Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+lora_tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qmodel.lora filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+  - bitnet
+  - lora
+  - ternary
+  - trillim
+  - cpu-inference
+base_model: microsoft/bitnet-b1.58-2B-4T-bf16
+---
+
+# BitNet-GenZ-LoRA-TRNQ
+
+Ternary-quantized LoRA adapter for [Trillim/BitNet-TRNQ](https://huggingface.co/Trillim/BitNet-TRNQ) that changes the model's style to speak in GenZ slang, packaged for the [Trillim DarkNet](https://huggingface.co/Trillim) inference engine.
+
+This adapter runs entirely on CPU — no GPU required.
+
+## Adapter Details
+
+| | |
+|---|---|
+| **Type** | LoRA adapter |
+| **Style** | GenZ slang |
+| **Architecture** | BitNet (BitNetForCausalLM) |
+| **Quantization** | Ternary ({-1, 0, 1}) |
+| **Platforms** | x86_64, aarch64 |
+| **Base model** | [Trillim/BitNet-TRNQ](https://huggingface.co/Trillim/BitNet-TRNQ) |
+| **Source model** | [microsoft/bitnet-b1.58-2B-4T-bf16](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T-bf16) |
+| **License** | MIT |
+
+## Usage
+
+```bash
+pip install trillim
+trillim pull Trillim/BitNet-TRNQ
+trillim pull Trillim/BitNet-GenZ-LoRA-TRNQ
+trillim chat Trillim/BitNet-TRNQ --lora Trillim/BitNet-GenZ-LoRA-TRNQ
+```
+
+This starts an interactive CLI chat.
+
+## What's in this repo
+
+| File | Description |
+|---|---|
+| `qmodel.lora` | Ternary-quantized LoRA weights in Trillim format |
+| `lora_tokenizer.json` | Tokenizer |
+| `lora_tokenizer_config.json` | Tokenizer configuration |
+| `lora_chat_template.jinja` | Chat template |
+| `trillim_config.json` | Trillim metadata |
+
+## License
+
+This adapter is released under the [MIT License](https://opensource.org/licenses/MIT), following the license of the source model.

lora_chat_template.jinja

@@ -0,0 +1 @@
+{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = message['role'] | capitalize + ': '+ message['content'] | trim + '<|eot_id|>' %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}

lora_tokenizer.json

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

lora_tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>"
+}

qmodel.lora

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22bfefec627721808a6b8fa507c9c8c6a747d2f7649684a53081bf81c846360c
+size 15974634

trillim_config.json

@@ -0,0 +1,12 @@
+{
+    "trillim_version": "0.1.0",
+    "format_version": 1,
+    "type": "lora_adapter",
+    "style": "genz-slang",
+    "description": "LoRA adapter that changes the model style to speak in GenZ slang",
+    "quantization": "ternary",
+    "source_model": "microsoft/bitnet-b1.58-2B-4T-bf16",
+    "base_model_dir": "BitNet",
+    "architecture": "bitnet",
+    "platforms": ["x86_64", "aarch64"]
+}