Instructions to use Girikannan/sarvam-eval with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Girikannan/sarvam-eval with Transformers:

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

pipe = pipeline("text-generation", model="Girikannan/sarvam-eval", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Girikannan/sarvam-eval", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Girikannan/sarvam-eval with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Girikannan/sarvam-eval

SGLang

How to use Girikannan/sarvam-eval 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 "Girikannan/sarvam-eval" \
    --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": "Girikannan/sarvam-eval",
		"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 "Girikannan/sarvam-eval" \
        --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": "Girikannan/sarvam-eval",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Girikannan/sarvam-eval with Docker Model Runner:
```
docker model run hf.co/Girikannan/sarvam-eval
```

Methodology

This model represents a fine-tuned version of the Sarvam-30B baseline, developed for the Resilient AI Challenge., developed for the Resilient AI Challenge.

The compression strategy utilized "Post-Training Quantization (PTQ) formatted via compressed-tensors to achieve a W4A16 precision balance.

The primary objective was to maximize energy efficiency while ensuring the model maintains at least 80% of the baseline Sarvam-30b performance.

Model Details

Base Model: sarvam-30b
Compression Precision: W4A16
License: Apache 2.0

Inference Configuration

The model is optimized to run using the vLLM inference engine.

`vllm_config.yaml`

model: ./models/sarvam-30b-compressed-w4a16
quantization: compressed-tensors
kv-cache-dtype: auto
max-model-len: 8192
trust-remote-code: true

Evaluation Metrics

The model has been evaluated against the challenge benchmarks:

Technical Reasoning: Advanced Science and Mathematics problem-solving.
Domain-Specific Expertise: Medical knowledge synthesis.
Linguistic Creativity: Narrative generation in English and Indian languages.
Analytical Logic: Complex logical reasoning and deductive tasks.
Energy Monitoring: Power consumption was tracked using the NVIDIA Management Library (NVML) for GPU draw and TDP-relative estimation for CPU load.

Usage

To serve this model for evaluation, use the following command:

vllm serve --config vllm_config.yaml

Downloads last month: 26

Safetensors

Model size

6B params

Tensor type

I64

I32

F16

Model tree for Girikannan/sarvam-eval

Base model

sarvamai/sarvam-30b

Finetuned

(11)

this model

Girikannan
/

sarvam-eval