1 contributor

History: 18 commits

notpushkin

Add pipeline_tag=conversational for Hosted inference API/demo to work

ea19f70 8 months ago

.gitattributes

1.52 kB

initial commit 8 months ago
README.md

9.39 kB

Add pipeline_tag=conversational for Hosted inference API/demo to work 8 months ago
added_tokens.json

42 Bytes

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago
all_results.json

732 Bytes

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago
colab-demo.ipynb

167 kB

Upload colab-demo.ipynb 8 months ago
config.json

628 Bytes

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
eval_results.json

557 Bytes

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago
generation_config.json

111 Bytes

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago
model-00001-of-00008.safetensors

1.89 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
model-00002-of-00008.safetensors

1.95 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
model-00003-of-00008.safetensors

1.98 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
model-00004-of-00008.safetensors

1.95 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
model-00005-of-00008.safetensors

1.98 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
model-00006-of-00008.safetensors

1.95 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
model-00007-of-00008.safetensors

1.98 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
model-00008-of-00008.safetensors

816 MB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
model.safetensors.index.json

24 kB

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model-00001-of-00008.bin
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
1.89 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model-00002-of-00008.bin
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
1.95 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model-00003-of-00008.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
1.98 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model-00004-of-00008.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
1.95 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model-00005-of-00008.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
1.98 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model-00006-of-00008.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
1.95 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model-00007-of-00008.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
1.98 GB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model-00008-of-00008.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
816 MB
LFS

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
pytorch_model.bin.index.json

24 kB

Shard checkpoints in 2GB chunks to run on Colab 8 months ago
special_tokens_map.json

168 Bytes

Add chat template (#2) 8 months ago
thumbnail.png

510 kB

Upload thumbnail.png 8 months ago
tokenizer.json

1.8 MB

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago
tokenizer.model

493 kB
LFS

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago
tokenizer_config.json

1.43 kB

Add chat template (#2) 8 months ago
train_results.json

195 Bytes

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago
trainer_state.json

104 kB

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago
training_args.bin
Detected Pickle imports (11)
- "torch.device",
- "h4.training.config.DPOTrainingArguments",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "accelerate.state.PartialState",
- "accelerate.utils.deepspeed.HfDeepSpeedConfig",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
5.44 kB
LFS

Add HuggingFaceH4/mistral-7b-dpo-v0.4 checkpoint 8 months ago

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (3)

Detected Pickle imports (11)