Instructions to use DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF", dtype="auto", device_map="auto")

llama-cpp-python

How to use DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF",
	filename="strawberry_smoothie-test-q6_k.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use DreadPoor/Strawberry_Smoothie-TEST-Q6_K-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 DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K

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 DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K

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 DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K

Use Docker

docker model run hf.co/DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K

LM Studio
Jan
Ollama
How to use DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF with Ollama:
```
ollama run hf.co/DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K
```

Unsloth Studio

How to use DreadPoor/Strawberry_Smoothie-TEST-Q6_K-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 DreadPoor/Strawberry_Smoothie-TEST-Q6_K-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 DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF with Docker Model Runner:
```
docker model run hf.co/DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K
```

Lemonade

How to use DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF:Q6_K

Run and chat with the model

lemonade run user.Strawberry_Smoothie-TEST-Q6_K-GGUF-Q6_K

List all available models

lemonade list

cassum-test-q5_k_m - off-topic

by ThijsL202 - opened Jan 5

Discussion

ThijsL202

Jan 5

Hey, I haven't tried many models lately since I'm on vacation and left my PC running with cassum-test-q5_k_m

I really like it, it can be a little incoherent from time to time, messing up some minor roles like ex's, family dynamics, etc... but I love the prose(?) it works very well with my minimal input/responses from my end. It's very steerable, doesn't repeat itself/is less repetitive than most models I've tried recently.

And then I saw it taken down. I have no idea if this model right here (DreadPoor/Strawberry_Smoothie-TEST-Q6_K-GGUF) is newer or not since I forgot when I got the model. But I'm loving it, seriously.

Do you have future plans with the merge configuration from that model? Any reason why it's gone? That's all, thank you.

DreadPoor

Owner Jan 6

Hi mate, thanks for the interest.

this here is the recipe for cassum:

models:

model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model: P0x0/Astra-v1-12B
model: ohyeah1/Violet-Lyra-Gutenberg-v2
model: TheDrummer/UnslopNemo-12B-v3
model: Sicarius-Prototyping/Impish_Longtail_12B
model: DreadPoor/Ward-12B-Model_Stock
merge_method: model_stock
base_model: DreadPoor/Ward-12B-Model_Stock
normalize: true
int8_mask: true
dtype: bfloat16

note, it was labelled as "test", that is how i mark "transient" (non-permanent) models. my compute is weak, so testing is slow, and not too extensive.
If i dont like the model, or feel it can be better, or if its outright broken somehow, i delete them. If i feel they are of "passing grade", they get renamed, "graduating" out of being just a "test".

i did delete cassum for this reason, but i can remake it for you, it will be up before long.

i am reworking its recipe, trying to make a better merge, which will also be up soon.

have a nice day/night. Happy new year!