|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- Mielikki/Erebus-87k |
|
- FourOhFour/Instruct_Phase |
|
- FourOhFour/RP_Phase |
|
- anthracite-core/full-opus-chosen-hermes-rejected-kto-v1 |
|
language: |
|
- en |
|
base_model: |
|
- IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml |
|
--- |
|
--- |
|
### These are EXL2 quants for Aura-4B, Measurement file in the main branch, Check revisions for different BPW |
|
--- |
|
## Aura-4B |
|
|
|
 |
|
|
|
## Introduction |
|
|
|
**Aura-4B** is a state of the art dedicated roleplaying model designed to fulfill your every desire. |
|
|
|
This finetune has seen several hundreds of millions of tokens of completion, instruction and roleplaying data. A Kahneman-Tversky Optimization was applied to give this model a unique output style. |
|
|
|
Developed by **Aura Industries**, with contributions from **Anthracite Org** |
|
|
|
## Model Details |
|
|
|
- **Model Name**: Aura-4B |
|
- **Base Model**: [IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml](https://huggingface.co/IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml) |
|
- **Model Type**: Chat Completions |
|
- **Prompt Format**: ChatML |
|
- **License**: Apache-2.0 |
|
- **Language**: English |
|
- **Max Context**: 8,192+ tokens |
|
|
|
## License |
|
|
|
This model is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0). |
|
|
|
## Quantizations |
|
|
|
[Static GGUF](https://huggingface.co/mradermacher/Aura-4B-GGUF) |
|
|
|
[Imatrix GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF) |
|
|
|
EXL2 coming soon... |
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) |
|
|
|
Coming soon... |
|
|
|
| Metric |Value| |
|
|-------------------|----:| |
|
|Avg. | N/A| |
|
|IFEval (0-Shot) | N/A| |
|
|BBH (3-Shot) | N/A| |
|
|MATH Lvl 5 (4-Shot)| N/A| |
|
|GPQA (0-shot) | N/A| |
|
|MuSR (0-shot) | N/A| |
|
|MMLU-PRO (5-shot) | N/A| |
|
|
|
## Training Configuration |
|
|
|
<details><summary>Click here for Axolotl configs</summary> |
|
|
|
Completion SFT |
|
|
|
```yaml |
|
base_model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
hub_model_id: jeiku/completion4B |
|
hub_strategy: "all_checkpoints" |
|
push_dataset_to_hub: |
|
hf_use_auth_token: true |
|
|
|
datasets: |
|
- path: Mielikki/Erebus-87k |
|
type: completion |
|
field: body |
|
|
|
shuffle_merged_datasets: true |
|
val_set_size: 0.0025 |
|
output_dir: ./outputs/out |
|
|
|
adapter: |
|
lora_r: |
|
lora_alpha: |
|
lora_dropout: |
|
lora_target_linear: |
|
|
|
sequence_len: 8192 |
|
sample_packing: true |
|
eval_sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
plugins: |
|
- axolotl.integrations.liger.LigerPlugin |
|
liger_rope: true |
|
liger_rms_norm: true |
|
liger_swiglu: true |
|
liger_fused_linear_cross_entropy: true |
|
|
|
wandb_project: EXP4B |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: EXP4B |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 12 |
|
micro_batch_size: 3 |
|
num_epochs: 1 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.00001 |
|
weight_decay: 0.05 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: true |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
warmup_ratio: 0.1 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_max_new_tokens: 128 |
|
saves_per_epoch: 1 |
|
|
|
debug: |
|
deepspeed: deepspeed_configs/zero3_bf16.json |
|
fsdp: |
|
fsdp_config: |
|
|
|
special_tokens: |
|
pad_token: <|finetune_right_pad_id|> |
|
``` |
|
|
|
Instruct SFT |
|
|
|
```yaml |
|
base_model: jeiku/completion4B |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
hub_model_id: jeiku/instructered4B |
|
hub_strategy: "all_checkpoints" |
|
push_dataset_to_hub: |
|
hf_use_auth_token: true |
|
|
|
datasets: |
|
- path: FourOhFour/Instruct_Phase |
|
type: sharegpt |
|
conversation: chatml |
|
|
|
chat_template: chatml |
|
|
|
shuffle_merged_datasets: true |
|
val_set_size: 0.0025 |
|
output_dir: ./outputs/out |
|
|
|
adapter: |
|
lora_r: |
|
lora_alpha: |
|
lora_dropout: |
|
lora_target_linear: |
|
|
|
sequence_len: 8192 |
|
sample_packing: true |
|
eval_sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
plugins: |
|
- axolotl.integrations.liger.LigerPlugin |
|
liger_rope: true |
|
liger_rms_norm: true |
|
liger_swiglu: true |
|
liger_fused_linear_cross_entropy: true |
|
|
|
wandb_project: EXP4B |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: EXP4B |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 12 |
|
micro_batch_size: 3 |
|
num_epochs: 2 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.00001 |
|
weight_decay: 0.05 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: true |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
warmup_ratio: 0.1 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_max_new_tokens: 128 |
|
saves_per_epoch: 2 |
|
|
|
debug: |
|
deepspeed: deepspeed_configs/zero3_bf16.json |
|
fsdp: |
|
fsdp_config: |
|
|
|
special_tokens: |
|
pad_token: <|finetune_right_pad_id|> |
|
``` |
|
|
|
Roleplaying SFT |
|
|
|
```yaml |
|
base_model: jeiku/instructered4B |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
hub_model_id: jeiku/TheBest4B |
|
hub_strategy: "all_checkpoints" |
|
push_dataset_to_hub: |
|
hf_use_auth_token: true |
|
|
|
datasets: |
|
- path: FourOhFour/RP_Phase |
|
type: sharegpt |
|
conversation: chatml |
|
|
|
chat_template: chatml |
|
|
|
shuffle_merged_datasets: true |
|
val_set_size: 0.0025 |
|
output_dir: ./outputs/out |
|
|
|
adapter: |
|
lora_r: |
|
lora_alpha: |
|
lora_dropout: |
|
lora_target_linear: |
|
|
|
sequence_len: 8192 |
|
sample_packing: true |
|
eval_sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
plugins: |
|
- axolotl.integrations.liger.LigerPlugin |
|
liger_rope: true |
|
liger_rms_norm: true |
|
liger_swiglu: true |
|
liger_fused_linear_cross_entropy: true |
|
|
|
wandb_project: EXP4B |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: EXP4B |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 12 |
|
micro_batch_size: 3 |
|
num_epochs: 2 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.00001 |
|
weight_decay: 0.05 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: true |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
warmup_ratio: 0.1 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_max_new_tokens: 128 |
|
saves_per_epoch: 2 |
|
|
|
debug: |
|
deepspeed: deepspeed_configs/zero3_bf16.json |
|
fsdp: |
|
fsdp_config: |
|
|
|
special_tokens: |
|
pad_token: <|finetune_right_pad_id|> |
|
``` |
|
|
|
KTO |
|
|
|
```yaml |
|
base_model: FourOhFour/Crispy_Crab_4B |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
hub_model_id: jeiku/aura4bkto |
|
hub_strategy: "all_checkpoints" |
|
push_dataset_to_hub: |
|
hf_use_auth_token: true |
|
|
|
chat_template: chatml |
|
|
|
rl: kto |
|
rl_beta: 0.2 |
|
kto_desirable_weight: 0.2 |
|
|
|
datasets: |
|
- path: anthracite-core/full-opus-chosen-hermes-rejected-kto-v1 |
|
type: chatml.argilla |
|
|
|
shuffle_merged_datasets: true |
|
val_set_size: 0.0 |
|
output_dir: ./outputs/out |
|
|
|
sequence_len: 8192 |
|
sample_packing: false |
|
eval_sample_packing: false |
|
pad_to_sequence_len: false |
|
|
|
wandb_project: Aura-4B |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: Aura-4B |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 16 |
|
micro_batch_size: 2 |
|
num_epochs: 2 |
|
max_steps: 500 |
|
|
|
optimizer: adamw_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.00001 |
|
weight_decay: 0.05 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: true |
|
|
|
gradient_checkpointing: true |
|
gradient_checkpointing_kwargs: |
|
use_reentrant: true |
|
remove_unused_columns: false |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 2 |
|
eval_table_size: |
|
eval_max_new_tokens: |
|
saves_per_epoch: 1 |
|
|
|
debug: |
|
deepspeed: |
|
fsdp: |
|
fsdp_config: |
|
fsdp: |
|
fsdp_config: |
|
|
|
special_tokens: |
|
pad_token: <|finetune_right_pad_id|> |
|
``` |
|
</details><br> |
