Instructions to use teddy-f-47/phi-pl-2_7B-v_0_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teddy-f-47/phi-pl-2_7B-v_0_1 with Transformers:

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

pipe = pipeline("text-generation", model="teddy-f-47/phi-pl-2_7B-v_0_1", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teddy-f-47/phi-pl-2_7B-v_0_1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("teddy-f-47/phi-pl-2_7B-v_0_1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use teddy-f-47/phi-pl-2_7B-v_0_1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teddy-f-47/phi-pl-2_7B-v_0_1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teddy-f-47/phi-pl-2_7B-v_0_1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/teddy-f-47/phi-pl-2_7B-v_0_1

SGLang

How to use teddy-f-47/phi-pl-2_7B-v_0_1 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 "teddy-f-47/phi-pl-2_7B-v_0_1" \
    --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": "teddy-f-47/phi-pl-2_7B-v_0_1",
		"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 "teddy-f-47/phi-pl-2_7B-v_0_1" \
        --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": "teddy-f-47/phi-pl-2_7B-v_0_1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use teddy-f-47/phi-pl-2_7B-v_0_1 with Docker Model Runner:
```
docker model run hf.co/teddy-f-47/phi-pl-2_7B-v_0_1
```

phi-2-pl-v_0_1

This model is based on microsoft/phi-2. It was trained from scratch on the 20231201 Polish Wikipedia dump.

Model description

The model was trained for a context length of 2048 tokens.

Intended uses & limitations

The model is intended for research purposes only. It may generate fictitious, incorrect, unethical, or biased texts. At its current state, it is not suitable for production purposes.

Example:

tokenizer = AutoTokenizer.from_pretrained(
    model_name, trust_remote_code=True, use_fast=True
)
model = AutoModelForCausalLM.from_pretrained(
    model_name, vocab_size=len(tokenizer), attn_implementation="flash_attention_2",
    trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="auto"
)
model.eval()

generation_config = GenerationConfig.from_pretrained(
    model_name, do_sample=False, repetition_penalty=1.5,
    min_new_tokens=1, max_new_tokens=128
)

test_input = tokenizer("Wrocław to polski miasto. Wrocław jest ", return_tensors='pt').to(torch.device('cuda'))
test_output = model.generate(**test_input, generation_config=generation_config)
test_preds = tokenizer.batch_decode(sequences=test_output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
print(test_preds)

Training and evaluation data

The 20231201 Polish Wikipedia dump.

Training procedure

Training environment

GPU: 1 x A100X (80GB)

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
num_devices: 1
train_batch_size: 8
gradient_accumulation_steps: 1
optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
precision: bf16
seed: 42

Training results

runtime: 1mo 3d 9h 40m 16s
train_loss: 2.983

Framework versions

Transformers 4.37.1
Pytorch 2.1.2
Datasets 2.16.1
Tokenizers 0.15.1

Downloads last month: 11

Safetensors

Model size

3B params

Tensor type

F32

Model tree for teddy-f-47/phi-pl-2_7B-v_0_1

Base model

microsoft/phi-2

Finetuned

(411)

this model