524 MB

Ctrl+K

1 contributor

History: 1 commit

kineticdrive

Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT)

02e3cea verified 6 months ago

README.md

5.23 kB
Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
adapter_config.json

950 Bytes
Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
adapter_model.safetensors

336 MB
xet

Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
chat_template.jinja

4.61 kB
Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
optimizer.pt
Detected Pickle imports (6)
- "torch._tensor._rebuild_from_type_v2",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.FloatStorage",
- "torch.Tensor",
- "torch.ByteStorage"
How to fix it?
171 MB
xet

Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
rng_state.pth
Detected Pickle imports (7)
- "numpy._core.multiarray._reconstruct",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "_codecs.encode",
- "numpy.dtype",
- "torch.ByteStorage",
- "numpy.ndarray"
How to fix it?
14.6 kB
xet

Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
scheduler.pt
Pickle imports
- No problematic imports detected
What is a pickle import?
1.47 kB
xet

Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
special_tokens_map.json

454 Bytes
Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
tokenizer.json

17.2 MB
xet

Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
tokenizer_config.json

50.6 kB
Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
trainer_state.json

20.5 kB
Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.training_args.TrainingArguments"
How to fix it?
5.91 kB
xet

Fine-tuned Llama 3.1 8B adapter for structured API generation - 40% accuracy (95% better than Azure GPT) 6 months ago

Detected Pickle imports (6)

Detected Pickle imports (7)

Pickle imports

Detected Pickle imports (10)