Instructions to use Tensoic/jalwa-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tensoic/jalwa-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="Tensoic/jalwa-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tensoic/jalwa-1.5B")
model = AutoModelForCausalLM.from_pretrained("Tensoic/jalwa-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tensoic/jalwa-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tensoic/jalwa-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tensoic/jalwa-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tensoic/jalwa-1.5B

SGLang

How to use Tensoic/jalwa-1.5B 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 "Tensoic/jalwa-1.5B" \
    --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": "Tensoic/jalwa-1.5B",
		"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 "Tensoic/jalwa-1.5B" \
        --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": "Tensoic/jalwa-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tensoic/jalwa-1.5B with Docker Model Runner:
```
docker model run hf.co/Tensoic/jalwa-1.5B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Task	Shot	Accuracy	Precision	Recall	F1 Score
indicxparaphrase	5	0.6119	0.9516	0.2358	0.3779
indicxparaphrase	0	0.7268	0.8650	0.5375	0.6630
indicxnli	0	0.4689	0.6390	0.4689	0.3782
indicxnli	5	0.5022	0.5180	0.5022	0.4651
indicsentiment	0	0.8367	0.7511	1.0000	0.8579
indicsentiment	5	0.9689	0.9894	0.9472	0.9678
indiccopa	0	0.6102	0.5701	0.8604	0.6858
indiccopa	5	0.7194	0.7000	0.7568	0.7273

Todo Tasks:

indicheadline
indicqa
in22 Dataset link link doesnt work for now.
Comparisons with other Indic models.

Downloads last month: -

Safetensors

Model size

1B params

Tensor type

F32

Model tree for Tensoic/jalwa-1.5B

Base model

tinycompany/ShawtyIsBad-nomic1.5

Finetuned

(1)

this model