Instructions to use tqfang229/llama-2-7b-atomic2020 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tqfang229/llama-2-7b-atomic2020 with Transformers:

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

pipe = pipeline("text-generation", model="tqfang229/llama-2-7b-atomic2020")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tqfang229/llama-2-7b-atomic2020")
model = AutoModelForCausalLM.from_pretrained("tqfang229/llama-2-7b-atomic2020")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tqfang229/llama-2-7b-atomic2020 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tqfang229/llama-2-7b-atomic2020"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tqfang229/llama-2-7b-atomic2020",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tqfang229/llama-2-7b-atomic2020

SGLang

How to use tqfang229/llama-2-7b-atomic2020 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 "tqfang229/llama-2-7b-atomic2020" \
    --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": "tqfang229/llama-2-7b-atomic2020",
		"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 "tqfang229/llama-2-7b-atomic2020" \
        --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": "tqfang229/llama-2-7b-atomic2020",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tqfang229/llama-2-7b-atomic2020 with Docker Model Runner:
```
docker model run hf.co/tqfang229/llama-2-7b-atomic2020
```

llama-2-7b-atomic2020 / tokenizer_config.json

tqfang229

Upload folder using huggingface_hub

5478519 verified almost 2 years ago

raw

history blame contribute delete

4.48 kB

	{
	"added_tokens_decoder": {
	"0": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<s>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32000": {
	"content": "<CLS>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32001": {
	"content": "<SEP>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32002": {
	"content": "<EOD>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32003": {
	"content": "<MASK>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32004": {
	"content": "<PAD>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32005": {
	"content": "[bib_ref]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32006": {
	"content": "[/bib_ref]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32007": {
	"content": "[fig_ref]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32008": {
	"content": "[/fig_ref]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32009": {
	"content": "[bib]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32010": {
	"content": "[/bib]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32011": {
	"content": "[fig]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32012": {
	"content": "[/fig]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32013": {
	"content": "[table]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32014": {
	"content": "[/table]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32015": {
	"content": "[formula]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32016": {
	"content": "[/formula]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32017": {
	"content": "<\|im_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32018": {
	"content": "<\|im_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [
	"[bib_ref]",
	"[/bib_ref]",
	"[fig_ref]",
	"[/fig_ref]",
	"[bib]",
	"[/bib]",
	"[fig]",
	"[/fig]",
	"[table]",
	"[/table]",
	"[formula]",
	"[/formula]",
	"<\|im_start\|>",
	"<\|im_end\|>"
	],
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": false,
	"cls_token": "<CLS>",
	"eos_token": "<\|im_end\|>",
	"legacy": true,
	"mask_token": "<MASK>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<PAD>",
	"sep_token": "<SEP>",
	"sp_model_kwargs": {},
	"tokenizer_class": "LlamaTokenizer",
	"unk_token": "<unk>",
	"use_default_system_prompt": false
	}