初始化项目，由ModelHub XC社区提供模型
Model: mrothroc/mixlab-gpt2-strict-small-replica Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz 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
|
||||
116
README.md
Normal file
116
README.md
Normal file
@@ -0,0 +1,116 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- babylm
|
||||
- babylm-2026
|
||||
- gpt2
|
||||
- mixlab
|
||||
- reproduction
|
||||
- causal-language-model
|
||||
datasets:
|
||||
- BabyLM-community/BabyLM-2026-Strict-Small
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# mixlab reproduction of the BabyLM 2026 GPT-2 Strict-Small baseline
|
||||
|
||||
A faithful, from-scratch reproduction of the **official BabyLM 2026 GPT-2 *Strict-Small* baseline**
|
||||
([`BabyLM-community/babylm-baseline-10m-gpt2`](https://huggingface.co/BabyLM-community/babylm-baseline-10m-gpt2)),
|
||||
trained entirely on a **single Apple M1 Max GPU** with [**mixlab**](https://github.com/mrothroc/mixlab), an
|
||||
open Metal/MLX trainer, on the same 10M-word 2026 Strict-Small corpus the organizers use (a data-identical
|
||||
reproduction).
|
||||
|
||||
This model reproduces the baseline as a reproducibility and efficiency study. The companion GitHub repo has the
|
||||
full recipe, configs, scripts, and per-task eval reports:
|
||||
[mixlab-babylm-gpt2](https://github.com/mrothroc/mixlab-babylm-gpt2).
|
||||
|
||||
## Faithfulness: per-component reproduction
|
||||
|
||||
For the six zero-shot components, both the reference baseline and this reproduction were scored through one
|
||||
identical eval harness ([`babylm-org/babylm-eval`](https://github.com/babylm-org/babylm-eval) @ `3bf5142`,
|
||||
causal backend); the reference column there is our within-harness re-evaluation of the official baseline, and
|
||||
it reproduces the official published numbers. GLUE is the exception (see †).
|
||||
|
||||
| Component | Reference baseline | This reproduction | Δ |
|
||||
|---|---:|---:|---:|
|
||||
| BLiMP | 66.35 | 65.86 | −0.49 |
|
||||
| BLiMP-supplement | 57.07 | 58.04 | +0.97 |
|
||||
| EWoK | 49.23 | 49.30 | +0.07 |
|
||||
| COMPS | 51.72 | 52.05 | +0.33 |
|
||||
| reading (eye+SPR) | 6.50 | 7.15 | +0.65 |
|
||||
| GLUE (macro) † | 63.62 | 64.15 | +0.53 |
|
||||
| entity tracking ‡ | 13.90 | 25.99 | +12.09 |
|
||||
|
||||
Within about one point on every stable component.
|
||||
|
||||
† **GLUE**: the reproduction was fine-tuned and scored here; the reference (63.62) is the official published
|
||||
baseline (GPT-2 model card per-task GLUE), not re-fine-tuned locally.
|
||||
‡ **entity tracking** is a length-bias artifact (both models near chance); the gap is not a real capability
|
||||
difference and is excluded from any aggregate claim. AoA (age-of-acquisition) is forfeited (0): the board scores it from a per-checkpoint surprisal trajectory submitted with the predictions, which this reproduction's submission does not include. Separately, the AoA scorer has a confirmed, still-open upstream bug — a log2/bits random-chance baseline with a hardcoded ~300k vocabulary instead of the model's actual size ([babylm-org/babylm-eval#2](https://github.com/babylm-org/babylm-eval/issues/2)) — which doesn't zero out small-vocab models (the reference scores 35.68 through it) but makes the metric noise-dominated and extraction-sensitive (one fixed model spans ~12–36). For both reasons we report per-component and exclude AoA.
|
||||
|
||||
## Architecture (read from the weights)
|
||||
|
||||
The exact architecture is in this repo's
|
||||
[`config.json`](https://huggingface.co/mrothroc/mixlab-gpt2-strict-small-replica/blob/main/config.json) (the
|
||||
exported HF model config); the full mixlab spec (architecture **and** training recipe) is in
|
||||
[`training_config.mixlab.json`](https://huggingface.co/mrothroc/mixlab-gpt2-strict-small-replica/blob/main/training_config.mixlab.json).
|
||||
|
||||
A vanilla GPT-2 Small, ≈98M params (16,384 vocab × 768 dim, tied to the output head). The reference model
|
||||
card's "124M" is the 50k-vocab number; with the 16k BabyLM vocab the real model is 98,425,344 params.
|
||||
|
||||
- 12 layers, hidden 768, 12 heads, context 1024, tied embeddings
|
||||
- Learned absolute position embeddings (GPT-2 WPE)
|
||||
- GELU (`gelu_new`, tanh approximation) feed-forward, intermediate 3072
|
||||
- Pre-LayerNorm (eps 1e-5) with affine weight+bias, plus a final LayerNorm
|
||||
- Standard causal self-attention with attention + projection biases
|
||||
- Dropout 0.1 (embedding, residual, attention), applied during training
|
||||
- GPT-2 weight initialization: normal(0, 0.02), residual `c_proj` scaled by 1/√(2·n_layer)
|
||||
|
||||
Exported as a native `GPT2LMHeadModel`; native↔HF logit parity verified (≈3e-8).
|
||||
|
||||
## Training
|
||||
|
||||
- **Trainer:** mixlab v0.40.0 (`-mode arch`), Metal/MLX, single Apple **M1 Max** (32-core GPU, 64 GB unified memory), ≈11h wall-clock (varies across Apple chip generations), seed 42, fp32
|
||||
- **Data:** the 2026 Strict-Small corpus (≈10M words → 18M tokens), full corpus, tokenized whole-block then
|
||||
sliced into 512-token chunks; each chunk framed as `<s>` + chunk + `</s>` (the reference convention)
|
||||
- **Optimizer:** AdamW (betas 0.9/0.999, eps 1e-8), lr 5e-5, **no weight decay**, grad-clip 1.0
|
||||
- **Schedule:** 21,300 steps (~9.7 epochs over the ~18M-token corpus), batch 16 × 514-token sequences (512 content + `<s>`/`</s>`), warmup 213 + cosine decay
|
||||
- **Tokenizer:** the reference 16,384-vocab tokenizer (`<unk>`=0, `<s>`=1, `</s>`=2, `<pad>`=3, `<mask>`=4)
|
||||
|
||||
## Use
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
tok = AutoTokenizer.from_pretrained("mrothroc/mixlab-gpt2-strict-small-replica")
|
||||
m = AutoModelForCausalLM.from_pretrained("mrothroc/mixlab-gpt2-strict-small-replica")
|
||||
```
|
||||
|
||||
## Reproduce
|
||||
|
||||
The full recipe (data prep, train, export, parity, eval), configs, and scripts are in the
|
||||
[companion GitHub repo](https://github.com/mrothroc/mixlab-babylm-gpt2). One command per step; ≈11h training
|
||||
on an M1 Max.
|
||||
|
||||
## Implementation Notes
|
||||
|
||||
- This reproduces the **2026** GPT-2 baseline on the **2026** Strict-Small corpus (data-identical).
|
||||
- **Weight initialization** was the remaining mismatch: arch, recipe, corpus, and forward (export) parity all
|
||||
matched the reference as far as verified, yet BLiMP was 5.7 points low until the GPT-2 init scheme (normal
|
||||
0.02 + residual c_proj scaling) was
|
||||
matched. Validation loss gave no warning (across our runs it did not track BLiMP), so it does not reveal an
|
||||
init-driven generalization gap.
|
||||
- Trained in fp32 on Apple silicon; numerical differences from a CUDA run are not characterized.
|
||||
- Single training seed; the official seed is unknown, so a residual point or two on BLiMP is expected.
|
||||
- Zero-shot faithfulness within one pinned harness; GLUE compares our fine-tune to the official published
|
||||
reference score. Absolute scores can differ across harness versions.
|
||||
|
||||
## Links
|
||||
|
||||
- Trainer: [mixlab](https://github.com/mrothroc/mixlab)
|
||||
- Reference: [`BabyLM-community/babylm-baseline-10m-gpt2`](https://huggingface.co/BabyLM-community/babylm-baseline-10m-gpt2)
|
||||
- Companion recipe: [mixlab-babylm-gpt2](https://github.com/mrothroc/mixlab-babylm-gpt2)
|
||||
|
||||
For the story behind it, read [I Built an ML Architecture Lab in Go](https://michael.roth.rocks/blog/mixlab/).
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"model_type": "gpt2",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"vocab_size": 16384,
|
||||
"n_positions": 1024,
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 768,
|
||||
"n_layer": 12,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"activation_function": "gelu_new",
|
||||
"resid_pdrop": 0.1,
|
||||
"embd_pdrop": 0.1,
|
||||
"attn_pdrop": 0.1,
|
||||
"layer_norm_epsilon": 0.00001,
|
||||
"initializer_range": 0.02,
|
||||
"scale_attn_weights": true,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"tie_word_embeddings": true,
|
||||
"pad_token_id": 3,
|
||||
"eos_token_id": 2,
|
||||
"bos_token_id": 1,
|
||||
"unk_token_id": 0
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1617b113ef12b1eb787d6a34688456539fb79830b0d0b25ae93e8d5f0a06b8fc
|
||||
size 444048248
|
||||
7
special_tokens_map.json
Normal file
7
special_tokens_map.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token": "\u003cs\u003e",
|
||||
"eos_token": "\u003c/s\u003e",
|
||||
"mask_token": "\u003cmask\u003e",
|
||||
"pad_token": "\u003cpad\u003e",
|
||||
"unk_token": "\u003cunk\u003e"
|
||||
}
|
||||
81029
tokenizer.json
Normal file
81029
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
60
tokenizer_config.json
Normal file
60
tokenizer_config.json
Normal file
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "\u003cunk\u003e",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "\u003cs\u003e",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "\u003c/s\u003e",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "\u003cpad\u003e",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "\u003cmask\u003e",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "\u003cs\u003e",
|
||||
"bos_token_id": 1,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"cls_token": null,
|
||||
"eos_token": "\u003c/s\u003e",
|
||||
"eos_token_id": 2,
|
||||
"extra_special_tokens": {},
|
||||
"mask_token": "\u003cmask\u003e",
|
||||
"mask_token_id": 4,
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "\u003cpad\u003e",
|
||||
"pad_token_id": 3,
|
||||
"sep_token": null,
|
||||
"tokenizer_class": "PreTrainedTokenizer",
|
||||
"unk_token": "\u003cunk\u003e",
|
||||
"unk_token_id": 0
|
||||
}
|
||||
151
training_config.mixlab.json
Normal file
151
training_config.mixlab.json
Normal file
@@ -0,0 +1,151 @@
|
||||
{
|
||||
"name": "gpt2_strict_small_gpt2init",
|
||||
"model_dim": 768,
|
||||
"vocab_size": 16384,
|
||||
"seq_len": 514,
|
||||
"max_positions": 1024,
|
||||
"mlp_mult": 4.0,
|
||||
"tie_embeddings": true,
|
||||
"norm_type": "layernorm",
|
||||
"norm_affine": true,
|
||||
"norm_eps": 1e-05,
|
||||
"positional_embedding": "learned_absolute",
|
||||
"embedding_dropout": 0.1,
|
||||
"hidden_dropout": 0.1,
|
||||
"attn_dropout": 0.1,
|
||||
"hf_export_format": "gpt2",
|
||||
"blocks": [
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
},
|
||||
{
|
||||
"type": "plain",
|
||||
"heads": 12,
|
||||
"attention_mask": "causal",
|
||||
"attn_bias": true,
|
||||
"ffn_activation": "gelu_new",
|
||||
"ffn_pre_norm": true,
|
||||
"ffn_bias": true
|
||||
}
|
||||
],
|
||||
"training": {
|
||||
"objective": "causal",
|
||||
"optimizer": "adamw",
|
||||
"lr": 5e-05,
|
||||
"weight_decay": 0.0,
|
||||
"beta1": 0.9,
|
||||
"beta2": 0.999,
|
||||
"epsilon": 1e-08,
|
||||
"grad_clip": 1.0,
|
||||
"steps": 21300,
|
||||
"warmup_steps": 213,
|
||||
"hold_steps": 0,
|
||||
"warmdown_steps": 0,
|
||||
"min_lr_fraction": 1e-06,
|
||||
"batch_tokens": 8224,
|
||||
"compute_dtype": "float32",
|
||||
"seed": 42,
|
||||
"example_framing": {
|
||||
"content_len": 512,
|
||||
"bos_id": 1,
|
||||
"eos_id": 2
|
||||
},
|
||||
"weight_init": "gpt2"
|
||||
}
|
||||
}
|
||||
1096
weight_map.json
Normal file
1096
weight_map.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user