Instructions to use cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq with Transformers:

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

pipe = pipeline("text-generation", model="cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq")
model = AutoModelForCausalLM.from_pretrained("cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq

SGLang

How to use cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq 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 "cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq" \
    --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": "cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq",
		"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 "cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq" \
        --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": "cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq with Docker Model Runner:
```
docker model run hf.co/cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq
```

OpenHathi Base GPTQ

Model creator: Sarvam AI
Original model: sarvamai/OpenHathi-7B-Hi-v0.1-Base

Description

This repo contains GPTQ model files for Sarvam's OpenHathi.

Files are made using AutoGPTQ with following config.

quantization_config : {"bits": 4,
  "group_size": 128,
  "damp_percent": 0.1,
  "desc_act": true,

}

We use a custom dataset which has both Hindi and English wiki articles. We truncate to max_length=1024 and model may not perform well beyond that context size.

Prompt template

This is a base model not tuned for any instructions. Feel free to use any format. Alpaca/Vicuna works fine.

Oobagooba

Standard oobagooba works with exllama2 / autogptq loader

Using in code

from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
from transformers import AutoTokenizer

model_dir = 'cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq'

model = AutoGPTQForCausalLM.from_quantized(model_dir, device="cuda:0")
tokenizer = AutoTokenizer.from_pretrained(model_dir, fast=True)
tokens = tokenizer("do aur do", return_tensors="pt").to(model.device)

print(tokenizer.decode(model.generate(**tokens, max_length=1024)[0]))

Downloads last month: 15

Safetensors

Model size

1B params

Tensor type

I32

F16

Model tree for cmeraki/OpenHathi-7B-Hi-v0.1-Base-gptq

Base model

meta-llama/Llama-2-7b-chat-hf

Quantized

(101)

this model