Nekochu
/

Llama-3.1-8B-french-DPO

Model card Files Files and versions

Llama-3.1-8B-french-DPO / QLoRA_french_sft

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

Nekochu's picture

Delete QLoRA_french_sft/rng_state.pth

83361eb verified 11 months ago

adapter_config.json

775 Bytes

Add QLoRA_french_pt + sft about 1 year ago
adapter_model.safetensors

336 MB
xet

Add QLoRA_french_pt + sft about 1 year ago
all_results.json

248 Bytes

Add QLoRA_french_pt + sft about 1 year ago
optimizer.pt
Detected Pickle imports (4)
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch.ByteStorage"
What is a pickle import?
170 MB
xet

Add QLoRA_french_pt + sft about 1 year ago
scheduler.pt
Pickle imports
- No problematic imports detected
What is a pickle import?
1.06 kB
xet

Add QLoRA_french_pt + sft about 1 year ago
special_tokens_map.json

342 Bytes

Add QLoRA_french_pt + sft about 1 year ago
tokenizer.json

9.09 MB

Add QLoRA_french_pt + sft about 1 year ago
tokenizer_config.json

53.2 kB

Add QLoRA_french_pt + sft about 1 year ago
train_results.json

207 Bytes

Add QLoRA_french_pt + sft about 1 year ago
trainer_log.jsonl

625 kB

Add QLoRA_french_pt + sft about 1 year ago
trainer_state.json

521 kB

Add QLoRA_french_pt + sft about 1 year ago
training_loss.png

52.8 kB

Add QLoRA_french_pt + sft about 1 year ago