Instructions to use InferenceIllusionist/Excalibur-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InferenceIllusionist/Excalibur-7b-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("InferenceIllusionist/Excalibur-7b-GGUF", dtype="auto")

llama-cpp-python

How to use InferenceIllusionist/Excalibur-7b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="InferenceIllusionist/Excalibur-7b-GGUF",
	filename="Excalibur-7b-q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use InferenceIllusionist/Excalibur-7b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf InferenceIllusionist/Excalibur-7b-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf InferenceIllusionist/Excalibur-7b-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf InferenceIllusionist/Excalibur-7b-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf InferenceIllusionist/Excalibur-7b-GGUF:Q8_0

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 InferenceIllusionist/Excalibur-7b-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf InferenceIllusionist/Excalibur-7b-GGUF:Q8_0

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 InferenceIllusionist/Excalibur-7b-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf InferenceIllusionist/Excalibur-7b-GGUF:Q8_0

Use Docker

docker model run hf.co/InferenceIllusionist/Excalibur-7b-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use InferenceIllusionist/Excalibur-7b-GGUF with Ollama:
```
ollama run hf.co/InferenceIllusionist/Excalibur-7b-GGUF:Q8_0
```

Unsloth Studio new

How to use InferenceIllusionist/Excalibur-7b-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 InferenceIllusionist/Excalibur-7b-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 InferenceIllusionist/Excalibur-7b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for InferenceIllusionist/Excalibur-7b-GGUF to start chatting

Docker Model Runner
How to use InferenceIllusionist/Excalibur-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/InferenceIllusionist/Excalibur-7b-GGUF:Q8_0
```

Lemonade

How to use InferenceIllusionist/Excalibur-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull InferenceIllusionist/Excalibur-7b-GGUF:Q8_0

Run and chat with the model

lemonade run user.Excalibur-7b-GGUF-Q8_0

List all available models

lemonade list

Excalibur-7b GGUF

Image generated with Envoid's Model9 SDXL model

FP16 can be found here

Magic-Dolphin-7b was an unexpected surprise. Profoundly satisfied with it as a first attempt. For this follow-up I wanted to target the MMLU benchmark specifically. The challenge this time was placing more weight on Merlinite-7b as an unknown quantity that hasn't been in the spotlight despite its novel LAB tuning method.

Excalibur-7b builds on past success and is the culmination of several learnings:

Measuring KL-divergences for new quantization types brought a deeper understanding of benchmarking and assessing model performance
This signifcantly sped up the testing process by using MMLU as a base, narrowing down over 10 candidate linear merges to 1: merliniteX-blockB1
Reaching the limitations of linear merging necessitated a pivot to reviewing the viability of SLERP, DARE-TIES, and Passthrough methods
Thus a competing candidate merge pool was tested between different merge algorithms. Once more the list was narrowed from 10 candidates to 1: merliniteX-blockF2
merliniteX-blockF2 (SLERP of Magic-Dolphin-7B and jaskier-7b-dpo in unorthadox proportions) was originally planned for release earlier this week
Instead -blockB1 and -blockF2 were merged and the results were placed head to head in a final round of tests. Ultimately a more conventional execution of SLERP showed the best results for the final step.

Sample Question

Bonus Question - Vision Capabilities

Requires additional mistral-7b-mmproj-v1.5-Q4_1.gguf file for vision functionality

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

models/merliniteX-blockB1
models/merliniteX-blockF2

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: models/merliniteX-blockF2
        layer_range: [0, 32]
      - model: models/merliniteX-blockB1
        layer_range: [0, 32]
# or, the equivalent models: syntax:
# models:
#   - model: psmathur/orca_mini_v3_13b
#   - model: garage-bAInd/Platypus2-13B
merge_method: slerp
base_model: models/merliniteX-blockF2
parameters:
  t:
    - filter: self_attn
      value: [1, 0.7, 0.3, 0.5, 0]
    - filter: mlp
      value: [0, 0.3, 0.7, 0.5, 1]
    - value: 0.5 # fallback for rest of tensors
dtype: float16

Downloads last month: 14

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for InferenceIllusionist/Excalibur-7b-GGUF

Base model

InferenceIllusionist/Excalibur-7b

Quantized

(3)

this model

Collection including InferenceIllusionist/Excalibur-7b-GGUF

GGUFs

Collection

I take requests, feel free to drop me a line in the community posts • 31 items • Updated Apr 28 • 3