Instructions to use grimjim/lemonade-rebase-32k-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/lemonade-rebase-32k-7B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/lemonade-rebase-32k-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/lemonade-rebase-32k-7B")
model = AutoModelForCausalLM.from_pretrained("grimjim/lemonade-rebase-32k-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grimjim/lemonade-rebase-32k-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/lemonade-rebase-32k-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/lemonade-rebase-32k-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimjim/lemonade-rebase-32k-7B

SGLang

How to use grimjim/lemonade-rebase-32k-7B 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 "grimjim/lemonade-rebase-32k-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/lemonade-rebase-32k-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "grimjim/lemonade-rebase-32k-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/lemonade-rebase-32k-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimjim/lemonade-rebase-32k-7B with Docker Model Runner:
```
docker model run hf.co/grimjim/lemonade-rebase-32k-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

lemonade-rebase-32k-7B

This is a rebase merge using the formula from KatyTheCutie/LemonadeRP-4.5.3 on Mistral v0.2 7B base (instead of v0.1), for 32K context length (eliminating the 4K sliding window), with rope theta set to 100K. No other changes were made.

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using alpindale/Mistral-7B-v0.2-hf as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: alpindale/Mistral-7B-v0.2-hf
dtype: float16
merge_method: task_arithmetic
slices:
- sources:
  - layer_range: [0, 32]
    model: alpindale/Mistral-7B-v0.2-hf
  - layer_range: [0, 32]
    model: NeverSleep/Noromaid-7B-0.4-DPO
    parameters:
      weight: 0.37
  - layer_range: [0, 32]
    model: cgato/Thespis-CurtainCall-7b-v0.2.2
    parameters:
      weight: 0.32
  - layer_range: [0, 32]
    model: NurtureAI/neural-chat-7b-v3-1-16k
    parameters:
      weight: 0.15
  - layer_range: [0, 32]
    model: cgato/Thespis-7b-v0.5-SFTTest-2Epoch
    parameters:
      weight: 0.38
  - layer_range: [0, 32]
    model: tavtav/eros-7b-test
    parameters:
      weight: 0.18