Instructions to use kash8080/Mantis-50M-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kash8080/Mantis-50M-Base with Transformers:

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

pipe = pipeline("text-generation", model="kash8080/Mantis-50M-Base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kash8080/Mantis-50M-Base")
model = AutoModelForCausalLM.from_pretrained("kash8080/Mantis-50M-Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kash8080/Mantis-50M-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kash8080/Mantis-50M-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kash8080/Mantis-50M-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kash8080/Mantis-50M-Base

SGLang

How to use kash8080/Mantis-50M-Base 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 "kash8080/Mantis-50M-Base" \
    --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": "kash8080/Mantis-50M-Base",
		"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 "kash8080/Mantis-50M-Base" \
        --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": "kash8080/Mantis-50M-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kash8080/Mantis-50M-Base with Docker Model Runner:
```
docker model run hf.co/kash8080/Mantis-50M-Base
```

Mantis-50M-Base / tokenizer_config.json

kash8080

Mantis-50M-Base: final checkpoint (step 34,000), model card, evals

f8bdce7 verified 2 days ago

Raw History Blame Contribute Delete

278 Bytes

{
  "backend": "tokenizers",
  "eos_token": "<|endoftext|>",
  "model_max_length": 1024,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "clean_up_tokenization_spaces": false,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ]
}

	{
	"backend": "tokenizers",
	"eos_token": "<\|endoftext\|>",
	"model_max_length": 1024,
	"pad_token": "<\|endoftext\|>",
	"tokenizer_class": "PreTrainedTokenizerFast",
	"clean_up_tokenization_spaces": false,
	"model_input_names": [
	"input_ids",
	"attention_mask"
	]
	}