QwQ-RP-LoRA

2

32.0B

—

by

Undi95

Other

OTHER

32B params

New

0 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

72GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

30GB+ RAM

Code Examples

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

Automatically upload checkpoint and final model to HFyaml

base_model: ./Qwen_QwQ-32B/
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: tokenizer_default

datasets:
  - path: Undi95/QwQ-dataset
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant"]
      system: ["system"]
      tool: ["tool"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 256
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qwq-rp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.1

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.

Replicate

One-click model deployment

Easiest Setup

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

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