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

LICENSE

@@ -0,0 +1,121 @@
+Creative Commons Legal Code
+
+CC0 1.0 Universal
+
+    CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
+    LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
+    ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
+    INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
+    REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
+    PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
+    THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
+    HEREUNDER.
+
+Statement of Purpose
+
+The laws of most jurisdictions throughout the world automatically confer
+exclusive Copyright and Related Rights (defined below) upon the creator
+and subsequent owner(s) (each and all, an "owner") of an original work of
+authorship and/or a database (each, a "Work").
+
+Certain owners wish to permanently relinquish those rights to a Work for
+the purpose of contributing to a commons of creative, cultural and
+scientific works ("Commons") that the public can reliably and without fear
+of later claims of infringement build upon, modify, incorporate in other
+works, reuse and redistribute as freely as possible in any form whatsoever
+and for any purposes, including without limitation commercial purposes.
+These owners may contribute to the Commons to promote the ideal of a free
+culture and the further production of creative, cultural and scientific
+works, or to gain reputation or greater distribution for their Work in
+part through the use and efforts of others.
+
+For these and/or other purposes and motivations, and without any
+expectation of additional consideration or compensation, the person
+associating CC0 with a Work (the "Affirmer"), to the extent that he or she
+is an owner of Copyright and Related Rights in the Work, voluntarily
+elects to apply CC0 to the Work and publicly distribute the Work under its
+terms, with knowledge of his or her Copyright and Related Rights in the
+Work and the meaning and intended legal effect of CC0 on those rights.
+
+1. Copyright and Related Rights. A Work made available under CC0 may be
+protected by copyright and related or neighboring rights ("Copyright and
+Related Rights"). Copyright and Related Rights include, but are not
+limited to, the following:
+
+  i. the right to reproduce, adapt, distribute, perform, display,
+     communicate, and translate a Work;
+ ii. moral rights retained by the original author(s) and/or performer(s);
+iii. publicity and privacy rights pertaining to a person's image or
+     likeness depicted in a Work;
+ iv. rights protecting against unfair competition in regards to a Work,
+     subject to the limitations in paragraph 4(a), below;
+  v. rights protecting the extraction, dissemination, use and reuse of data
+     in a Work;
+ vi. database rights (such as those arising under Directive 96/9/EC of the
+     European Parliament and of the Council of 11 March 1996 on the legal
+     protection of databases, and under any national implementation
+     thereof, including any amended or successor version of such
+     directive); and
+vii. other similar, equivalent or corresponding rights throughout the
+     world based on applicable law or treaty, and any national
+     implementations thereof.
+
+2. Waiver. To the greatest extent permitted by, but not in contravention
+of, applicable law, Affirmer hereby overtly, fully, permanently,
+irrevocably and unconditionally waives, abandons, and surrenders all of
+Affirmer's Copyright and Related Rights and associated claims and causes
+of action, whether now known or unknown (including existing as well as
+future claims and causes of action), in the Work (i) in all territories
+worldwide, (ii) for the maximum duration provided by applicable law or
+treaty (including future time extensions), (iii) in any current or future
+medium and for any number of copies, and (iv) for any purpose whatsoever,
+including without limitation commercial, advertising or promotional
+purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
+member of the public at large and to the detriment of Affirmer's heirs and
+successors, fully intending that such Waiver shall not be subject to
+revocation, rescission, cancellation, termination, or any other legal or
+equitable action to disrupt the quiet enjoyment of the Work by the public
+as contemplated by Affirmer's express Statement of Purpose.
+
+3. Public License Fallback. Should any part of the Waiver for any reason
+be judged legally invalid or ineffective under applicable law, then the
+Waiver shall be preserved to the maximum extent permitted taking into
+account Affirmer's express Statement of Purpose. In addition, to the
+extent the Waiver is so judged Affirmer hereby grants to each affected
+person a royalty-free, non transferable, non sublicensable, non exclusive,
+irrevocable and unconditional license to exercise Affirmer's Copyright and
+Related Rights in the Work (i) in all territories worldwide, (ii) for the
+maximum duration provided by applicable law or treaty (including future
+time extensions), (iii) in any current or future medium and for any number
+of copies, and (iv) for any purpose whatsoever, including without
+limitation commercial, advertising or promotional purposes (the
+"License"). The License shall be deemed effective as of the date CC0 was
+applied by Affirmer to the Work. Should any part of the License for any
+reason be judged legally invalid or ineffective under applicable law, such
+partial invalidity or ineffectiveness shall not invalidate the remainder
+of the License, and in such case Affirmer hereby affirms that he or she
+will not (i) exercise any of his or her remaining Copyright and Related
+Rights in the Work or (ii) assert any associated claims and causes of
+action with respect to the Work, in either case contrary to Affirmer's
+express Statement of Purpose.
+
+4. Limitations and Disclaimers.
+
+ a. No trademark or patent rights held by Affirmer are waived, abandoned,
+    surrendered, licensed or otherwise affected by this document.
+ b. Affirmer offers the Work as-is and makes no representations or
+    warranties of any kind concerning the Work, express, implied,
+    statutory or otherwise, including without limitation warranties of
+    title, merchantability, fitness for a particular purpose, non
+    infringement, or the absence of latent or other defects, accuracy, or
+    the present or absence of errors, whether or not discoverable, all to
+    the greatest extent permissible under applicable law.
+ c. Affirmer disclaims responsibility for clearing rights of other persons
+    that may apply to the Work or any use thereof, including without
+    limitation any person's Copyright and Related Rights in the Work.
+    Further, Affirmer disclaims responsibility for obtaining any necessary
+    consents, permissions or other rights required for any use of the
+    Work.
+ d. Affirmer understands and acknowledges that Creative Commons is not a
+    party to this document and has no duty or obligation with respect to
+    this CC0 or use of the Work.

NOTICE

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

README.md

@@ -1,3 +1,160 @@
 ---
+language:
+- en
+library_name: transformers
+tags:
+- text-generation
+- gpt_neox
+- roleplay
+- victorian
 license: cc0-1.0
 ---
+
+# Violet 1B4 Completion
+
+![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 intended to behave as if unfamiliar with modern society and events (with occasional OCR artifacts—see Known Issues). This is the completion version of the model, so if you were looking for the Chat version, you should check out [Violet 1b4 Chat](https://huggingface.co/zakarth/violet-1b4-chat)
+
+She is intended for **creative writing**, **roleplay**, **period-appropriate correspondence**, and **Victorian etiquette**. 
+
+- Architecture: `GPTNeoXForCausalLM`
+- Parameters: ~1.41B
+- Context length: 4096
+- Vocab size: 24014
+- Tokenizer: `PreTrainedTokenizerFast`
+
+## Intended Use
+**Good for**
+- Victorian-flavored narrative completions
+
+**Not good for**
+- Contemporary factual Q&A
+- Medical/legal/financial advice
+
+## Known Issues / Limitations
+- 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”).
+- Training data includes UK and US English from the era.
+
+## 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:
+- A structured “mood” line as part of chat output (1b4 chat and 160m chat only)
+- Built-in character design and prompt protocol (1b4 chat and 160m chat only)
+- A custom Victorian-era tokenizer
+
+Violet was built on a corpus spanning 1800–1899 sourced from Project Gutenberg, the Internet Archive, the British National Library, and other archives.
+
+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-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
+The morning fog had scarcely lifted when
+```
+
+The model will then generate:
+
+```text
+{response...}
+```
+
+## Tokenization and Special Tokens
+Violet 1b4 was trained on a custom tokenizer specific for Victorian text.
+
+Recommended IDs for generation:
+* eos_token_id: 0
+* pad_token_id: 1
+
+Special tokens used during training (typical IDs from training config):
+
+* <|system|>: 24000
+* <|user|>: 24001
+* <|assistant|>: 24002
+* <|violet_mood|>: 24005
+
+!! Do not mix tokenizers from other Violet variants (e.g. 160M) with this model.
+
+## How to use (Transformers)
+```code
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+repo = "Zakarth/violet-1b4-chat"
+tok = AutoTokenizer.from_pretrained(repo, use_fast=True)
+model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto")
+
+prompt = "The morning fog had scarcely lifted when"""
+
+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=1,  
+)
+print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))
+```
+
+## Sample Outputs
+
+> The morning fog had scarcely lifted when
+
+```text
+The morning fog had scarcely lifted whenthe first
+light streamed through the window, and before it was quite light the
+flood of rain came on with a suddenness which seemed to scorch up the
+roof. The lightning was as bright as ever, but there were only three or
+four flashes in the sky--a bright flash like a meteor--and the thunder
+was not so loud nor so deafening as usual.
+
+At last the storm ceased. The storm was over; the stars shone out; the
+thunder rolled away, leaving the clouds behind it in an impenetrable
+haze, which at once became visible, and soon they disappeared. The wind
+blew with fury, driving the snow and ice from off the roofs of the houses
+```
+
+## 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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 26,
+  "pad_token_id": 1,
+  "partial_rotary_factor": 1.0,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 24014
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    0,
+    2
+  ],
+  "pad_token_id": 1,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e4c5287f51bf205c4784acc8c8a0fae7d6ef4214b30a98c69b3f1e54b3949b
+size 2815398440

special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|violet|>",
+    "<|violet_rpm|>",
+    "<|violet_mood|>",
+    "<|violet_act|>",
+    "<|doc|>",
+    "<|novel|>",
+    "<|letter|>",
+    "<|periodical|>",
+    "<|title|>",
+    "<|author|>",
+    "<|year|>"
+  ],
+  "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": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,164 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24000": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24001": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24002": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24003": {
+      "content": "<|violet|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24004": {
+      "content": "<|violet_rpm|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24005": {
+      "content": "<|violet_mood|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24006": {
+      "content": "<|violet_act|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24007": {
+      "content": "<|doc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24008": {
+      "content": "<|novel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24009": {
+      "content": "<|letter|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24010": {
+      "content": "<|periodical|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24011": {
+      "content": "<|title|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24012": {
+      "content": "<|author|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24013": {
+      "content": "<|year|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|violet|>",
+    "<|violet_rpm|>",
+    "<|violet_mood|>",
+    "<|violet_act|>",
+    "<|doc|>",
+    "<|novel|>",
+    "<|letter|>",
+    "<|periodical|>",
+    "<|title|>",
+    "<|author|>",
+    "<|year|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|unk|>"
+}