Instructions to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/lightblue_-_reranker_0.5_cont-gguf",
	filename="reranker_0.5_cont.IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M
```

Unsloth Studio new

How to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RichardErkhov/lightblue_-_reranker_0.5_cont-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RichardErkhov/lightblue_-_reranker_0.5_cont-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/lightblue_-_reranker_0.5_cont-gguf to start chatting

Pi new

How to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/lightblue_-_reranker_0.5_cont-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/lightblue_-_reranker_0.5_cont-gguf:Q4_K_M

Run and chat with the model

lemonade run user.lightblue_-_reranker_0.5_cont-gguf-Q4_K_M

List all available models

lemonade list

Quantization made by Richard Erkhov.

Github

Discord

Request more models

reranker_0.5_cont - GGUF

Model creator: https://huggingface.co/lightblue/
Original model: https://huggingface.co/lightblue/reranker_0.5_cont/

Name	Quant method	Size
reranker_0.5_cont.Q2_K.gguf	Q2_K	0.39GB
reranker_0.5_cont.IQ3_XS.gguf	IQ3_XS	0.39GB
reranker_0.5_cont.IQ3_S.gguf	IQ3_S	0.39GB
reranker_0.5_cont.Q3_K_S.gguf	Q3_K_S	0.39GB
reranker_0.5_cont.IQ3_M.gguf	IQ3_M	0.39GB
reranker_0.5_cont.Q3_K.gguf	Q3_K	0.4GB
reranker_0.5_cont.Q3_K_M.gguf	Q3_K_M	0.4GB
reranker_0.5_cont.Q3_K_L.gguf	Q3_K_L	0.42GB
reranker_0.5_cont.IQ4_XS.gguf	IQ4_XS	0.4GB
reranker_0.5_cont.Q4_0.gguf	Q4_0	0.4GB
reranker_0.5_cont.IQ4_NL.gguf	IQ4_NL	0.4GB
reranker_0.5_cont.Q4_K_S.gguf	Q4_K_S	0.45GB
reranker_0.5_cont.Q4_K.gguf	Q4_K	0.46GB
reranker_0.5_cont.Q4_K_M.gguf	Q4_K_M	0.46GB
reranker_0.5_cont.Q4_1.gguf	Q4_1	0.43GB
reranker_0.5_cont.Q5_0.gguf	Q5_0	0.46GB
reranker_0.5_cont.Q5_K_S.gguf	Q5_K_S	0.48GB
reranker_0.5_cont.Q5_K.gguf	Q5_K	0.49GB
reranker_0.5_cont.Q5_K_M.gguf	Q5_K_M	0.49GB
reranker_0.5_cont.Q5_1.gguf	Q5_1	0.49GB
reranker_0.5_cont.Q6_K.gguf	Q6_K	0.61GB
reranker_0.5_cont.Q8_0.gguf	Q8_0	0.63GB

Original model description:

library_name: transformers license: other base_model: Qwen/Qwen2.5-0.5B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: reranker_continuous_train results: []

reranker_continuous_train

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the reranker_continuous_train dataset. It achieves the following results on the evaluation set:

Loss: 0.3195

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4242	0.1	2156	0.3844
0.236	0.2	4312	0.3643
0.6602	0.3	6468	0.3521
0.3464	0.4	8624	0.3472
0.3598	0.5	10780	0.3412
0.3377	0.6	12936	0.3341
0.4547	0.7	15092	0.3258
0.2282	0.8	17248	0.3228
0.2692	0.9	19404	0.3195
0.2059	1.0	21560	0.3195

Framework versions

Transformers 4.46.1
Pytorch 2.4.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3

Downloads last month: 63

GGUF

Model size

0.6B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

Text Ranking

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support