| { | |
| "created_from": { | |
| "local_gpt_checkpoint": "/Users/kacper/Local/Ventures/Slayer/gpt2-pl-mac/ckpt.pt", | |
| "local_gpt_tokenizer": "/Users/kacper/Local/Ventures/Slayer/gpt2-pl-mac/polish_bpe_32k.json", | |
| "local_rxlm_tokenizer": "/Users/kacper/Local/DueDil/rxlm/beta-training/tokenizer.json", | |
| "remote_rxlm_tokenizer": "slayer:/home/ubuntu/rxlm_dd/beta-training/tokenizer.json", | |
| "remote_nanogpt_tree": "slayer:/home/ubuntu/modded-nanogpt" | |
| }, | |
| "model_ckpt": { | |
| "path": "model/ckpt.pt", | |
| "format": "torch checkpoint", | |
| "checkpoint_keys": ["model", "model_args", "iter"], | |
| "model_args": { | |
| "n_layer": 12, | |
| "n_head": 12, | |
| "n_embd": 768, | |
| "block_size": 1024, | |
| "bias": false, | |
| "vocab_size": 32768, | |
| "dropout": 0.0 | |
| }, | |
| "iter": 500, | |
| "state_dict_parameters": 136071936, | |
| "tokenizer": "tokenizers/polish_bpe_32k.json" | |
| }, | |
| "tokenizers": { | |
| "polish_bpe_32k": { | |
| "path": "tokenizers/polish_bpe_32k.json", | |
| "type": "ByteLevel BPE", | |
| "vocab_size": 32768, | |
| "merges": 32511, | |
| "add_prefix_space": false | |
| }, | |
| "rxlm_polish_bpe_65k": { | |
| "path": "tokenizers/rxlm_polish_bpe_65k.json", | |
| "type": "ByteLevel BPE", | |
| "vocab_size": 65536, | |
| "merges": 65283, | |
| "normalizer": "NFKC", | |
| "add_prefix_space": true | |
| } | |
| } | |
| } | |