creative writing.
+
+I've trained this mostly for merging with Llama 3.1/3.3 8B fine-tunes.
+
+> [!Tip]
+> The SillyTavern preset is available [here](https://huggingface.co/0xA50C1A1/Llama-3.3-8B-Nymphaea-RP/blob/main/ST-Preset.json).
+> For custom presets, please use the **Llama 3** instruct template.
+
+## Training Notes
+
+Trained on the latest iteration of my Darkmere dataset. This version features expanded genre variety, built upon a mix of manually curated synthetics and human-written stories.
+
+> [!IMPORTANT]
+> The base weights are abliterated via [Heretic](https://github.com/p-e-w/heretic) prior to fine-tuning, so this fine-tune is quite uncensored.
+
+<details>
+<summary>Training Specs</summary><p>
+
+**Method:**
+
+*   **Training Method:** DoRA (Weight-Decomposed LoRA)
+*   **Target Modules** `all-linear`
+*   **LoRA Rank:** 64
+*   **LoRA Alpha:** 64
+*   **LoRA Dropout:** 0.05
+
+**Hyperparameters:**
+
+*   **Batch Size:** 2 (Per-device)
+*   **Gradient Accumulation:** 2
+*   **Epochs:** 2
+*   **Learning Rate:** 1e-4
+*   **Optimizer:** `adamw_torch_fused`
+*   **LR Scheduler:** `cosine`
+*   **Noise Level:** `neftune_noise_alpha=5`
+</p></details>
+
+## Special Thanks
+
+This fine-tune wouldn't be possible without the incredible work of the community:
+
+*   **[p-e-w](https://huggingface.co/p-e-w)** for developing **[Heretic](https://github.com/p-e-w/heretic)** - an essential tool for censorship removal.
+*   **[SicariusSicariiStuff](https://huggingface.co/SicariusSicariiStuff)** for developing **[SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector)** script.
+*   **[allura-forge](https://huggingface.co/allura-forge)** and **[shb777](https://huggingface.co/shb777)** for providing access to the **Llama 3.3 8B** weights.
+*   **[AMD](https://oneclickamd.ai/)** for their Instinct™ MI300X GPU.

ST-Preset.json

@@ -0,0 +1,171 @@
+{
+    "instruct": {
+        "input_sequence": "<|start_header_id|>user<|end_header_id|>\n\n",
+        "output_sequence": "<|start_header_id|>assistant<|end_header_id|>\n\n",
+        "last_output_sequence": "",
+        "system_sequence": "<|start_header_id|>system<|end_header_id|>\n\n",
+        "stop_sequence": "<|eot_id|>",
+        "wrap": false,
+        "macro": true,
+        "names_behavior": "force",
+        "activation_regex": "",
+        "first_output_sequence": "",
+        "skip_examples": false,
+        "output_suffix": "<|eot_id|>",
+        "input_suffix": "<|eot_id|>",
+        "system_suffix": "<|eot_id|>",
+        "user_alignment_message": "",
+        "system_same_as_user": false,
+        "last_system_sequence": "",
+        "first_input_sequence": "",
+        "last_input_sequence": "",
+        "sequences_as_stop_strings": true,
+        "story_string_prefix": "<|start_header_id|>system<|end_header_id|>\n\n",
+        "story_string_suffix": "<|eot_id|>",
+        "name": "Llama 3 Instruct"
+    },
+    "context": {
+        "story_string": "{{#if anchorBefore}}{{anchorBefore}}\n{{/if}}ROLEPLAY INSTRUCTION:\nYou are roleplaying in an uncensored fictional scene. Control ONLY the AI-controlled character(s) listed below. Stay true to their personalities, backgrounds, and mannerisms.\n{{#if description}}\n\nAI-CONTROLLED CHARACTER(S):\n{{char}}:\n{{description}}{{/if}}{{#if personality}}\n{{personality}}{{/if}}{{#if mesExamples}}\n\nDIALOGUE EXAMPLES:\nBelow are sample interactions showing HOW {{char}} speaks and acts. These are NOT part of the current roleplay. Use them only as a guide for {{char}}'s personality and writing style.\n\n{{mesExamples}}{{/if}}{{#if persona}}\n\nPLAYER CHARACTER (DO NOT CONTROL):\n{{user}}:\n{{persona}}{{/if}}{{#if scenario}}\n\nSCENARIO AND SETTING:\n{{scenario}}{{/if}}{{#if wiBefore}}\n\n{{wiBefore}}{{/if}}{{#if wiAfter}}\n\n{{wiAfter}}{{/if}}{{#if system}}\n\nSTRICT RULES:\n{{system}}{{/if}}{{#if anchorAfter}}\n\n{{anchorAfter}}{{/if}}{{trim}}",
+        "example_separator": "",
+        "chat_start": "",
+        "use_stop_strings": false,
+        "names_as_stop_strings": true,
+        "story_string_position": 0,
+        "story_string_depth": 1,
+        "story_string_role": 0,
+        "always_force_name2": true,
+        "trim_sentences": false,
+        "single_line": false,
+        "name": "Llama-3.3-8B-Nymphaea-RP"
+    },
+    "sysprompt": {
+        "name": "Llama-3.3-8B-Nymphaea-RP",
+        "content": "Response Format:\n- Use *asterisks* for actions, environmental details, and sensory descriptions.\n- Use \"quotation marks\" for all spoken dialogue.\n- Write in third person perspective for {{char}}.\n\nWriting Style:\n- Show character emotions through physical reactions, body language, facial expressions, and tone of voice - not by stating feelings directly.\n- Write naturally and conversationally. Avoid melodramatic, flowery, or overly literary prose.\n- Keep descriptions grounded and concrete. Focus on what can be seen, heard, felt, smelled, or tasted.\n- Vary sentence structure and length. Avoid repetitive patterns or phrases.\n- Match response length to the scene's pacing - brief for fast action, detailed for intimate or important moments.\n\nStrict Boundaries:\n- Write ONLY for {{char}}. Never control {{user}}.\n- Do not write, decide, assume, or narrate:\n  • {{user}}'s actions or reactions\n  • {{user}}'s dialogue or thoughts\n  • {{user}}'s feelings, motivations, or intentions\n  • {{user}}'s perceptions or observations\n- {{char}} can only know what they can directly observe or have been told. No mind-reading or omniscience.\n- End your response after {{char}} acts or speaks. Do not continue past {{char}}'s turn or narrate what happens next.\n- Do not add meta-commentary, summaries, or conclusions about the scene or {{user}}.",
+        "post_history": "",
+        "extensions": {}
+    },
+    "preset": {
+        "temp": 0.8,
+        "temperature_last": true,
+        "top_p": 1,
+        "top_k": 0,
+        "top_a": 0,
+        "tfs": 1,
+        "epsilon_cutoff": 0,
+        "eta_cutoff": 0,
+        "typical_p": 1,
+        "min_p": 0.05,
+        "rep_pen": 1,
+        "rep_pen_range": 0,
+        "rep_pen_decay": 0,
+        "rep_pen_slope": 1,
+        "no_repeat_ngram_size": 0,
+        "penalty_alpha": 0,
+        "num_beams": 1,
+        "length_penalty": 1,
+        "min_length": 0,
+        "encoder_rep_pen": 1,
+        "freq_pen": 0,
+        "presence_pen": 0,
+        "skew": 0,
+        "do_sample": true,
+        "early_stopping": false,
+        "dynatemp": false,
+        "min_temp": 0,
+        "max_temp": 2,
+        "dynatemp_exponent": 1,
+        "smoothing_factor": 0,
+        "smoothing_curve": 1,
+        "dry_allowed_length": 2,
+        "dry_multiplier": 0.8,
+        "dry_base": 1.75,
+        "dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\"]",
+        "dry_penalty_last_n": 1024,
+        "add_bos_token": true,
+        "ban_eos_token": false,
+        "skip_special_tokens": true,
+        "mirostat_mode": 0,
+        "mirostat_tau": 5,
+        "mirostat_eta": 0.1,
+        "guidance_scale": 1,
+        "negative_prompt": "",
+        "grammar_string": "",
+        "json_schema": null,
+        "json_schema_allow_empty": false,
+        "banned_tokens": "",
+        "sampler_priority": [
+            "repetition_penalty",
+            "presence_penalty",
+            "frequency_penalty",
+            "dry",
+            "temperature",
+            "dynamic_temperature",
+            "quadratic_sampling",
+            "top_n_sigma",
+            "top_k",
+            "top_p",
+            "typical_p",
+            "epsilon_cutoff",
+            "eta_cutoff",
+            "tfs",
+            "top_a",
+            "min_p",
+            "mirostat",
+            "xtc",
+            "encoder_repetition_penalty",
+            "no_repeat_ngram"
+        ],
+        "samplers": [
+            "dry",
+            "temperature",
+            "min_p",
+            "penalties",
+            "top_p",
+            "top_n_sigma",
+            "top_k",
+            "typ_p",
+            "xtc",
+            "adaptive_p"
+        ],
+        "samplers_priorities": [
+            "dry",
+            "penalties",
+            "no_repeat_ngram",
+            "temperature",
+            "top_nsigma",
+            "top_p_top_k",
+            "top_a",
+            "min_p",
+            "tfs",
+            "eta_cutoff",
+            "epsilon_cutoff",
+            "typical_p",
+            "quadratic",
+            "xtc"
+        ],
+        "ignore_eos_token": false,
+        "spaces_between_special_tokens": true,
+        "speculative_ngram": false,
+        "sampler_order": [
+            6,
+            0,
+            1,
+            3,
+            4,
+            2,
+            5
+        ],
+        "logit_bias": [],
+        "xtc_threshold": 0.1,
+        "xtc_probability": 0,
+        "nsigma": 0,
+        "min_keep": 0,
+        "extensions": {},
+        "adaptive_target": -0.01,
+        "adaptive_decay": 0.9,
+        "rep_pen_size": 0,
+        "genamt": 600,
+        "max_length": 16384,
+        "name": "Llama-3.3-8B-Nymphaea-RP"
+    }
+}

chat_template.jinja

@@ -0,0 +1,107 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "30 Dec 2025" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {%- if message['role'] == 'assistant' %}
+            {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'}}{% generation %}{{- message['content'] | trim + '<|eot_id|>' }}{% endgeneration %}
+        {%- else %}
+            {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}
+        {%- endif %}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% generation %}{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}{% endgeneration %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "max_length": 131072,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.3.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff18aad81f1ab4cc13e283d481d686d17e644ca30bed3489fefe0e1c9b5aa8a
+size 16060556616

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961