14B-Qwen2.5-Freya-x1

Name: 14B-Qwen2.5-Freya-x1
Author: Sao10K

—

Sao10K

Language Model

OTHER

14B params

New

26 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

32GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

14GB+ RAM

Code Examples

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

Datayaml

base_model:
- s1: Qwen/Qwen2.5-14B
- s2: Qwen/Qwen2.5-14B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:
  
adapter: lora # 16-bit
lora_r:
- s1: 64
- s2: 32
lora_alpha: 64
lora_dropout: 0.2
lora_fan_in_fan_out:
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: chatml
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs:
- s1: 1
- s2: 2

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate:
- s1: 0.000002
- s2: 0.000004
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero2.json

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.