This model is a fine-tuned version of
NeverSleep/Nethena-20B
on a private dataset.
It achieves the following results on the evaluation set:
Loss: 1.3864
Model description
athirdpath/Nethena-20b-Glued-LORA is a 128 rank LORA for RP, trained on
NeverSleep/Nethena-20B
. It is unalligned and NSFW-oriented.
This is a test, exploring the effects of "gluing" the components of the 20b model together to reduce the iconic word replacement errors, increase lucidity, and improve recall.
Training and evaluation data
The private ~500k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories:
- Medical texts (on psychology, reproductive organs, anatomy, and pregnancy). These are formatted so the model, in character as a doctor or therapist, answers a patient's question in short to medium form.
- Excerpts from short stories and novellas (erotic and romantic) centered around both realistic and fantastic situations, covering several fetishes as well. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions.
- A selection from PIPPA, using a wide keyword search for tokens associated with low quality human or AI data to remove those responses, then a positive search was done for words and phrases associated with a higher reading level. These are converted to Alpaca with “Enter RP mode.” in all the instruction fields.
- ~18k tokens of GPT-4 generated data on role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations.
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 5
total_train_batch_size: 20
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
1.955
0.38
25
1.9037
1.6598
0.75
50
1.6192
1.5649
1.13
75
1.5010
1.4424
1.5
100
1.4424
1.4142
1.88
125
1.4068
1.4951
2.25
150
1.3908
1.4418
2.63
175
1.3864
Framework versions
Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1
Runs of athirdpath Nethena-20b-Glue-LORA on huggingface.co
16
Total runs
0
24-hour runs
-2
3-day runs
-3
7-day runs
3
30-day runs
More Information About Nethena-20b-Glue-LORA huggingface.co Model
Nethena-20b-Glue-LORA huggingface.co is an AI model on huggingface.co that provides Nethena-20b-Glue-LORA's model effect (), which can be used instantly with this athirdpath Nethena-20b-Glue-LORA model. huggingface.co supports a free trial of the Nethena-20b-Glue-LORA model, and also provides paid use of the Nethena-20b-Glue-LORA. Support call Nethena-20b-Glue-LORA model through api, including Node.js, Python, http.
Nethena-20b-Glue-LORA huggingface.co is an online trial and call api platform, which integrates Nethena-20b-Glue-LORA's modeling effects, including api services, and provides a free online trial of Nethena-20b-Glue-LORA, you can try Nethena-20b-Glue-LORA online for free by clicking the link below.
athirdpath Nethena-20b-Glue-LORA online free url in huggingface.co:
Nethena-20b-Glue-LORA is an open source model from GitHub that offers a free installation service, and any user can find Nethena-20b-Glue-LORA on GitHub to install. At the same time, huggingface.co provides the effect of Nethena-20b-Glue-LORA install, users can directly use Nethena-20b-Glue-LORA installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Nethena-20b-Glue-LORA install url in huggingface.co: