Instructions to use EshAhm/phi-2-IA3_1-Python with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EshAhm/phi-2-IA3_1-Python with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2")
model = PeftModel.from_pretrained(base_model, "EshAhm/phi-2-IA3_1-Python")

Transformers

How to use EshAhm/phi-2-IA3_1-Python with Transformers:

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

pipe = pipeline("text-generation", model="EshAhm/phi-2-IA3_1-Python")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("EshAhm/phi-2-IA3_1-Python", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EshAhm/phi-2-IA3_1-Python with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EshAhm/phi-2-IA3_1-Python"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EshAhm/phi-2-IA3_1-Python",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EshAhm/phi-2-IA3_1-Python

SGLang

How to use EshAhm/phi-2-IA3_1-Python 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 "EshAhm/phi-2-IA3_1-Python" \
    --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": "EshAhm/phi-2-IA3_1-Python",
		"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 "EshAhm/phi-2-IA3_1-Python" \
        --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": "EshAhm/phi-2-IA3_1-Python",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EshAhm/phi-2-IA3_1-Python with Docker Model Runner:
```
docker model run hf.co/EshAhm/phi-2-IA3_1-Python
```

phi-2-IA3_1-Python / README.md

EshAhm

EshAhm/phi-2-IA3_1-Python

cc6183f verified about 1 year ago

preview code

Raw History Blame Contribute Delete

2.63 kB

---
library_name: peft
license: mit
base_model: microsoft/phi-2
tags:
- base_model:adapter:microsoft/phi-2
- transformers
pipeline_tag: text-generation
model-index:
- name: phi-2-IA3_1-Python
  results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# phi-2-IA3_1-Python
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 4.4994
## 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: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 6.003         | 0.1333 | 100  | 6.1547          |
| 5.798         | 0.2667 | 200  | 5.8543          |
| 5.4963        | 0.4    | 300  | 5.5766          |
| 5.4936        | 0.5333 | 400  | 5.3316          |
| 5.2081        | 0.6667 | 500  | 5.1551          |
| 4.8002        | 0.8    | 600  | 5.0209          |
| 4.7734        | 0.9333 | 700  | 4.9287          |
| 4.9121        | 1.0667 | 800  | 4.8604          |
| 4.8736        | 1.2    | 900  | 4.8028          |
| 4.4034        | 1.3333 | 1000 | 4.7485          |
| 4.7587        | 1.4667 | 1100 | 4.6937          |
| 4.3786        | 1.6    | 1200 | 4.6457          |
| 4.3765        | 1.7333 | 1300 | 4.6145          |
| 4.6507        | 1.8667 | 1400 | 4.5827          |
| 4.8214        | 2.0    | 1500 | 4.5567          |
| 4.1151        | 2.1333 | 1600 | 4.5434          |
| 4.6073        | 2.2667 | 1700 | 4.5267          |
| 3.9566        | 2.4    | 1800 | 4.5202          |
| 4.7471        | 2.5333 | 1900 | 4.5094          |
| 4.5244        | 2.6667 | 2000 | 4.5046          |
| 4.3776        | 2.8    | 2100 | 4.5010          |
| 4.3815        | 2.9333 | 2200 | 4.4994          |


### Framework versions

- PEFT 0.17.1
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0

	---
	library_name: peft
	license: mit
	base_model: microsoft/phi-2
	tags:
	- base_model:adapter:microsoft/phi-2
	- transformers
	pipeline_tag: text-generation
	model-index:
	- name: phi-2-IA3_1-Python
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# phi-2-IA3_1-Python

	This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 4.4994

	## 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: 2
	- seed: 42
	- gradient_accumulation_steps: 2
	- total_train_batch_size: 4
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: linear
	- lr_scheduler_warmup_steps: 100
	- num_epochs: 3

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 6.003 \| 0.1333 \| 100 \| 6.1547 \|
	\| 5.798 \| 0.2667 \| 200 \| 5.8543 \|
	\| 5.4963 \| 0.4 \| 300 \| 5.5766 \|
	\| 5.4936 \| 0.5333 \| 400 \| 5.3316 \|
	\| 5.2081 \| 0.6667 \| 500 \| 5.1551 \|
	\| 4.8002 \| 0.8 \| 600 \| 5.0209 \|
	\| 4.7734 \| 0.9333 \| 700 \| 4.9287 \|
	\| 4.9121 \| 1.0667 \| 800 \| 4.8604 \|
	\| 4.8736 \| 1.2 \| 900 \| 4.8028 \|
	\| 4.4034 \| 1.3333 \| 1000 \| 4.7485 \|
	\| 4.7587 \| 1.4667 \| 1100 \| 4.6937 \|
	\| 4.3786 \| 1.6 \| 1200 \| 4.6457 \|
	\| 4.3765 \| 1.7333 \| 1300 \| 4.6145 \|
	\| 4.6507 \| 1.8667 \| 1400 \| 4.5827 \|
	\| 4.8214 \| 2.0 \| 1500 \| 4.5567 \|
	\| 4.1151 \| 2.1333 \| 1600 \| 4.5434 \|
	\| 4.6073 \| 2.2667 \| 1700 \| 4.5267 \|
	\| 3.9566 \| 2.4 \| 1800 \| 4.5202 \|
	\| 4.7471 \| 2.5333 \| 1900 \| 4.5094 \|
	\| 4.5244 \| 2.6667 \| 2000 \| 4.5046 \|
	\| 4.3776 \| 2.8 \| 2100 \| 4.5010 \|
	\| 4.3815 \| 2.9333 \| 2200 \| 4.4994 \|


	### Framework versions

	- PEFT 0.17.1
	- Transformers 4.56.1
	- Pytorch 2.8.0+cu126
	- Datasets 4.0.0
	- Tokenizers 0.22.0