Mistral-Nemo-Gutenberg-Encore-12B

7
11
license:apache-2.0
by
nbeerbower
Language Model
OTHER
12B params
New
7 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
27GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
12GB+ RAM

Code Examples

ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)
ORPO configtext
orpo_args = ORPOConfig(
    learning_rate=8e-6,
    lr_scheduler_type="cosine",
    warmup_ratio=0.05,
    max_length=4096,
    max_prompt_length=1024,
    max_completion_length=4096,
    beta=0.1,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=64,
    optim="paged_adamw_8bit",
    num_train_epochs=3,
    max_grad_norm=0.5,
    bf16=True,
)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.