Instructions to use DivyaRani/TallyAssistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DivyaRani/TallyAssistant with Transformers:

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

pipe = pipeline("text-generation", model="DivyaRani/TallyAssistant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DivyaRani/TallyAssistant")
model = AutoModelForCausalLM.from_pretrained("DivyaRani/TallyAssistant", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DivyaRani/TallyAssistant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DivyaRani/TallyAssistant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DivyaRani/TallyAssistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DivyaRani/TallyAssistant

SGLang

How to use DivyaRani/TallyAssistant 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 "DivyaRani/TallyAssistant" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DivyaRani/TallyAssistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "DivyaRani/TallyAssistant" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DivyaRani/TallyAssistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DivyaRani/TallyAssistant with Docker Model Runner:
```
docker model run hf.co/DivyaRani/TallyAssistant
```

TallyAssistant / training_config.json

DivyaRani

Upload folder using huggingface_hub

3b3bb07 verified about 1 year ago

Raw

History Blame Contribute Delete

1.41 kB

	{
	"teacher_model": "gpt2-large",
	"student_model": "distilgpt2",
	"tokenizer_model": "gpt2",
	"batch_size": 4,
	"max_length": 256,
	"num_epochs": 3,
	"learning_rate": 5e-05,
	"distillation_alpha": 0.7,
	"student_lm_beta": 0.3,
	"dataset_file": "/home/divyarani.k/Internship-2025-Team1/Distillation/Model_Exploration/Distillation-Gpt2-DistilGpt/F-Tallyqa.csv",
	"train_samples": 106414,
	"val_samples": 11824,
	"eval_samples": 100,
	"best_validation_loss": 1.8084159012737713,
	"evaluation_metrics": {
	"rouge1_teacher_student_before": 0.3164868777314132,
	"rouge2_teacher_student_before": 0.07499568529627544,
	"rougeL_teacher_student_before": 0.18821303864954625,
	"cosine_similarity_teacher_student_before": 0.36006441712379456,
	"rouge1_teacher_student_after": 0.3048857745421187,
	"rouge2_teacher_student_after": 0.06675678541680866,
	"rougeL_teacher_student_after": 0.18748940481226373,
	"cosine_similarity_teacher_student_after": 0.4749462604522705,
	"rouge1_student_before_student_after": 0.2562567617366068,
	"rouge2_student_before_student_after": 0.0373565907888051,
	"rougeL_student_before_student_after": 0.14784319087594555,
	"cosine_similarity_student_before_student_after": 0.33844634890556335,
	"avg_teacher_time": 0.9765390038490296,
	"avg_student_before_time": 0.27398345947265623,
	"avg_student_after_time": 0.29969048976898194
	}
	}