Instructions to use manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq with Transformers:

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

pipe = pipeline("text-generation", model="manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq")

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

tokenizer = AutoTokenizer.from_pretrained("manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq")
model = AutoModelForCausalLM.from_pretrained("manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq

SGLang

How to use manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq 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 "manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq" \
    --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": "manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq",
		"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 "manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq" \
        --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": "manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq with Docker Model Runner:
```
docker model run hf.co/manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq
```

all-MiniLM-L6-v2 (Quantized)

Description

This model is a 4-bit quantized version of the original sentence-transformers/all-MiniLM-L6-v2 model, optimized for reduced memory usage while maintaining performance.

Quantization Details

Quantization Type: 4-bit
bnb_4bit_quant_type: nf4
bnb_4bit_use_double_quant: True
bnb_4bit_compute_dtype: bfloat16
bnb_4bit_quant_storage: uint8
Original Footprint: 90.99 MB (FLOAT32)
Quantized Footprint: 53.83 MB (UINT8)
Memory Reduction: 40.8%

Usage

from transformers import AutoModel, AutoTokenizer

model_name = "all-MiniLM-L6-v2-bnb-4bit-nf4"
model = AutoModel.from_pretrained(
    "manu02/all-MiniLM-L6-v2-bnb-4bit-nf4",
)
tokenizer = AutoTokenizer.from_pretrained("manu02/all-MiniLM-L6-v2-bnb-4bit-nf4", use_fast=True)

Downloads last month: 48

Safetensors

Model size

23.1M params

Tensor type

F32

Model tree for manu02/all-MiniLM-L6-v2-bnb-4bit-nf4-dq

Base model

nreimers/MiniLM-L6-H384-uncased

Quantized

sentence-transformers/all-MiniLM-L6-v2

Quantized

(132)

this model