All MiniLM L6 V2 GGUF

🚀 all-MiniLM-L6-v2 GGUF Models

This project offers all-MiniLM-L6-v2 GGUF models, which map sentences and paragraphs to a 384-dimensional dense vector space. These models are suitable for tasks such as clustering and semantic search, providing efficient and accurate solutions.

🚀 Quick Start

Choosing the Right Model Format

Selecting the appropriate model format depends on your hardware capabilities and memory constraints. Here are the details of different formats:

BF16 (Brain Float 16) – Use if BF16 acceleration is available

• A 16-bit floating-point format designed for faster computation while retaining good precision.
• Provides similar dynamic range as FP32 but with lower memory usage.
• Recommended if your hardware supports BF16 acceleration (check your device’s specs).
• Ideal for high-performance inference with reduced memory footprint compared to FP32.

📌 Use BF16 if: ✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). ✔ You want higher precision while saving memory. ✔ You plan to requantize the model into another format.

📌 Avoid BF16 if: ❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower). ❌ You need compatibility with older devices that lack BF16 optimization.

F16 (Float 16) – More widely supported than BF16

• A 16-bit floating-point format with high precision but a smaller range of values than BF16.
• Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
• Slightly lower numerical precision than BF16 but generally sufficient for inference.

📌 Use F16 if: ✔ Your hardware supports FP16 but not BF16. ✔ You need a balance between speed, memory usage, and accuracy. ✔ You are running on a GPU or another device optimized for FP16 computations.

📌 Avoid F16 if: ❌ Your device lacks native FP16 support (it may run slower than expected). ❌ You have memory limitations.

Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference

Quantization reduces model size and memory usage while maintaining as much accuracy as possible.

• Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision.
• Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory.

📌 Use Quantized Models if: ✔ You are running inference on a CPU and need an optimized model. ✔ Your device has low VRAM and cannot load full-precision models. ✔ You want to reduce memory footprint while keeping reasonable accuracy.

📌 Avoid Quantized Models if: ❌ You need maximum accuracy (full-precision models are better for this). ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).

Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)

These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint.

• IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency.
  • Use case: Best for ultra-low-memory devices where even Q4_K is too large.
  • Trade-off: Lower accuracy compared to higher-bit quantizations.
• IQ3_S: Small block size for maximum memory efficiency.
  • Use case: Best for low-memory devices where IQ3_XS is too aggressive.
• IQ3_M: Medium block size for better accuracy than IQ3_S.
  • Use case: Suitable for low-memory devices where IQ3_S is too limiting.
• Q4_K: 4-bit quantization with block-wise optimization for better accuracy.
  • Use case: Best for low-memory devices where Q6_K is too large.
• Q4_0: Pure 4-bit quantization, optimized for ARM devices.
  • Use case: Best for ARM-based devices or low-memory environments.

Summary Table: Model Format Selection

📦 Installation

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F

#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)

print("Sentence embeddings:")
print(sentence_embeddings)

📚 Documentation

Included Files & Details

all-MiniLM-L6-v2-bf16.gguf

• Model weights preserved in BF16.
• Use this if you want to requantize the model into a different format.
• Best if your device supports BF16 acceleration.

all-MiniLM-L6-v2-f16.gguf

• Model weights stored in F16.
• Use if your device supports FP16, especially if BF16 is not available.

all-MiniLM-L6-v2-bf16-q8_0.gguf

• Output & embeddings remain in BF16.
• All other layers quantized to Q8_0.
• Use if your device supports BF16 and you want a quantized version.

all-MiniLM-L6-v2-f16-q8_0.gguf

• Output & embeddings remain in F16.
• All other layers quantized to Q8_0.

all-MiniLM-L6-v2-q4_k.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q4_K.
• Good for CPU inference with limited memory.

all-MiniLM-L6-v2-q4_k_s.gguf

• Smallest Q4_K variant, using less memory at the cost of accuracy.
• Best for very low-memory setups.

all-MiniLM-L6-v2-q6_k.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q6_K .

all-MiniLM-L6-v2-q8_0.gguf

• Fully Q8 quantized model for better accuracy.
• Requires more memory but offers higher precision.

all-MiniLM-L6-v2-iq3_xs.gguf

• IQ3_XS quantization, optimized for extreme memory efficiency.
• Best for ultra-low-memory devices.

all-MiniLM-L6-v2-iq3_m.gguf

• IQ3_M quantization, offering a medium block size for better accuracy.
• Suitable for low-memory devices.

all-MiniLM-L6-v2-q4_0.gguf

• Pure Q4_0 quantization, optimized for ARM devices.
• Best for low-memory environments.
• Prefer IQ4_NL for better accuracy.

Testing the Models

Please click like ❤. Also, I’d really appreciate it if you could test my Network Monitor Assistant at 👉 Network Monitor Assitant. 💬 Click the chat icon (bottom right of the main and dashboard pages). Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM.

What I'm Testing

I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 🟡 TestLLM – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works!

The other Available AI Assistants

🟢 TurboLLM – Uses gpt-4o-mini Fast! Note: tokens are limited since OpenAI models are pricey, but you can Login or Download the Free Network Monitor agent to get more tokens, Alternatively use the TestLLM. 🔵 HugLLM – Runs open-source Hugging Face models Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)

🔧 Technical Details

Background

The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained nreimers/MiniLM-L6-H384-uncased model and fine-tuned it on a 1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset. We developed this model during the Community week using JAX/Flax for NLP & CV, organized by Hugging Face. We developed this model as part of the project: Train the Best Sentence Embedding Model Ever with 1B Training Pairs. We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.

Intended uses

Our model is intended to be used as a sentence and short paragraph encoder. Given an input text, it outputs a vector which captures the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks. By default, input text longer than 256 word pieces is truncated.

Training procedure

Pre-training

We use the pretrained nreimers/MiniLM-L6-H384-uncased model. Please refer to the model card for more detailed information about the pre-training procedure.

Fine-tuning

We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch. We then apply the cross entropy loss by comparing with true pairs.

Hyper parameters

We trained our model on a TPU v3-8. We train the model during 100k steps using a batch size of 1024 (128 per TPU core). We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with a 2e-5 learning rate. The full training script is accessible in this current repository: train_script.py.

Training data

We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences. We sampled each dataset given a weighted probability which configuration is detailed in the data_config.json file.

📄 License

This project is licensed under the Apache-2.0 license.