alexredna
/

Tukan-1.1B-Chat-reasoning-sft-COLA

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Tukan-1.1B-Chat-reasoning-sft-COLA

1 contributor

History: 16 commits

alexredna's picture

Not needed as lora weights are merged

fa129eb verified 10 months ago

runs
Training in progress, step 40 10 months ago
.gitattributes

1.52 kB

initial commit 10 months ago
README.md

1.66 kB

Model save 10 months ago
all_results.json

353 Bytes

Model save 10 months ago
config.json

692 Bytes

Model save 10 months ago
eval_results.json

184 Bytes

Model save 10 months ago
generation_config.json

124 Bytes

Model save 10 months ago
model.safetensors

4.4 GB
LFS

Model save 10 months ago
special_tokens_map.json

551 Bytes

Model save 10 months ago
tokenizer.model

500 kB
LFS

Model save 10 months ago
tokenizer_config.json

1.38 kB

Model save 10 months ago
train_results.json

190 Bytes

Model save 10 months ago
trainer_state.json

816 Bytes

Model save 10 months ago
training_args.bin
Detected Pickle imports (8)
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "alignment.configs.SFTConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState"
How to fix it?
4.79 kB
LFS

Training in progress, step 40 10 months ago