Add MicroMixer-4-100K-TinyStories: TinyStories pretrain card + 3 epoch safetensors

README.md

@@ -0,0 +1,305 @@
+---
+license: apache-2.0
+library_name: pytorch
+language:
+  - en
+pipeline_tag: text-generation
+tags:
+  - mlp-mixer
+  - byte-level
+  - causal-lm
+  - attention-free
+  - ccd-mixer
+  - content-gated-dilated-conv
+  - tiny-stories
+  - pretrained-backbone
+  - micro-language-model
+  - sub-1m-parameters
+model_name: MicroMixer-4-100K-TinyStories
+datasets:
+  - roneneldan/TinyStories
+metrics:
+  - perplexity
+---
+
+<div align="center">
+
+<img src="https://raw.githubusercontent.com/llaa33219/MicroMixer-4/main/logo.svg" width="300" alt="MicroMixer-4 Logo"/>
+
+# MicroMixer-4-100K-TinyStories
+
+<img src="https://img.shields.io/badge/Parameters-95%2C084-blue?style=for-the-badge&logo=python&logoColor=white&color=%23007BFF" alt="Parameters"/>
+<img src="https://img.shields.io/badge/Architecture-CCD--Mixer-purple?style=for-the-badge&color=%23AE00FF" alt="Architecture"/>
+<img src="https://img.shields.io/badge/Stage-Pretrain-green?style=for-the-badge&color=%2300D620" alt="Pretrain"/>
+
+<br/>
+<br/>
+
+<table>
+<tr>
+<td align="center" style="padding: 20px;">
+<strong style="color: #007BFF; font-size: 1.2em;">Micro Language Model</strong><br/><em>Attention-Free • MLP-Only • Byte-Level • Content-Gated Dilated Convolution</em>
+</td>
+</tr>
+</table>
+
+[![GitHub](https://img.shields.io/badge/GitHub-MicroMixer--4-blue?style=for-the-badge&logo=github&color=%23007BFF)](https://github.com/llaa33219/MicroMixer-4)
+
+</div>
+
+<div style="background: linear-gradient(135deg, #007BFF22, #AE00FF22); padding: 20px; border-radius: 10px; border-left: 4px solid #007BFF;">
+
+## 📋 Overview
+
+**MicroMixer-4-100K-TinyStories** is a **95,084-parameter** pure MLP-Mixer causal language model — **no attention, no recurrence, no SSM** — **pretrained on [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories)** as part of the MicroMixer-4 **dataset-efficiency comparison study** ([analysis](https://github.com/llaa33219/MicroMixer-4/blob/main/DATASET_COMPARISON_ANALYSIS.md)). TinyStories is a corpus of ~200K short synthetic children's stories (GPT-3.5/4-generated, constrained grammar and vocabulary).
+
+⚠️ This repo is **pretrain-only** — it is **NOT FMSP-fine-tuned**. TinyStories contains free-flowing prose with no `User:`/`Assistant:` dialogue markers, so the FMSP answer-only cross-entropy recipe does not apply (there is no answer region to isolate). What you get is the **raw pretrained backbone** (seed 42, V76 recipe, 3 epochs). It continues stories; it does not answer questions or follow instructions.
+
+The backbone is **V87 Final**, the project's champion CCD-Mixer architecture (the V83-RPG champion frozen and scaled to six budgets). The 100K preset reproduces the champion recipe at its budget.
+
+</div>
+
+## 🏗️ Architecture
+
+<div align="center">
+
+```mermaid
+graph TD
+    A[Byte Input] --> B[Embed 256→48 NoPE]
+    B --> C[CCD-Mixer Block × 4]
+    C --> D[RMSNorm]
+    D --> E[LM Head Tied with Embed]
+    E --> F[Byte Output]
+
+    subgraph "CCD-Mixer Block"
+        X[Input 48] --> U["Linear d→2d → split v, g"]
+        U --> RP[Full RoPE on v AND g]
+        RP --> M["Shared-weight dilated conv<br/>dilations 1·2·4·8, k=65"]
+        M --> G["Per-position 4-way gate<br/>softmax(Linear_dil(x)/τ)"]
+        G --> O["W_o(v ⊙ g)  — zero-init"]
+        O --> SW[SwiGLU Channel-Mix]
+        SW --> RM[ReMixerLayer sidecar]
+    end
+
+    style A fill:#007BFF,color:#fff
+    style F fill:#00D620,color:#fff
+    style G fill:#AE00FF,color:#fff
+    style M fill:#FF6600,color:#fff
+```
+
+</div>
+
+### Model Configuration
+
+<table>
+<tr>
+<th style="background-color: #007BFF; color: white;">Parameter</th>
+<th style="background-color: #AE00FF; color: white;">Value</th>
+</tr>
+<tr><td>Hidden Dimension (d_model)</td><td><code>48</code></td></tr>
+<tr><td>Number of Blocks</td><td><code>4</code></td></tr>
+<tr><td>Token-Mix</td><td><code>GLCTokenMixCCD</code> (content-gated mixture of shared-weight dilated causal conv)</td></tr>
+<tr><td>Dilations</td><td><code>(1, 2, 4, 8)</code> — one shared depthwise kernel, zero extra conv params</td></tr>
+<tr><td>Depthwise Kernel Size</td><td><code>65</code></td></tr>
+<tr><td>RoPE</td><td>Full RoPE on <b>both</b> v and g (V76 "RPG" pattern)</td></tr>
+<tr><td>Channel-Mix</td><td><code>SwiGLU</code></td></tr>
+<tr><td>Sidecar</td><td><code>ReMixerLayer</code> per block (label_dim 16, pool_heads 4)</td></tr>
+<tr><td>Max Sequence Length</td><td><code>1024</code></td></tr>
+<tr><td>Vocabulary Size</td><td><code>256</code> (byte-level)</td></tr>
+<tr><td>Position Encoding</td><td>RoPE inside token-mix only; no position embedding table</td></tr>
+<tr><td>Normalization</td><td><code>RMSNorm</code> (pre-norm)</td></tr>
+<tr><td>Output Head</td><td>Tied with input embedding</td></tr>
+<tr><td>Zero-Init</td><td><code>W_o</code>, <code>dil_gate</code>, <code>log_τ</code> — silent at init</td></tr>
+</table>
+
+### Core Components
+
+```
+┌────────────────────────────────���─────────────────────────────┐
+│                 CCD-Mixer Block (×4)                        │
+│  u    = Linear(d → 2d)(x)                                    │
+│  v, g = u.chunk(2)                                           │
+│  v    = RoPE(v)          g = RoPE(g)      ← full-RoPE (RPG)  │
+│  y_d  = CausalDSConv(v, dilation=d) for d ∈ (1,2,4,8)        │
+│         └── ONE shared depthwise kernel                      │
+│  w(t) = softmax(Linear_dil(x)_t / τ)      ← per-position     │
+│  v    = Σ_d w_d(t) · y_d(t)             time-varying filter  │
+│  out  = W_o(v ⊙ g)                      ← W_o zero-init      │
+│  then SwiGLU channel-mix + ReMixerLayer sidecar              │
+└──────────────────────────────────────────────────────────────┘
+```
+
+The token-mix is **non-LTI** (time-varying): the per-position gate remixes four dilated views of the same kernel at every byte, which is the mechanism that breaks the periodic-orbit collapse that pure LTI mixers fall into — without attention and without a position table.
+
+---
+
+## 🎯 Generation Examples
+
+<div style="background-color: #FF050515; padding: 15px; border-radius: 8px; border-left: 4px solid #FF6600;">
+
+**Story-continuation probes** (raw text — no `User:/Assistant:` prefix, since TinyStories is a plain LM; greedy decoding, `repetition_penalty=1.2`, `no_repeat_ngram_size=4`, `max_new_tokens=200`):
+
+```
+[Prompt] Once upon a time, there was a little girl named Lily.
+[Output] She loved to play with her toys and she loved to play with her toys. One day, she was three yea…
+```
+
+<sub>coherent — on-topic story continuation in the TinyStories register</sub>
+
+```
+[Prompt] One day, a boy named Tom found a big red balloon.
+[Output] He was very happy and he wanted to go to the park. He was so happy and said, "I want to play wi…
+```
+
+<sub>coherent — on-topic story continuation in the TinyStories register</sub>
+
+```
+[Prompt] The sun was shining and the birds were singing.
+[Output] The bird was so happy and the birds were so happy. They were so happy to see a big box and the …
+```
+
+<sub>drifts — starts as story but falls into a repetitive loop</sub>
+
+```
+[Prompt] A little dog ran into the garden and saw
+[Output] a big box. It was a big box and said, "It's okay, I want to be careful."
+
+The bird said, "I wan…
+```
+
+<sub>drifts — starts as story but falls into a repetitive loop</sub>
+
+
+</div>
+
+---
+
+## 📊 Results
+
+<div style="background-color: #007BFF15; padding: 15px; border-radius: 8px; border-left: 4px solid #007BFF;">
+
+### Pretraining (TinyStories, V76 recipe, 3 epochs)
+
+| Metric | 1 ep | 2 ep | 3 ep |
+|--------|------|------|------|
+| Val PPL | 2.51 | 2.44 | **2.31** |
+
+AdamW lr 3e-3 · WSD (warmup 500) · wd 0.01 · bs 16 · seq 1024 · seed 42 · plain CE on non-pad bytes.
+
+### MicroMixer-4 TinyStories family (pretrain-only, all sizes)
+
+| Size | Params | 3ep Val PPL |
+|------|--------|------------|
+| 1M | 996,873 | **1.78** |
+| 500K | 491,742 | **1.90** |
+| 300K | 292,525 | **2.00** |
+| **100K** | 95,084 | **2.31** |
+| 50K | 48,684 | **2.60** |
+| 10K | 9,666 | **4.06** |
+
+<sub>Pretrain-only family — FMSP-based axes (chatter fluency, full-988 EM, q-relevance, OOD, unanswerable fabrication) are N/A: TinyStories has no `User:/Assistant:` markers, so the answer-only-CE recipe does not apply.</sub>
+
+</div>
+
+---
+
+## 📚 Training Data
+
+<div style="background-color: #00D62015; padding: 15px; border-radius: 8px; border-left: 4px solid #00D620;">
+
+1. **Pretraining**: [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories) — synthetic short stories generated by GPT-3.5/4 with a constrained vocabulary and simple grammar, ~200K stories sampled, flattened to 1024-byte sequences, 3 epochs. No `User:/Assistant:` dialogue structure.
+
+</div>
+
+---
+
+## 🔧 Usage
+
+### Files in this repository
+- `epoch_{0,1,2}.safetensors` — per-epoch pretrained backbone weights (pickle-free safetensors). **`epoch_2.safetensors` is the final (3rd-epoch) checkpoint.** No FMSP adapter — this is the plain backbone.
+
+### Load and generate (local clone)
+
+```python
+import torch
+from safetensors.torch import load_file
+from src.model_v87_final import MicroMixerV87Final, v87_final_100k
+from src.tokenizer import ByteTokenizer
+
+# Clone the code repository first:
+# git clone https://github.com/llaa33219/MicroMixer-4.git && cd MicroMixer-4
+
+cfg = v87_final_100k()
+model = MicroMixerV87Final(cfg)                         # plain backbone — NO attach_adapter (pretrain-only)
+model.load_state_dict(load_file("epoch_2.safetensors"), strict=True)
+model.eval()
+
+tok = ByteTokenizer()
+prompt = "Once upon a time, there was a little girl named Lily."
+ids = tok.encode(prompt)
+if ids and ids[-1] == tok.eos_token_id:
+    ids = ids[:-1]                       # ByteTokenizer appends EOS; the prompt must end open
+ids = torch.tensor([ids])
+with torch.no_grad():
+    out = model.generate(
+        ids, max_new_tokens=200,
+        temperature=0.0,                 # greedy
+        repetition_penalty=1.2,
+        no_repeat_ngram_size=4,
+        eos_token_id=tok.eos_token_id,
+    )
+print(prompt + tok.decode(out[0].tolist()[len(ids):]))
+```
+
+> Note the differences from the FMSP cards: (1) **no `attach_adapter`** — the backbone is loaded
+> as-is; (2) the prompt is **raw story text**, not the `User: …\n\nAssistant: ` dialogue format.
+
+### Load from Hugging Face Hub (no clone of the weights needed)
+
+```python
+import torch
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+from src.model_v87_final import MicroMixerV87Final, v87_final_100k
+
+REPO = "llaa33219/MicroMixer-4-100K-TinyStories"
+
+cfg = v87_final_100k()
+model = MicroMixerV87Final(cfg)
+model.load_state_dict(
+    load_file(hf_hub_download(REPO, "epoch_2.safetensors")), strict=True)
+model.eval()
+# ... continue a story as above
+```
+
+---
+
+## ⚠️ Limitations
+
+<div style="background-color: #FF050515; padding: 15px; border-radius: 8px; border-left: 4px solid #FF0505;">
+
+| Limitation | Description |
+|------------|-------------|
+| **Pretrain-only — no instruction/QA ability** | Not FMSP-fine-tuned; it only continues TinyStories-style prose. It cannot answer questions or follow instructions. |
+| **Micro parameters** | 95,084 parameters; capacity is the binding constraint |
+| **Knows only TinyStories** | Distribution is synthetic children's stories; no real-world knowledge |
+| **Byte-level noise** | 256-vocab byte tokenizer; PPL not comparable to BPE baselines |
+| **Research use only** | Architecture/pretraining research artifact, not a production model |
+
+</div>
+
+---
+
+## 🧬 Context
+
+This is the **100K** TinyStories-pretrained arm of the **dataset-efficiency comparison study** in the [MicroMixer-4](https://github.com/llaa33219/MicroMixer-4) project — the pretrain-only third corpus alongside the UltraChat and SmolTalk2 FMSP arms (TinyStories is excluded from the FMSP/eval battery because it has no `User:/Assistant:` markers). Sibling repos: `llaa33219/{MicroMixer-4,MicroT-test1}-{1M..10K}-TinyStories`, plus the UltraChat/SmolTalk2 arms `…-{UltraChat,SmolTalk2}` and the discord-pretrained baselines `llaa33219/{MicroMixer-4,MicroT-test1}-{1M..10K}`. Full analysis: [DATASET_COMPARISON_ANALYSIS.md](https://github.com/llaa33219/MicroMixer-4/blob/main/DATASET_COMPARISON_ANALYSIS.md).
+
+---
+
+<div align="center">
+
+[![GitHub](https://img.shields.io/badge/Back_to_Repository-MicroMixer--4-blue?style=for-the-badge&logo=github&color=%23007BFF)](https://github.com/llaa33219/MicroMixer-4)
+
+<sub>Part of the <a href="https://github.com/llaa33219/MicroMixer-4">MicroMixer-4</a> research project — V87 Final (CCD-Mixer) family, 100K preset, TinyStories pretraining (pretrain-only)</sub>
+
+</div>

epoch_0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ae9183fec5c2c1557fc4f83fedd10608e44f74d6061dc476829ac2990b744c
+size 407168

epoch_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37081ee660d21309a1ee417702632ae2b061f3e0040c9f46fe47c04f31b0b189
+size 407168

epoch_2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c680a44e23bdca7c6934181782ff70d1d07c104a918f7393f14fecda064866c
+size 407168