Instructions to use RuVI-AI/Pragya-EXP3-CHAT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RuVI-AI/Pragya-EXP3-CHAT with Transformers:

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

pipe = pipeline("text-generation", model="RuVI-AI/Pragya-EXP3-CHAT", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("RuVI-AI/Pragya-EXP3-CHAT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RuVI-AI/Pragya-EXP3-CHAT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RuVI-AI/Pragya-EXP3-CHAT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RuVI-AI/Pragya-EXP3-CHAT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RuVI-AI/Pragya-EXP3-CHAT

SGLang

How to use RuVI-AI/Pragya-EXP3-CHAT 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 "RuVI-AI/Pragya-EXP3-CHAT" \
    --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": "RuVI-AI/Pragya-EXP3-CHAT",
		"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 "RuVI-AI/Pragya-EXP3-CHAT" \
        --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": "RuVI-AI/Pragya-EXP3-CHAT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RuVI-AI/Pragya-EXP3-CHAT with Docker Model Runner:
```
docker model run hf.co/RuVI-AI/Pragya-EXP3-CHAT
```

Pragya-EXP3-CHAT / tokenizer_config.json

ArushBuilds

Upload checkpoint-15858 (SFT, final step)

f1ef71c verified about 23 hours ago

Raw History Blame Contribute Delete

626 Bytes

{
  "added_tokens_decoder": {
    "12287": {
      "content": "<|bos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_pragya.PragyaTokenizer",
      null
    ]
  },
  "backend": "custom",
  "bos_token": "<|bos|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|bos|>",
  "is_local": false,
  "local_files_only": false,
  "model_max_length": 1024,
  "pad_token": "<|bos|>",
  "padding_side": "left",
  "tokenizer_class": "PragyaTokenizer",
  "unk_token": "<|bos|>"
}

	{
	"added_tokens_decoder": {
	"12287": {
	"content": "<\|bos\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"auto_map": {
	"AutoTokenizer": [
	"tokenization_pragya.PragyaTokenizer",
	null
	]
	},
	"backend": "custom",
	"bos_token": "<\|bos\|>",
	"clean_up_tokenization_spaces": false,
	"eos_token": "<\|bos\|>",
	"is_local": false,
	"local_files_only": false,
	"model_max_length": 1024,
	"pad_token": "<\|bos\|>",
	"padding_side": "left",
	"tokenizer_class": "PragyaTokenizer",
	"unk_token": "<\|bos\|>"
	}