Instructions to use vishnu2003/phi2-finetuned-textbook-21 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vishnu2003/phi2-finetuned-textbook-21 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2")
model = PeftModel.from_pretrained(base_model, "vishnu2003/phi2-finetuned-textbook-21")

Transformers

How to use vishnu2003/phi2-finetuned-textbook-21 with Transformers:

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

pipe = pipeline("text-generation", model="vishnu2003/phi2-finetuned-textbook-21")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vishnu2003/phi2-finetuned-textbook-21", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vishnu2003/phi2-finetuned-textbook-21 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vishnu2003/phi2-finetuned-textbook-21"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vishnu2003/phi2-finetuned-textbook-21",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vishnu2003/phi2-finetuned-textbook-21

SGLang

How to use vishnu2003/phi2-finetuned-textbook-21 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 "vishnu2003/phi2-finetuned-textbook-21" \
    --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": "vishnu2003/phi2-finetuned-textbook-21",
		"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 "vishnu2003/phi2-finetuned-textbook-21" \
        --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": "vishnu2003/phi2-finetuned-textbook-21",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vishnu2003/phi2-finetuned-textbook-21 with Docker Model Runner:
```
docker model run hf.co/vishnu2003/phi2-finetuned-textbook-21
```

phi2-finetuned-textbook-21

This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2209

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: 0.0002
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.6047	0.1016	100	1.5466
1.3265	0.2032	200	1.1507
1.0355	0.3048	300	0.8742
0.8164	0.4063	400	0.6808
0.6442	0.5079	500	0.5399
0.5446	0.6095	600	0.4273
0.4727	0.7111	700	0.3645
0.4179	0.8127	800	0.3171
0.3762	0.9143	900	0.2857
0.3514	1.0152	1000	0.2714
0.3191	1.1168	1100	0.2552
0.301	1.2184	1200	0.2464
0.2894	1.32	1300	0.2395
0.29	1.4216	1400	0.2353
0.2724	1.5232	1500	0.2300
0.2628	1.6248	1600	0.2283
0.2629	1.7263	1700	0.2251
0.2612	1.8279	1800	0.2228
0.2452	1.9295	1900	0.2209

Framework versions

PEFT 0.17.1
Transformers 4.56.2
Pytorch 2.7.1+cu128
Datasets 4.1.1
Tokenizers 0.22.1

Downloads last month: 4

Model tree for vishnu2003/phi2-finetuned-textbook-21

Base model

microsoft/phi-2

Adapter

(994)

this model