Instructions to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF",
	filename="kalm-reranker-v1-small-q4_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-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 KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KaLM-Embedding/KaLM-Reranker-V1-Small-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.KaLM-Reranker-V1-Small-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

llama-cpp folder use cases

by daruokta - opened 4 days ago

Discussion

daruokta

4 days ago

•

edited 4 days ago

Wanna ask, is this llama.cpp version can be use as normal chat for the original t5gemma2? and if so, how to do it?

cosyy

KaLM-Embedding org 4 days ago

Hi, thanks for reaching out!

Sorry to say that this GGUF/llama.cpp version is only for reranking, not for normal chat.

Although it is based on T5Gemma2, the llama.cpp support here implements the KaLM reranker scoring flow: given a query and a passage, it outputs a relevance score. It does not support free-form generation or chat like the original T5Gemma2.

You can use it like:

./llama-kalm-reranker \
  -m kalm-reranker-v1-small-q4_k_m.gguf \
  --query "your query here" \
  --passage "candidate document here"

If you want regular chat or text generation, please use the original T5Gemma2 model with a compatible framework like Transformers.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment