Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,24 @@ 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
+tinybpe1m.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.F16.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.F32.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
+tinybpe1m.TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,115 @@
+---
+license: mit
+base_model: karpathy/tinyllamas
+tags:
+- llama2
+- gguf
+- safetensors
+- transformers
+- tinyllamas
+- validation
+- test-suite
+---
+
+# TinyStories Llama2 1M (tinybpe1m) GGUF & HF Validation Suite
+
+This repository provides ultra-lightweight Llama2 model files across various formats (both **GGUF** and **Hugging Face / Safetensors**), trained on the TinyStories dataset and optimized for testing and validation.
+
+### Why this repository exists
+When developing a custom LLM inference engine, debugging with a full-sized model is slow. This suite offers a true **1M parameter scale model** (~0.5MB to ~4MB depending on the quantization format), allowing developers to validate their loaders, serialization, quantization kernels, and inference logic step-by-step with maximum efficiency.
+
+### Difference from `tiny1m`
+This is a **BPE-based model variant**. Unlike the standard `tiny1m` model, this model is **NOT compatible with `llama2.c`**. 
+The custom SentencePiece BPE tokenizer utilized here relies on the `byte_fallback` mechanism to handle unknown characters. Because `llama2.c`'s simplified native C loader/tokenizer cannot interpret or process `byte_fallback` routines, text generation will fail or corrupt in that environment. This suite is strictly designed and optimized for **`llama.cpp` (GGUF)** and **Hugging Face `transformers` (Python)** execution.
+
+---
+
+## 📂 Repository Structure & File Descriptions
+
+### 1. GGUF Formats (Root Directory `./`)
+A comprehensive validation suite converted for `llama.cpp` and compatible engines. The tokenizer vocabulary and special tokens are fully embedded within each GGUF binary. Every compiled quantization variant available in the root directory is explicitly covered below:
+
+| Filename(s) / Wildcard Pattern | Type | Size | Purpose / Validation Target |
+| :--- | :--- | :--- | :--- |
+| **`tinybpe1m.F32.gguf`** | `F32` | ~4.0 MB | **Baseline Test.** Validates GGUF parsing, tensor layout, matrix multiplication, RoPE, and Attention logic without dequantization overhead. |
+| **`tinybpe1m.F16.gguf`**<br>**`tinybpe1m.BF16.gguf`** | `F16`<br>`BF16` | ~2.0 MB | **Half-Precision Test.** Validates 16-bit floating point loading, type casting, and inference stability. |
+| **`tinybpe1m.Q8_0.gguf`** | `Q8_0` | ~1.1 MB | **Quantization Level 1.** Validates block-based uniform scaling with 32 elements. |
+| **`tinybpe1m.Q4_0.gguf`**<br>**`tinybpe1m.Q4_1.gguf`** | `Q4_0`<br>`Q4_1` | ~0.7 MB | **Quantization Level 2.** Validates classic 4-bit linear quantization and bit-unpacking logic. |
+| **`tinybpe1m.Q2_K.gguf`** | `Q2_K` | ~0.5 MB | **Standard K-Quant (2-bit).** Validates 2-bit super-block quantization parsing. |
+| **`tinybpe1m.Q3_K_*.gguf`**<br>↳ *`tinybpe1m.Q3_K_S.gguf`*<br>↳ *`tinybpe1m.Q3_K_M.gguf`*<br>↳ *`tinybpe1m.Q3_K_L.gguf`* | `Q3_K` | ~0.6 MB | **Standard K-Quant (3-bit).** Validates Small, Medium, and Large sub-variants of 3-bit multi-block structures. |
+| **`tinybpe1m.Q4_K_*.gguf`**<br>↳ *`tinybpe1m.Q4_K_S.gguf`*<br>↳ *`tinybpe1m.Q4_K_M.gguf`* | `Q4_K` | ~0.7 MB | **Standard K-Quant (4-bit).** Validates Small and Medium sub-variants of modern 4-bit super-block structural parsing. |
+| **`tinybpe1m.Q5_K_*.gguf`**<br>↳ *`tinybpe1m.Q5_K_S.gguf`*<br>↳ *`tinybpe1m.Q5_K_M.gguf`* | `Q5_K` | ~0.8 MB | **Standard K-Quant (5-bit).** Validates Small and Medium sub-variants of 5-bit mixed precision super-blocks. |
+| **`tinybpe1m.Q6_K.gguf`** | `Q6_K` | ~0.9 MB | **Standard K-Quant (6-bit).** Validates 6-bit high-fidelity super-block quantization. |
+| **`tinybpe1m.IQ3_*.gguf`**<br>↳ *`tinybpe1m.IQ3_XXS.gguf`*<br>↳ *`tinybpe1m.IQ3_S.gguf`* | `I-Quants` | ~0.5 MB | **Importance Quants (3-bit).** Non-linear 3-bit importance quantization targeting lookup table (codebook) decoding logic. |
+| **`tinybpe1m.IQ4_*.gguf`**<br>↳ *`tinybpe1m.IQ4_NL.gguf`*<br>↳ *`tinybpe1m.IQ4_XS.gguf`* | `I-Quants` | ~0.6 MB | **Importance Quants (4-bit).** Non-linear 4-bit importance quantization variants (Non-Linear and Extra Small). |
+| **`tinybpe1m.TQ1_0.gguf`**<br>**`tinybpe1m.TQ2_0.gguf`** | `Ternary` | ~0.4 MB | **Experimental.** Ternary (-1, 0, 1) state quantization for cutting-edge engine testing. |
+
+### 2. Hugging Face Native Format (`./hf/`)
+This directory contains the standard files required to load the model using the PyTorch `transformers` library:
+* **`hf/model.safetensors`**: The raw, unquantized model weights stored securely in Safetensors format.
+* **`hf/config.json`**: The architectural configuration file defining hyperparameters (layers, heads, dimensions).
+* **`hf/generation_config.json`**: Default parameters optimized for text generation (temperature, top_p, etc.).
+* **`hf/tokenizer.model`**: The custom 512-vocab SentencePiece tokenizer model file required for Python-side encoding/decoding.
+
+---
+
+## 🚀 Usage Examples
+
+### A. Running GGUF via llama.cpp
+To verify your local setup or test custom execution backends using the official native utilities:
+```bash
+./llama-cli -m tinybpe1m.Q4_K_M.gguf -p "Tom and Jerry are " -n 64 --temp 0.0
+
+```
+
+### B. Loading Hugging Face Formats via Python
+
+You can import the Hugging Face variant directly into Python using the `transformers` library.
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+repo_id = "shibatch/tinybpe1m"
+
+# The library automatically loads from the hf/ subfolder
+tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder="hf")
+model = AutoModelForCausalLM.from_pretrained(repo_id, subfolder="hf")
+
+prompt = "Tom and Jerry are "
+inputs = tokenizer(prompt, return_tensors="pt")
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs, 
+        max_new_tokens=64, 
+        do_sample=False,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+```
+
+---
+
+## 📝 Model Specifications
+
+The network architecture features an unshared output layer (`lm_head`) to keep memory structures consistent with standard Llama 2 definitions. Thanks to the highly optimized 512 vocabulary size, the token embedding and output layers remain extremely lightweight.
+
+* **Architecture:** Llama 2 (Scaled-down variant)
+* **Dataset:** TinyStories
+* **Total Parameters:** ~1M (Exactly 896,256 parameters)
+* **Vocabulary Size:** 512 (Custom SentencePiece BPE Tokenizer with `byte_fallback` enabled)
+* **Hidden Size (`hidden_size`):** 128
+* **Number of Hidden Layers (`num_hidden_layers`):** 4
+* **Number of Attention Heads (`num_heads`):** 2
+* **Number of Key-Value Heads (`num_kv_heads`):** 2
+* **Intermediate Size (`intermediate_size`):** 352
+* **Max Position Embeddings (`max_position_embeddings`):** 256
+
+## 📜 Acknowledgments & License
+
+* **Original Implementation:** Inspired by Andrej Karpathy's `llama2.c` project.
+* **Dataset:** TinyStories dataset.
+* **License:** **MIT License**. You are free to use, modify, and distribute these assets for any purpose.

hf/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 352,
+  "max_position_embeddings": 256,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 2,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.9.0",
+  "use_cache": false,
+  "vocab_size": 512
+}

hf/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 2,
+  "transformers_version": "5.9.0",
+  "use_cache": true
+}

hf/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39c5ff9c53cbda295e88a57bb25009f6a23045555cb76a1d66501230d001a7bb
+size 3744288

hf/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b432388a969eb49dbb64e25d9ebcffd9de04919f88b13f7805cde6c8ad6684f
+size 247523

tinybpe1m.BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd2563eaf811ae1d12a3f38365a8315601d3539c864734fd59b600820ae59e1
+size 1886240

tinybpe1m.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d21f397845a9ce92f18a55c7f0698a4016ef475041b996fd5a39b3f30d8d89
+size 1886240

tinybpe1m.F32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b6c2075b1e774643faaf46adaeea54b8500d24c6a903350dbf5480e6d11a9e
+size 3754016

tinybpe1m.IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef0a3c2116a41a1b1d78f6768bef230034c57e2bb1650ec04d5dfcc200e512d
+size 576544

tinybpe1m.IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfae34d0fb9d30d0ee4156702dc6b80c31d2240a3c99b76f2f27ad24d2e5680
+size 576544

tinybpe1m.IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d377c65479f5a62e91a1eca730d884d9fe164e0808a8fbed74df119ea81c7e1
+size 576544

tinybpe1m.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44279e858ae0f4a7a3b3cf4a4f8031148acfb514eb0bf4bfa7a13d40a6ce62cc
+size 576544

tinybpe1m.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417e611d483bbf79802cb23cdc22bbd9339a0cbc95136f2b2708475936a1a7f9
+size 576544

tinybpe1m.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5e249341719b7de52ba7714445885103c720cc03a9167c1bdb717bb28d093a
+size 634912

tinybpe1m.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cbac852529e34c3753891143f8bb09e31b23140a2496ba2271f4fecc4d81d2
+size 617504

tinybpe1m.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac6e38760029f893db587041f154648827994c5ebf85a078698eb16ba4bf741
+size 576544

tinybpe1m.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f37ac9de3a907abf512ce20ac4545de5091a2509e059289fb1eefde14342d79
+size 576544

tinybpe1m.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7c6cd0e27bce416487e229be783ed95ab08bd2eb48f23a982141fa0110b1ea
+size 630816

tinybpe1m.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f5bcd15b90c9e2937dd0551a875a0ae45865617253e0a4c337b0eceb8e36bd
+size 731168

tinybpe1m.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aca8ddadfe86ab9ee0c5d6bbeb40a91c3bcf673bc32e372ec6bd4db6a76b8a3
+size 689184

tinybpe1m.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320ede8f17d2c0007754f2a4d8668b86c7f01dc52efde3c90e468b9b6b585f0a
+size 777760

tinybpe1m.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a595f24fbefd6686996ddf637a02c007df148a50303503d8087d57bb1d87cc
+size 739360

tinybpe1m.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd581fbd61a6404bdf74e02efa6c8d11611f7840bfc1c30a3e78e0c9dcd41db7
+size 1010720

tinybpe1m.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbde54169767f110f1ccedf26b4f42ad219d902d83ea4f44ec8176f33c2d0cf
+size 1010720

tinybpe1m.TQ1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944bfa1694ae5683b5e5e39f496e71f3ea4c0240d5d1a7cef53bf4fda699f2aa
+size 584736

tinybpe1m.TQ2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c653e44063a5589d748658319b3e8b03a5c8e35dc1ff9f2c6091b09ded2d44
+size 584736