Instructions to use KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b with Transformers:

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

pipe = pipeline("text-generation", model="KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b")
model = AutoModelForCausalLM.from_pretrained("KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b

SGLang

How to use KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b 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 "KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b" \
    --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": "KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b",
		"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 "KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b" \
        --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": "KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b with Docker Model Runner:
```
docker model run hf.co/KaraKaraWitch/LLENN-v0.69420-Qwen2.5-72b
```

LLENN-v0.69420-Qwen2.5-72b / README.md

KaraKaraWitch

Update README.md

3162216 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

2.12 kB

	---
	license: other
	license_name: qwen
	license_link: https://huggingface.co/Qwen/Qwen2.5-72B/blob/main/LICENSE
	base_model:
	- rombodawg/Rombos-LLM-V2.5-Qwen-72b
	- abacusai/Dracarys2-72B-Instruct
	- EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0
	- ZeusLabs/Chronos-Platinum-72B
	- Qwen/Qwen2.5-72B
	- anthracite-org/magnum-v4-72b
	- m8than/banana-2-b-72b
	language:
	- en
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- mergekit
	- merge

	---

	# LLENN-v0.69420-Qwen2.5-72b

	[![image/png](https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/mYiG-Ndxzqu8ofaBGbOIZ.png)](https://www.youtube.com/watch?v=PaEPo1sUc4Y "Cute Girl with a gun!")

	Model stock merge for fun. Probably final model mix.
	This merge is an answer to people's requests. I really don't wanna do more merges without myself considering to use it.

	### Models Merged

	The following models were included in the merge:
	* [rombodawg/Rombos-LLM-V2.5-Qwen-72b](https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-72b)
	* [abacusai/Dracarys2-72B-Instruct](https://huggingface.co/abacusai/Dracarys2-72B-Instruct)
	* [EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0)
	* [ZeusLabs/Chronos-Platinum-72B](https://huggingface.co/ZeusLabs/Chronos-Platinum-72B)
	* [anthracite-org/magnum-v4-72b](https://huggingface.co/anthracite-org/magnum-v4-72b)
	* [m8than/banana-2-b-72b](https://huggingface.co/m8than/banana-2-b-72b)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	models:
	- model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0
	- model: ZeusLabs/Chronos-Platinum-72B
	- model: anthracite-org/magnum-v4-72b
	- model: abacusai/Dracarys2-72B-Instruct
	- model: rombodawg/Rombos-LLM-V2.5-Qwen-72b
	- model: m8than/banana-2-b-72b

	merge_method: model_stock
	base_model: Qwen/Qwen2.5-72B
	parameters:
	normalize: true
	dtype: bfloat16
	```

	### Prompt Format

	ChatML works for the most part.

	### Sampler Settings

	Personally I use the following:

	```
	Temp: 1.2
	Min P: 0.07
	Rep Pen: 1.1
	```

	Others have suggested the following:

	```
	Temp: 1.1
	Top P: 0.98
	Min P: 0.05
	```