Downloads · 30 days
0
nazdef/gpt2small-en-it-nanochat-lr2e4-bs6-wsd-fastdecay-step10000
gpt2small-en-it-nanochat-lr2e4-bs6-wsd-fastdecay-step10000 is a text generation model from nazdef. Use it when you need the model to write or continue text. It is set up for custom. The card lists the license as other.
This repo stages the best saved checkpoint from the local NanoChat EN/IT GPT-2-small-like run 20260517stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay.
Downloads · 30 days
0
Access
Public
Updated May 19, 2026
Repo size
2.2 GB
Likes
0
Public
Click a slice to open those files.
.pt1.6 GB · 75%
From the Hugging Face model README
This repo stages the best saved checkpoint from the local NanoChat EN/IT GPT-2-small-like run 20260517_stable-config-recipe-v5-gpt2small-lr2e4-batchmaxpossible-bs6-wsd-fastdecay.
step_10000.ptbest_validation.jsonThis checkpoint is the best validation checkpoint within this run family. It is a useful intermediate bilingual pretraining artifact, not a polished factual assistant model.
training_config.yamltokenizer.json + tokenizer_meta.json/mnt/apps/llm-nanochat/datasets/202605011052_fresh_50_50_score100_2500_sourcebalanced/mnt/apps/llm-nanochat/tokenizers/tok_202605011052_fresh_50_50_score100_32k_fromscratchstep_10000.ptstep_10000.safetensorsstep_10000.safetensors.jsontraining_config.yamltokenizer.jsontokenizer_meta.jsonbest_validation.jsoneval_summary.jsonprobe_step10000_summary.jsoneval_metrics.jsonl, metrics.jsonl, probe_generations.jsonlThe run includes probe telemetry, but the stored payload for this experiment is legacy/partial: the probe_generations.jsonl entries at step 10000 keep prompts and expected continuations, while generated text / target-rank fields are null. So this release does not make strong probe-quality claims from those rows.
This project uses a custom NanoChat inference/training stack. The easiest local UI in the source repo is the Chainlit checkpoint tester documented in the repo README.