Instructions to use ramkumarsivakumar/openchat_3.5-ramsprofiledata with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ramkumarsivakumar/openchat_3.5-ramsprofiledata with Transformers:

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

pipe = pipeline("text-generation", model="ramkumarsivakumar/openchat_3.5-ramsprofiledata")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ramkumarsivakumar/openchat_3.5-ramsprofiledata", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ramkumarsivakumar/openchat_3.5-ramsprofiledata with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ramkumarsivakumar/openchat_3.5-ramsprofiledata"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ramkumarsivakumar/openchat_3.5-ramsprofiledata",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ramkumarsivakumar/openchat_3.5-ramsprofiledata

SGLang

How to use ramkumarsivakumar/openchat_3.5-ramsprofiledata 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 "ramkumarsivakumar/openchat_3.5-ramsprofiledata" \
    --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": "ramkumarsivakumar/openchat_3.5-ramsprofiledata",
		"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 "ramkumarsivakumar/openchat_3.5-ramsprofiledata" \
        --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": "ramkumarsivakumar/openchat_3.5-ramsprofiledata",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ramkumarsivakumar/openchat_3.5-ramsprofiledata with Docker Model Runner:
```
docker model run hf.co/ramkumarsivakumar/openchat_3.5-ramsprofiledata
```

openchat_3.5-ramsprofiledata / tokenizer_config.json

ramkumarsivakumar

Upload tokenizer

f8f0d63 verified about 2 years ago

Raw

History Blame Contribute Delete

2.13 kB

	{
	"add_bos_token": true,
	"add_eos_token": false,
	"added_tokens_decoder": {
	"0": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32000": {
	"content": "<\|end_of_turn\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32001": {
	"content": "<\|pad_0\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [
	"<\|end_of_turn\|>",
	"<\|pad_0\|>"
	],
	"bos_token": "<s>",
	"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{{bos_token}}{%- if not ns.found -%}{{'You are an AI assistant and you do your best to answer all questions and requests\n'}}{%- endif %}{%- for message in messages %}{%- if message['role'] == 'system' %}{{ message['content'] }}{%- else %}{%- if message['role'] == 'user' %}{{'Instruction:' + message['content'] + '\n'}}{%- else %}{{'\nOutput:' + message['content'] + '\n<\|EOT\|>\n'}}{%- endif %}{%- endif %}{%- endfor %}{% if add_generation_prompt %}{{'\nOutput:'}}{% endif %}",
	"clean_up_tokenization_spaces": false,
	"eos_token": "<\|end_of_turn\|>",
	"legacy": true,
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<unk>",
	"sp_model_kwargs": {},
	"spaces_between_special_tokens": false,
	"tokenizer_class": "LlamaTokenizer",
	"unk_token": "<unk>",
	"use_default_system_prompt": true
	}