47 lines
1.7 KiB
Markdown
47 lines
1.7 KiB
Markdown
---
|
|
license: other
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- qwen3
|
|
- text-generation
|
|
- littlelearner
|
|
- bounded
|
|
- base
|
|
---
|
|
|
|
# littlelearner-0.6b-base
|
|
|
|
0.617B K-5-bounded base model (pretraining only). Smallest scale point of the family.
|
|
|
|
Part of the [**LittleLearner**](https://arxiv.org/abs/2608.13545) scale-up study (*pedagogically-controlled knowledge exposure*): Qwen3 dense LMs trained on a corpus filtered to U.S. K-5 material (**bounded**) vs an unfiltered FineWeb-Edu corpus (**unbounded**), to measure what an interpretable knowledge boundary costs and grants.
|
|
|
|
## Model
|
|
- **Architecture:** Qwen3 dense (`Qwen3ForCausalLM`).
|
|
- **Size:** 0.617B params, hidden 1536, 20 layers, 12 query / 6 KV heads, FFN 4096. **Context:** 4096.
|
|
- **Tokenizer:** custom 64k byte-level BPE with per-digit splitting (ChatML special tokens).
|
|
- **Pretraining:** 88B tokens on K-5 **LittleCurriculum** (FineWeb-Edu filtered to U.S. grades K-5). WSD schedule, sharded Muon, MXFP8, Megatron-Core on 8xB200.
|
|
|
|
## Evaluation
|
|
- In-domain (K-5) bits-per-byte (BPB): **0.622**.
|
|
|
|
## Usage
|
|
```python
|
|
# transformers (completion)
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
repo = "manueldeprada/littlelearner-0.6b-bounded-base"
|
|
tok = AutoTokenizer.from_pretrained(repo)
|
|
model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="cuda")
|
|
ids = tok("The sum of 2 and 3 is", return_tensors="pt").to(model.device)
|
|
print(tok.decode(model.generate(**ids)[0], skip_special_tokens=True))
|
|
```
|
|
|
|
```python
|
|
# vLLM
|
|
from vllm import LLM
|
|
llm = LLM("manueldeprada/littlelearner-0.6b-bounded-base")
|
|
print(llm.generate(["The sum of 2 and 3 is"])[0].outputs[0].text)
|
|
```
|