Upload 7 files

Venomoussaversai

README.md

@@ -1,3 +1,28 @@
----
-license: apache-2.0
----
+# Bun AI 🥟
+
+**Bun AI** is a lightweight, low-resource AI model designed for mobile and low-end devices.
+
+## Features
+- ✅ Under 100MB safetensors
+- ✅ INT8 quantized
+- ✅ Google Colab trained
+- ✅ Mobile-friendly
+- ✅ Open & minimal
+
+## Files
+- `bun_model.safetensors` — model weights
+- `vocab.json` — tokenizer vocabulary
+- `tokenizer_config.json` — tokenizer settings
+- `special_tokens_map.json` — special tokens
+
+## Intended Use
+- Education
+- Experiments
+- Edge devices
+- Offline inference
+
+## Limitations
+This is a small model and not suitable for high-accuracy tasks.
+
+## License
+MIT

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 50257
+}

bun_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828f3a3c088d32602d1914fdc984216c4e4e73b0b84b44af83220b745dec83f5
+size 137065

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}