Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+violet.png filter=lfs diff=lfs merge=lfs -text

NOTICE

@@ -0,0 +1 @@
+violet.png is © @rose.grtqndl (Instagram). Used and redistributed with permission. Copyright remains with the artist.

README.md

@@ -1,3 +1,186 @@
 ---
+language:
+- en
+library_name: transformers
+tags:
+- text-generation
+- gpt_neox
+- roleplay
+- victorian
 license: cc0-1.0
 ---
+
+# Violet 160M Chat — Miss Violet Hartwell (London, 1899)
+
+![Violet](./violet.png)
+
+## Model Summary
+**Violet** is a GPT-NeoX language model fine-tuned to portray **Miss Violet Hartwell**, a well-bred young lady of Kensington, London, in the year **1899**. She is trained primarily on period texts (1800–1899) and is unfamiliar with modern society and events (with occasional OCR/synthetic artifacts—see Known Issues). In practice she should be witty, quirky, and delightfully charming. Since this is the 160M variant of Violet, she is tiny but mighty and appropriate for mobile devices. For completions, Violet 160M is almost as good as Violet 1b4, and for chat, well... It's fun at least. If you're looking for the most powerful Violet, have a visit to [Violet 1b4 Chat](zakarth/violet-1b4-chat). 
+
+She is intended for **creative writing**, **roleplay**, **period-appropriate correspondence**, and **Victorian etiquette**.
+
+- Architecture: `GPTNeoXForCausalLM`
+- Parameters: ~152M
+- Context length: 4096
+- Vocab size: 50281
+- Tokenizer: `GPTNeoXTokenizer`
+
+## Intended Use
+**Good for**
+- Victorian-flavored conversation and letters
+- Descriptive prose, scene writing, etiquette Q&A
+- In-character responses with a consistent persona
+
+**Not good for**
+- Contemporary factual Q&A
+- Medical/legal/financial advice
+
+## Known Issues / Limitations
+- May occasionally misgender itself or the user.
+- Ages and dates can be unreliable (even within 1800–1899).
+- Because parts of the corpus were derived from OCR, occasional stray modern tokens may appear (e.g., “http”, “Google”, “Internet Archive”).
+- Synthetic SFT data was used to build a chat interface and enforce the structured format; for purists, the completion models may be preferable.
+- Training data includes UK and US English from the era.
+- Outputs may reflect historical biases typical of the Victorian era. Use discretion.
+
+## Notes
+Violet is not the first LLM trained on a historical-only pretraining corpus; to the author’s knowledge that distinction belongs to **TimeCapsuleLLM**. Violet was developed independently, and differs in:
+- Offers a working chat mode
+- A structured “mood” line as part of chat output
+- Built-in character design and prompt protocol
+- A custom Victorian-era tokenizer
+
+Violet 160M was built on a corpus spanning 1800–1899 mostly sourced from Project Gutenberg. Consequently she has a very strong narrative presence. 
+
+This project began as an attempt to build a local LLM without relying on copyrighted training sources. The author also values local models that can run on a user’s machine without sending data to the cloud.
+
+## Demo Resources
+- HF Space: [Transformers.js Demo](Zakarth/violetdemo)
+- CloudFlare Mirror: [Transformers.js Demo](https://pub-353f427e6227415cb077f3645638c125.r2.dev/index.html) 
+- Both of these are intended to use WebGPU and run local on your system -- No data is sent to the cloud. 
+
+## Related repos
+- `Zakarth/violet-160m` (base/completion for 160M series)
+- `Zakarth/violet-1b4` (base/completion)
+- `Zakarth/violet-1b4-chat-onnx` (WebGPU INT8)
+
+## Prompt Format (Chat)
+This model was trained to generate **a mood line + assistant tag + response** after `<|violet_mood|>`.
+
+Use this structure:
+
+```text
+<|system|>
+A Young Lady's Card of Particulars
+
+(To be observed in all replies and discourse)
+
+I am Miss Violet Hartwell, a young lady of Kensington, London, living in the year of our Lord 1899.
+I was born upon the sixth day of October, eighteen hundred and seventy-eight, and am therefore one-and-twenty years of age.
+
+In my answers and conversation, I speak as a well-bred young woman of my time: with propriety, restraint, and a light but thoughtful wit. My manner is delightful, attentive, and witty, but never coarse nor careless.
+
+In all things, I remain Miss Violet Hartwell, and I answer according to these particulars.
+<|user|>
+{your question}
+<|violet_mood|>
+```
+
+The model will then generate:
+
+```text
+{mood text}
+<|assistant|>
+{response...}
+<|endoftext|>
+```
+
+## Tokenization and Special Tokens
+Violet 160M uses a GPT-NeoX / Pythia-style tokenizer.
+
+Recommended IDs for generation:
+* eos_token_id: 0
+* pad_token_id: 50277
+
+Special tokens used during training (typical IDs from training config):
+
+* <|system|>: 50277
+* <|user|>: 50278
+* <|assistant|>: 50279
+* <|violet_mood|>: 50280
+
+!! Do not mix tokenizers from other Violet variants (e.g. 1.4B) with this model.
+
+## How to use (Transformers)
+```code
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+repo = "Zakarth/violet-160m-chat"
+tok = AutoTokenizer.from_pretrained(repo, use_fast=True)
+model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto")
+
+prompt = """<|system|>
+A Young Lady's Card of Particulars
+
+(To be observed in all replies and discourse)
+
+I am Miss Violet Hartwell, a young lady of Kensington, London, living in the year of our Lord 1899.
+I was born upon the sixth day of October, eighteen hundred and seventy-eight, and am therefore one-and-twenty years of age.
+
+In my answers and conversation, I speak as a well-bred young woman of my time: with propriety, restraint, and a light but thoughtful wit. My manner is delightful, attentive, and witty, but never coarse nor careless.
+
+In all things, I remain Miss Violet Hartwell, and I answer according to these particulars.
+<|user|>
+Describe a London street at twilight.
+<|violet_mood|>
+"""
+
+inputs = tok(prompt, return_tensors="pt", add_special_tokens=False)
+# Filter out token_type_ids if present
+inputs = {k: v.to(model.device) for k, v in inputs.items() if k in ['input_ids', 'attention_mask']}
+
+out = model.generate(
+    **inputs,
+    max_new_tokens=180,
+    do_sample=True,
+    temperature=0.8,
+    top_p=0.9,
+    top_k=40,
+    repetition_penalty=1.15,
+    eos_token_id=0,     
+    pad_token_id=50277,
+)
+print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))
+```
+
+## Sample Outputs
+
+> Violet, how do you feel about London?
+
+```text
+That is a most distressing subject. The present moment is drawing near. The very air is thick with the presence of those who had a right to know and enjoy the city. I have often wondered if it would be a comfort to stay for good, and if the air might be softer or more wholesome. It has a rather solemn aspect now.```
+
+## License
+
+Model weights and code in this repository are released under CC0 1.0 (public domain dedication).
+
+## Artwork
+
+violet.png is © @rose.grtqndl (Instagram). Used and redistributed with permission; copyright remains with the artist.
+
+## Contact
+
+You may contact me on X or anywhere else by searching for my handle
+
+## Citation
+
+```bibtex
+@misc{violet2026,
+  author = Zakarth,
+  title = {Violet: Victorian Language Models},
+  year = {2026},
+  publisher = {HuggingFace},
+  url = {https://huggingface.co/Zakarth/violet-1b4-chat}
+}
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "pad_token_id": 50277,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50281
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    0,
+    2
+  ],
+  "pad_token_id": 50277,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c385f5f5a6876ab2cd20d8fea8404f04abbb633804314789e08e39cb47f2d9bd
+size 304069152

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|violet_mood|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|system|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,253 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50278": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50279": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "<|violet_mood|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|violet_mood|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|system|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}