Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-dpo-full-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-dpo-full-gguf
like
0
conversational
endpoints_compatible
gguf
template
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
uf-rlced-conifer_tulu-2-7b-dpo-full - GGUF
Model creator:
https://huggingface.co/NicholasCorrado/
Original model:
https://huggingface.co/NicholasCorrado/uf-rlced-conifer_tulu-2-7b-dpo-full/
Name
Quant method
Size
uf-rlced-conifer_tulu-2-7b-dpo-full.Q2_K.gguf
Q2_K
2.36GB
uf-rlced-conifer_tulu-2-7b-dpo-full.IQ3_XS.gguf
IQ3_XS
2.6GB
uf-rlced-conifer_tulu-2-7b-dpo-full.IQ3_S.gguf
IQ3_S
2.75GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q3_K_S.gguf
Q3_K_S
2.75GB
uf-rlced-conifer_tulu-2-7b-dpo-full.IQ3_M.gguf
IQ3_M
2.9GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q3_K.gguf
Q3_K
3.07GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q3_K_M.gguf
Q3_K_M
3.07GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q3_K_L.gguf
Q3_K_L
3.35GB
uf-rlced-conifer_tulu-2-7b-dpo-full.IQ4_XS.gguf
IQ4_XS
3.4GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q4_0.gguf
Q4_0
3.56GB
uf-rlced-conifer_tulu-2-7b-dpo-full.IQ4_NL.gguf
IQ4_NL
3.58GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q4_K_S.gguf
Q4_K_S
3.59GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q4_K.gguf
Q4_K
3.8GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q4_K_M.gguf
Q4_K_M
3.8GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q4_1.gguf
Q4_1
3.95GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q5_0.gguf
Q5_0
4.33GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q5_K_S.gguf
Q5_K_S
4.33GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q5_K.gguf
Q5_K
4.45GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q5_K_M.gguf
Q5_K_M
4.45GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q5_1.gguf
Q5_1
4.72GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q6_K.gguf
Q6_K
5.15GB
uf-rlced-conifer_tulu-2-7b-dpo-full.Q8_0.gguf
Q8_0
6.67GB
Original model description:
library_name: transformers base_model: allenai/tulu-2-7b tags:
alignment-handbook
trl
dpo
generated_from_trainer
trl
dpo
alignment-handbook
generated_from_trainer datasets:
data/uf_rlced_conifer model-index:
name: uf-rlced-conifer_tulu-2-7b-dpo-full results: []
uf-rlced-conifer_tulu-2-7b-dpo-full
This model is a fine-tuned version of
allenai/tulu-2-7b
on the data/uf_rlced_conifer dataset. It achieves the following results on the evaluation set:
Loss: 0.3316
Rewards/chosen: -2.6774
Rewards/rejected: -5.0456
Rewards/accuracies: 0.8383
Rewards/margins: 2.3682
Logps/rejected: -989.8275
Logps/chosen: -729.1251
Logits/rejected: -0.3176
Logits/chosen: -0.4437
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 5e-07
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 256
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
Training results
Framework versions
Transformers 4.44.1
Pytorch 2.1.2+cu121
Datasets 2.21.0
Tokenizers 0.19.1
