Instructions to use 2p8xx/Foundation-Sec-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 2p8xx/Foundation-Sec-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="2p8xx/Foundation-Sec-8B-Instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("2p8xx/Foundation-Sec-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("2p8xx/Foundation-Sec-8B-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 2p8xx/Foundation-Sec-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "2p8xx/Foundation-Sec-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "2p8xx/Foundation-Sec-8B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/2p8xx/Foundation-Sec-8B-Instruct

SGLang

How to use 2p8xx/Foundation-Sec-8B-Instruct 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 "2p8xx/Foundation-Sec-8B-Instruct" \
    --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": "2p8xx/Foundation-Sec-8B-Instruct",
		"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 "2p8xx/Foundation-Sec-8B-Instruct" \
        --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": "2p8xx/Foundation-Sec-8B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use 2p8xx/Foundation-Sec-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/2p8xx/Foundation-Sec-8B-Instruct
```

2p8xx commited on May 17, 2025

Commit

ffe01c3

verified ·

1 Parent(s): 1cd6ff5

Upload tokenizer

Browse files

Files changed (1) hide show

tokenizer_config.json +0 -1

tokenizer_config.json CHANGED Viewed

@@ -2124,7 +2124,6 @@
     "[/FORMULA]"
   ],
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{% for message in messages %}{% if message['role'] == 'system' %}{{ message['content'] }}{% endif %}{% endfor %}\n\n### Input:\n{% for message in messages %}{% if message['role'] == 'user' %}{{ message['content'] }}{% endif %}{% endfor %}\n\n### Response:\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "extra_special_tokens": {},

     "[/FORMULA]"
   ],
   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "extra_special_tokens": {},