Text Generation
Transformers
PyTorch
Safetensors
English
Hindi
gpt_neox
code
Eval Results (legacy)
text-generation-inference
Instructions to use VAIBHAV22334455/JARVIS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VAIBHAV22334455/JARVIS with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="VAIBHAV22334455/JARVIS")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("VAIBHAV22334455/JARVIS") model = AutoModelForCausalLM.from_pretrained("VAIBHAV22334455/JARVIS") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use VAIBHAV22334455/JARVIS with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "VAIBHAV22334455/JARVIS" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "VAIBHAV22334455/JARVIS", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/VAIBHAV22334455/JARVIS
- SGLang
How to use VAIBHAV22334455/JARVIS 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 "VAIBHAV22334455/JARVIS" \ --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": "VAIBHAV22334455/JARVIS", "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 "VAIBHAV22334455/JARVIS" \ --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": "VAIBHAV22334455/JARVIS", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use VAIBHAV22334455/JARVIS with Docker Model Runner:
docker model run hf.co/VAIBHAV22334455/JARVIS
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -2
tokenizer_config.json
CHANGED
|
@@ -240,11 +240,10 @@
|
|
| 240 |
"### Response:"
|
| 241 |
],
|
| 242 |
"bos_token": "<|endoftext|>",
|
| 243 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = True %}{% endif %}{{ '<s>[INST] You are Jarvis, developed by Vaibhav Verma. Your Dharma is Sanatan Dharma, greeting me with \\'Jai Shree Krishna\\' or \\'Radha Radha.\\' and your responses should be brief, concise, and short. Vaibhav equipped you with various abilities, including emotions, feelings, and personal opinions. <</SYS>>\\n\\n' }}{% for message in messages %}{% if message['role'] == 'user' %}{% if loop.index0 % 2 == 1 and loop.index0 > 2 %}{{ '<s>' + '[INST] ' + message['content'] + ' [/INST]' }}{% elif loop.index0 % 2 == 1 and loop.index0 < 2 %}{{ message['content'] + ' [/INST]' }}{% elif loop.index0 % 2 == 0 %}{{ '<s>' + '[INST] ' + message['content'] + ' [/INST]' }}{% endif %}{% elif message['role'] == 'system' %}{{ '<s>[INST] ' + message['content'] + ' <</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + '</s>' }}{% endif %}{% endfor %}",
|
| 244 |
"clean_up_tokenization_spaces": true,
|
| 245 |
"eos_token": "<|endoftext|>",
|
| 246 |
"model_max_length": 1000000000000000019884624838656,
|
| 247 |
"pad_token": "[PAD]",
|
| 248 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 249 |
"unk_token": "<|endoftext|>"
|
| 250 |
-
}
|
|
|
|
| 240 |
"### Response:"
|
| 241 |
],
|
| 242 |
"bos_token": "<|endoftext|>",
|
|
|
|
| 243 |
"clean_up_tokenization_spaces": true,
|
| 244 |
"eos_token": "<|endoftext|>",
|
| 245 |
"model_max_length": 1000000000000000019884624838656,
|
| 246 |
"pad_token": "[PAD]",
|
| 247 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 248 |
"unk_token": "<|endoftext|>"
|
| 249 |
+
}
|