Instructions to use Jyo-K/Fine-Tuned-Qwen2.5_1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jyo-K/Fine-Tuned-Qwen2.5_1B with Transformers:

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

pipe = pipeline("text-generation", model="Jyo-K/Fine-Tuned-Qwen2.5_1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jyo-K/Fine-Tuned-Qwen2.5_1B")
model = AutoModelForCausalLM.from_pretrained("Jyo-K/Fine-Tuned-Qwen2.5_1B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jyo-K/Fine-Tuned-Qwen2.5_1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jyo-K/Fine-Tuned-Qwen2.5_1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jyo-K/Fine-Tuned-Qwen2.5_1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jyo-K/Fine-Tuned-Qwen2.5_1B

SGLang

How to use Jyo-K/Fine-Tuned-Qwen2.5_1B 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 "Jyo-K/Fine-Tuned-Qwen2.5_1B" \
    --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": "Jyo-K/Fine-Tuned-Qwen2.5_1B",
		"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 "Jyo-K/Fine-Tuned-Qwen2.5_1B" \
        --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": "Jyo-K/Fine-Tuned-Qwen2.5_1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Jyo-K/Fine-Tuned-Qwen2.5_1B with Docker Model Runner:
```
docker model run hf.co/Jyo-K/Fine-Tuned-Qwen2.5_1B
```

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Jyotirmoy Konwar
Funded by No one:
Shared by Me:
Model type: Qwen, LLM, Transformer
Language(s) (NLP):
License: none
Finetuned from model Qwen2.5 1.5B Instruct:

Model Sources [optional]

Repository: TO be uploaded on my Github soon
Paper :
Demo :

Uses

Direct Use

This is for my portfolio project for agentic AI

Downstream Use [optional]

Out-of-Scope Use

Idk

Bias, Risks, and Limitations

Not good fine tuning

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

This is just to showcase my skills in my portfolio. Not for any commercial use. I am not liable for any hurt or problems caused by this model. Preferably Do Not Use This Model Anywhere

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

Jyo-K/Med_Agent_Dataset

Training Procedure

Preprocessing [optional]

To Alpaca format

Training Hyperparameters

Training regime: fp4

Speeds, Sizes, Times [optional]

100 steps only in training

Evaluation

Testing Data, Factors & Metrics

Testing Data

None

Factors

None

Metrics

None

Results

Idk

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: T4 on Google Colab
Hours used: Needed 5 hours for this because of the SHIT INTERNET PROVIDED MY EIB RGIPT
Cloud Provider: Google Colab
Compute Region: Google knows
Carbon Emitted: Google knows

Technical Specifications [optional]

Model Architecture and Objective

Qwen2.5

Compute Infrastructure

Idk

Hardware

Software

Unsloth

Glossary [optional]

Model Card Authors

Jyotirmoy Konwar

Model Card Contact

jyotirmoykonwarjk@gmail.com or my linkedin

Downloads last month: 6

Safetensors

Model size

2B params

Tensor type

F16

Model tree for Jyo-K/Fine-Tuned-Qwen2.5_1B

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Finetuned

unsloth/Qwen2.5-1.5B-Instruct

Finetuned

(293)

this model

Dataset used to train Jyo-K/Fine-Tuned-Qwen2.5_1B

Space using Jyo-K/Fine-Tuned-Qwen2.5_1B 1

Paper for Jyo-K/Fine-Tuned-Qwen2.5_1B

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 61