broadfield-dev
/

savant_2_gsm8k_final

Model card Files Files and versions

savant_2_gsm8k_final / checkpoints /stable-run-sft-step-260

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

broadfield-dev's picture

Save benchmark: stable-run-sft-step-260

c7cd0a9 verified 7 months ago

config.json

971 Bytes
Save benchmark: stable-run-sft-step-260 7 months ago
generation_config.json

119 Bytes
Save benchmark: stable-run-sft-step-260 7 months ago
hyperparameters.json

461 Bytes
Save benchmark: stable-run-sft-step-260 7 months ago
merges.txt

456 kB
Save benchmark: stable-run-sft-step-260 7 months ago
model.safetensors

328 MB
xet

Save benchmark: stable-run-sft-step-260 7 months ago
optimizer.pt
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.FloatStorage"
What is a pickle import?
655 MB
xet

Save benchmark: stable-run-sft-step-260 7 months ago
scheduler.pt
Pickle imports
- No problematic imports detected
What is a pickle import?
1.47 kB
xet

Save benchmark: stable-run-sft-step-260 7 months ago
special_tokens_map.json

131 Bytes
Save benchmark: stable-run-sft-step-260 7 months ago
tokenizer.json

3.56 MB
Save benchmark: stable-run-sft-step-260 7 months ago
tokenizer_config.json

507 Bytes
Save benchmark: stable-run-sft-step-260 7 months ago
training_state.json

64 kB
Save benchmark: stable-run-sft-step-260 7 months ago
vocab.json

798 kB
Save benchmark: stable-run-sft-step-260 7 months ago