Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
AlleSpezza
/
Qwen-3-8B-Unified-R64
like
0
Text Generation
PEFT
Safetensors
Transformers
lora
sft
trl
conversational
arxiv:
1910.09700
Model card
Files
Files and versions
xet
Community
Use this model
main
Qwen-3-8B-Unified-R64
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
AlleSpezza
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
4e06cb5
verified
2 months ago
.gitattributes
Safe
1.57 kB
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
README.md
Safe
5.19 kB
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
adapter_config.json
Safe
897 Bytes
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
adapter_model.safetensors
Safe
698 MB
xet
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
added_tokens.json
Safe
707 Bytes
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
chat_template.jinja
Safe
4.17 kB
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
merges.txt
Safe
1.67 MB
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
optimizer.pt
pickle
Detected Pickle imports (5)
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch.Tensor"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
1.4 GB
xet
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
rng_state.pth
pickle
Detected Pickle imports (7)
"numpy._core.multiarray._reconstruct"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"numpy.ndarray"
,
"_codecs.encode"
,
"torch.ByteStorage"
,
"numpy.dtype"
How to fix it?
14.6 kB
xet
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
scheduler.pt
Safe
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
1.47 kB
xet
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
special_tokens_map.json
Safe
613 Bytes
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
tokenizer.json
Safe
11.4 MB
xet
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
tokenizer_config.json
Safe
5.4 kB
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
trainer_state.json
Safe
8.96 kB
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
training_args.bin
pickle
Detected Pickle imports (10)
"trl.trainer.sft_config.SFTConfig"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.SchedulerType"
How to fix it?
6.1 kB
xet
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
vocab.json
Safe
2.78 MB
Upload LoRa adapter model with Rank = 64. Only question and fts are trained. NO keyword.
2 months ago
