Instructions to use Deadwalker0/maverickPhi-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Deadwalker0/maverickPhi-2 with Transformers:

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

pipe = pipeline("text-generation", model="Deadwalker0/maverickPhi-2", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Deadwalker0/maverickPhi-2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Deadwalker0/maverickPhi-2", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Deadwalker0/maverickPhi-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Deadwalker0/maverickPhi-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Deadwalker0/maverickPhi-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Deadwalker0/maverickPhi-2

SGLang

How to use Deadwalker0/maverickPhi-2 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 "Deadwalker0/maverickPhi-2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Deadwalker0/maverickPhi-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Deadwalker0/maverickPhi-2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Deadwalker0/maverickPhi-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Deadwalker0/maverickPhi-2 with Docker Model Runner:
```
docker model run hf.co/Deadwalker0/maverickPhi-2
```

See axolotl config

axolotl version: 0.4.0

base_model: microsoft/phi-2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: tatsu-lab/alpaca
    type: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./phi-sft-out

sequence_len: 2048
sample_packing: false  # currently unsupported
pad_to_sequence_len:

wandb_project: phi2
wandb_entity: oaaic
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 4
num_epochs: 1
optimizer: paged_adamw_8bit
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 1e-5

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

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

warmup_steps: 100
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
resize_token_embeddings_to_32x: true
special_tokens:
  pad_token: "<|endoftext|>"

phi-sft-out

This model is a fine-tuned version of microsoft/phi-2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9915

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: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 7
gradient_accumulation_steps: 8
total_train_batch_size: 224
total_eval_batch_size: 28
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.4814	0.0	1	1.4537
1.3529	0.25	55	1.3007
1.2246	0.5	110	1.0940
1.0636	0.75	165	0.9949
1.0758	1.0	220	0.9915

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.17.0
Tokenizers 0.15.0

Downloads last month: 4

Model tree for Deadwalker0/maverickPhi-2

Base model

microsoft/phi-2

Finetuned

(409)

this model