Francois-Huali-12B

6
6
—
by
Delta-Vector
Other
OTHER
12B params
New
6 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
27GB+ RAM
Mobile
Laptop
Server
Quick Summary

A finetune ontop of the orginial Francois-PE model that incorporates KTO to increase coherency and prose.

Device Compatibility

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

Code Examples

Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
Axolotl configyaml
base_model: Delta-Vector_Francois-PE-12B

load_in_8bit: false
load_in_4bit: false
strict: false

rl: kto
kto_undesirable_weight: 1.0

#datasets:
#  - ds_type: json
#    data_files:
#      - NewEden/Ohashi-accepted-Hermes-rejected
#    split: train
#    type: chatml.argilla
datasets:
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./francois-PE-kto-r1

remove_unused_columns: false

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 64
lora_alpha: 32
lora_dropout: 0.0
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: KTO-NeMo
wandb_entity: 
wandb_watch:
wandb_name: Ohashi-accepted-hermes-rejected-r1
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: constant_with_warmup
learning_rate: 1e-6
max_grad_norm: 0.01

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:  /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:

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.