|
Download README.md from anonymous-md/test: direct link, hf CLI and curl.
- Browser
- Download file 1.78 kB
-
https://huggingface.co/anonymous-md/test/resolve/main/README.md
- Command line
-
hf download hf://anonymous-md/test/README.md
-
curl -L -o README.md https://huggingface.co/anonymous-md/test/resolve/main/README.md
1.78 kB
metadata
license: cc-by-nc-4.0
Qwen3-1.7B on Nemotron-CC (low-quality tier): ablation checkpoints
Four base language models with the Qwen3-1.7B architecture (1.72B parameters). Each was pretrained from scratch for one epoch on 34.4B tokens of the low-quality (LQ) tier of Nemotron-CC, Common Crawl snapshots 2013–2015.
| Folder | Training data | Seed |
|---|---|---|
v2-lq-seed1234/ |
LQ after V2 repair (prose-only repair + linguistic repair) | 1234 |
raw-lq-seed1234/ |
LQ, unrepaired | 1234 |
raw-lq-seed1337/ |
LQ, unrepaired | 1337 |
raw-lq-seed42/ |
LQ, unrepaired | 42 |
- Seeds: the seed sets the weight initialization only. Every run used the same data-shuffling seed (1234), so the three raw runs saw identical batches in identical order.
v2-lq-seed1234/andraw-lq-seed1234/share the same configuration and seed and differ only in training data. - Training: 16,406 steps × 512 sequences × 4,096 tokens, BF16, AdamW (β = 0.9/0.95, weight decay 0.1), learning rate 3e-4 → 3e-5 (warmup–stable–decay).
- Base models only: no instruction tuning.
Format and compatibility
Each folder is a standard Hugging Face checkpoint: BF16 model.safetensors, tokenizer, and generation config. The checkpoints were exported with transformers 5.3. config.json and tokenizer_config.json also carry the older field names, so transformers 4.x (4.51 or newer) loads the same RoPE base (1,000,000) and the same tokenizer.
Usage
hf download anonymous-md/test --include "v2-lq-seed1234/*" --local-dir ./qwen3-lq
from transformers import AutoModelForCausalLM, AutoTokenizer
path = "./qwen3-lq/v2-lq-seed1234"
tokenizer = AutoTokenizer.from_pretrained(path)
model = AutoModelForCausalLM.from_pretrained(path)