Instructions to use maldv/winter-garden-7b-gamma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maldv/winter-garden-7b-gamma with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="maldv/winter-garden-7b-gamma")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maldv/winter-garden-7b-gamma")
model = AutoModelForCausalLM.from_pretrained("maldv/winter-garden-7b-gamma")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use maldv/winter-garden-7b-gamma with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maldv/winter-garden-7b-gamma"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maldv/winter-garden-7b-gamma",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/maldv/winter-garden-7b-gamma

SGLang

How to use maldv/winter-garden-7b-gamma with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "maldv/winter-garden-7b-gamma" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maldv/winter-garden-7b-gamma",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "maldv/winter-garden-7b-gamma" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maldv/winter-garden-7b-gamma",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use maldv/winter-garden-7b-gamma with Docker Model Runner:
```
docker model run hf.co/maldv/winter-garden-7b-gamma
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Winter Garden 7B - Γ

It was mentioned that we are in the open ai dark winter; so I thought I would make myself a nice winter garden.

An experiment

This time I did something a bit different.

Mistral-7B-v0.1

and merged in

Yarn-Mistral-7b-128k
Thespis-Balanced-7b-v1
ZySec-7B-v1
LemonadeRP-4.5.3
Noromaid-7B-0.4-DPO
Prima-LelantaclesV6-7b
West-Hermes-7B
Capricorn-7B-DPO
kun-kunoichi-v1-DPO-v2-SLERP-7B
Kunoichi-DPO-v2-7B
WestLake-7B-v2-laser-truthy-dpo
StrangeMerges_6-7B-dare_ties
NeuralMarcoro14-7B
multi_verse_model
Multi-Verse-RP-7B
MonarchLake-7B
AlphaMonarch-7B

in an iterative DARE-TIES tree merge, ordering the merge order by tensor-relative cosine similarity until the merge branches resolve to a single value.

Chat Template

Basic Mistral <s>[INST][/INST] works pretty well. It seems smart, but we will see.

Scores

Metric	Score

Downloads last month: 63

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for maldv/winter-garden-7b-gamma

Quantizations

2 models