Instructions to use broalantap/Llama3-Compressor-Adapter-4-12000steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use broalantap/Llama3-Compressor-Adapter-4-12000steps with Transformers:

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

pipe = pipeline("text-generation", model="broalantap/Llama3-Compressor-Adapter-4-12000steps")

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

tokenizer = AutoTokenizer.from_pretrained("broalantap/Llama3-Compressor-Adapter-4-12000steps")
model = AutoModelForCausalLM.from_pretrained("broalantap/Llama3-Compressor-Adapter-4-12000steps", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use broalantap/Llama3-Compressor-Adapter-4-12000steps with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "broalantap/Llama3-Compressor-Adapter-4-12000steps"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "broalantap/Llama3-Compressor-Adapter-4-12000steps",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/broalantap/Llama3-Compressor-Adapter-4-12000steps

SGLang

How to use broalantap/Llama3-Compressor-Adapter-4-12000steps 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 "broalantap/Llama3-Compressor-Adapter-4-12000steps" \
    --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": "broalantap/Llama3-Compressor-Adapter-4-12000steps",
		"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 "broalantap/Llama3-Compressor-Adapter-4-12000steps" \
        --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": "broalantap/Llama3-Compressor-Adapter-4-12000steps",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use broalantap/Llama3-Compressor-Adapter-4-12000steps with Docker Model Runner:
```
docker model run hf.co/broalantap/Llama3-Compressor-Adapter-4-12000steps
```

Llama3-Compressor-Adapter-4-12000steps / tokenizer_config.json

broalantap

Upload tokenizer

1931205 verified over 1 year ago

Raw History Blame Contribute Delete

12.7 kB

	{
	"add_prefix_space": false,
	"added_tokens_decoder": {
	"50256": {
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50257": {
	"content": "<mem_0>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50258": {
	"content": "<mem_1>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50259": {
	"content": "<mem_2>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50260": {
	"content": "<mem_3>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50261": {
	"content": "<mem_4>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50262": {
	"content": "<mem_5>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50263": {
	"content": "<mem_6>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50264": {
	"content": "<mem_7>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50265": {
	"content": "<mem_8>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50266": {
	"content": "<mem_9>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50267": {
	"content": "<mem_10>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50268": {
	"content": "<mem_11>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50269": {
	"content": "<mem_12>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50270": {
	"content": "<mem_13>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50271": {
	"content": "<mem_14>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50272": {
	"content": "<mem_15>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50273": {
	"content": "<mem_16>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50274": {
	"content": "<mem_17>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50275": {
	"content": "<mem_18>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50276": {
	"content": "<mem_19>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50277": {
	"content": "<mem_20>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50278": {
	"content": "<mem_21>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50279": {
	"content": "<mem_22>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50280": {
	"content": "<mem_23>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50281": {
	"content": "<mem_24>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50282": {
	"content": "<mem_25>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50283": {
	"content": "<mem_26>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50284": {
	"content": "<mem_27>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50285": {
	"content": "<mem_28>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50286": {
	"content": "<mem_29>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50287": {
	"content": "<mem_30>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50288": {
	"content": "<mem_31>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50289": {
	"content": "<mem_32>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50290": {
	"content": "<mem_33>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50291": {
	"content": "<mem_34>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50292": {
	"content": "<mem_35>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50293": {
	"content": "<mem_36>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50294": {
	"content": "<mem_37>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50295": {
	"content": "<mem_38>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50296": {
	"content": "<mem_39>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50297": {
	"content": "<mem_40>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50298": {
	"content": "<mem_41>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50299": {
	"content": "<mem_42>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50300": {
	"content": "<mem_43>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50301": {
	"content": "<mem_44>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50302": {
	"content": "<mem_45>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50303": {
	"content": "<mem_46>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50304": {
	"content": "<mem_47>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50305": {
	"content": "<mem_48>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50306": {
	"content": "<mem_49>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50307": {
	"content": "<mem_50>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50308": {
	"content": "<mem_51>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50309": {
	"content": "<mem_52>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50310": {
	"content": "<mem_53>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50311": {
	"content": "<mem_54>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50312": {
	"content": "<mem_55>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50313": {
	"content": "<mem_56>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50314": {
	"content": "<mem_57>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50315": {
	"content": "<mem_58>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50316": {
	"content": "<mem_59>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50317": {
	"content": "<mem_60>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50318": {
	"content": "<mem_61>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50319": {
	"content": "<mem_62>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"50320": {
	"content": "<mem_63>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [
	"<mem_0>",
	"<mem_1>",
	"<mem_2>",
	"<mem_3>",
	"<mem_4>",
	"<mem_5>",
	"<mem_6>",
	"<mem_7>",
	"<mem_8>",
	"<mem_9>",
	"<mem_10>",
	"<mem_11>",
	"<mem_12>",
	"<mem_13>",
	"<mem_14>",
	"<mem_15>",
	"<mem_16>",
	"<mem_17>",
	"<mem_18>",
	"<mem_19>",
	"<mem_20>",
	"<mem_21>",
	"<mem_22>",
	"<mem_23>",
	"<mem_24>",
	"<mem_25>",
	"<mem_26>",
	"<mem_27>",
	"<mem_28>",
	"<mem_29>",
	"<mem_30>",
	"<mem_31>",
	"<mem_32>",
	"<mem_33>",
	"<mem_34>",
	"<mem_35>",
	"<mem_36>",
	"<mem_37>",
	"<mem_38>",
	"<mem_39>",
	"<mem_40>",
	"<mem_41>",
	"<mem_42>",
	"<mem_43>",
	"<mem_44>",
	"<mem_45>",
	"<mem_46>",
	"<mem_47>",
	"<mem_48>",
	"<mem_49>",
	"<mem_50>",
	"<mem_51>",
	"<mem_52>",
	"<mem_53>",
	"<mem_54>",
	"<mem_55>",
	"<mem_56>",
	"<mem_57>",
	"<mem_58>",
	"<mem_59>",
	"<mem_60>",
	"<mem_61>",
	"<mem_62>",
	"<mem_63>"
	],
	"bos_token": "<\|endoftext\|>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|endoftext\|>",
	"model_max_length": 1024,
	"pad_token": "<\|endoftext\|>",
	"tokenizer_class": "GPT2Tokenizer",
	"unk_token": "<\|endoftext\|>"
	}