Instructions to use jeiku/Aura-MoEv2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeiku/Aura-MoEv2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="jeiku/Aura-MoEv2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jeiku/Aura-MoEv2")
model = AutoModelForCausalLM.from_pretrained("jeiku/Aura-MoEv2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jeiku/Aura-MoEv2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeiku/Aura-MoEv2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeiku/Aura-MoEv2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jeiku/Aura-MoEv2

SGLang

How to use jeiku/Aura-MoEv2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jeiku/Aura-MoEv2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeiku/Aura-MoEv2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "jeiku/Aura-MoEv2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeiku/Aura-MoEv2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jeiku/Aura-MoEv2 with Docker Model Runner:
```
docker model run hf.co/jeiku/Aura-MoEv2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

See axolotl config

axolotl version: 0.6.0

base_model: jeiku/MoEv2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: FourOhFour/RP_Phase
    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: jeiku/Writing
    type: completion
    field: text

chat_template: chatml

shuffle_merged_datasets: true
dataset_prepared_path:
val_set_size: 0.01
output_dir: ./output/out

hub_model_id: jeiku/Aura-MoEv2
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len:

wandb_project: Aura-MoEv2
wandb_entity:
wandb_watch:
wandb_name: Aura-MoEv2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00005

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

gradient_checkpointing: true
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: 
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>

Aura-MoEv2

This model is a fine-tuned version of jeiku/MoEv2 on the FourOhFour/RP_Phase and the jeiku/Writing datasets. It achieves the following results on the evaluation set:

Loss: 1.7106

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 32
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
29.5342	0.0038	1	1.8693
27.8562	0.4990	130	1.7601
26.632	0.9981	260	1.6990
21.9675	1.4952	390	1.7117
21.648	1.9942	520	1.7106

Framework versions

Transformers 4.47.0
Pytorch 2.3.1+cu121
Datasets 3.1.0
Tokenizers 0.21.0

Downloads last month: 6

Safetensors

Model size

7B params

Tensor type

F32

BF16

Model tree for jeiku/Aura-MoEv2

Base model

jeiku/MoEv2

Finetuned

(1)

this model

Quantizations

3 models

jeiku
/

Aura-MoEv2

Aura-MoEv2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for jeiku/Aura-MoEv2

Datasets used to train jeiku/Aura-MoEv2