Instructions to use premkumarkora/kora-2-2b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use premkumarkora/kora-2-2b-it with Transformers:

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

pipe = pipeline("text-generation", model="premkumarkora/kora-2-2b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("premkumarkora/kora-2-2b-it")
model = AutoModelForCausalLM.from_pretrained("premkumarkora/kora-2-2b-it")
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

vLLM

How to use premkumarkora/kora-2-2b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "premkumarkora/kora-2-2b-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "premkumarkora/kora-2-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/premkumarkora/kora-2-2b-it

SGLang

How to use premkumarkora/kora-2-2b-it 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 "premkumarkora/kora-2-2b-it" \
    --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": "premkumarkora/kora-2-2b-it",
		"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 "premkumarkora/kora-2-2b-it" \
        --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": "premkumarkora/kora-2-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use premkumarkora/kora-2-2b-it with Docker Model Runner:
```
docker model run hf.co/premkumarkora/kora-2-2b-it
```

Model Card for Model ID

Model Information

Summary description and brief definition of inputs and outputs.

Description

The text-to-text, decoder-only large language models, available in English, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.

Running with the `pipeline` API

import torch
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="premkumarkora/kora-2-2b-it",
    load_in_4bit=True,                 # actually load 4-bit integer weights
    bnb_4bit_quant_type="nf4",         # NormalFloat4 quantizer
    device_map="auto",                 # shard layers automatically on your GPU(s)
    torch_dtype=torch.bfloat16,        # do matrix-math in BF16 (optional)
)

messages = [
    {"role": "user", "content": "Who are you? Please, answer in pirate-speak."},
]

outputs = pipe(messages, max_new_tokens=256)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)

Developed by: [PremKumar Kora]

Downloads last month: 1

Safetensors

Model size

3B params

Tensor type

F32

F16

Model tree for premkumarkora/kora-2-2b-it

Base model

google/gemma-2-2b

Finetuned

google/gemma-2-2b-it

Quantized

(177)

this model

Model Card for Model ID

Model Information

Description

Running with the pipeline API

Model tree for premkumarkora/kora-2-2b-it

Running with the `pipeline` API