Not-For-All-Audiences

nsfw

Instructions to use Undi95/MLewd-ReMM-L2-Chat-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/MLewd-ReMM-L2-Chat-20B with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/MLewd-ReMM-L2-Chat-20B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/MLewd-ReMM-L2-Chat-20B")
model = AutoModelForMultimodalLM.from_pretrained("Undi95/MLewd-ReMM-L2-Chat-20B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Undi95/MLewd-ReMM-L2-Chat-20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/MLewd-ReMM-L2-Chat-20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/MLewd-ReMM-L2-Chat-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/MLewd-ReMM-L2-Chat-20B

SGLang

How to use Undi95/MLewd-ReMM-L2-Chat-20B 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 "Undi95/MLewd-ReMM-L2-Chat-20B" \
    --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": "Undi95/MLewd-ReMM-L2-Chat-20B",
		"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 "Undi95/MLewd-ReMM-L2-Chat-20B" \
        --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": "Undi95/MLewd-ReMM-L2-Chat-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/MLewd-ReMM-L2-Chat-20B with Docker Model Runner:
```
docker model run hf.co/Undi95/MLewd-ReMM-L2-Chat-20B
```

MLewd-ReMM-L2-Chat-20B / README.md

Undi95

Adding Evaluation Results (#2)

58dac7b over 2 years ago

preview code

raw

history blame contribute delete

3.13 kB

	---
	license: cc-by-nc-4.0
	tags:
	- not-for-all-audiences
	- nsfw
	---

	First :
	```shell
	layer_slices:
	- model: Undi95/MLewd-L2-Chat-13B
	start: 0
	end: 16
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 8
	end: 20
	- model: Undi95/MLewd-L2-Chat-13B
	start: 17
	end: 32
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 21
	end: 40
	```

	Inverted:
	```shell
	layer_slices:
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 0
	end: 16
	- model: Undi95/MLewd-L2-Chat-13B
	start: 8
	end: 20
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 17
	end: 32
	- model: Undi95/MLewd-L2-Chat-13B
	start: 21
	end: 40
	```

	Precise:
	```shell
	layer_slices:
	- model: Undi95/MLewd-L2-Chat-13B
	start: 0
	end: 8
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 4
	end: 12
	- model: Undi95/MLewd-L2-Chat-13B
	start: 9
	end: 16
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 13
	end: 22
	- model: Undi95/MLewd-L2-Chat-13B
	start: 17
	end: 24
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 23
	end: 32
	- model: Undi95/MLewd-L2-Chat-13B
	start: 25
	end: 32
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 33
	end: 40
	```

	PreciseInverted:
	```shell
	layer_slices:
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 0
	end: 8
	- model: Undi95/MLewd-L2-Chat-13B
	start: 4
	end: 12
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 9
	end: 16
	- model: Undi95/MLewd-L2-Chat-13B
	start: 13
	end: 22
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 17
	end: 24
	- model: Undi95/MLewd-L2-Chat-13B
	start: 23
	end: 32
	- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
	start: 25
	end: 32
	- model: Undi95/MLewd-L2-Chat-13B
	start: 33
	end: 40
	```

	Part1 = ReMM v2.1 merged /w MLewd low weight to keep consistency. I call this "dilution" and result show consistency and coherency without repeat/loop beside the small amount of duplicated datas.

	The goal is to find the best way to interlace layers the best way possible to have a sweetspot between 13B and +30B.

	Normal/Inverted is by chunk of 16 layers and Precise/PreciseInverted is by chunk of 8 layers.

	All the models are made of 64(+1) layers. Need testing.

	## Prompt template: Alpaca

	```
	Below is an instruction that describes a task. Write a response that completes the request.

	### Instruction:
	{prompt}

	### Response:
	```
	# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
	Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__MLewd-ReMM-L2-Chat-20B)

	\| Metric \| Value \|
	\|-----------------------\|---------------------------\|
	\| Avg. \| 53.33 \|
	\| ARC (25-shot) \| 62.46 \|
	\| HellaSwag (10-shot) \| 85.62 \|
	\| MMLU (5-shot) \| 59.13 \|
	\| TruthfulQA (0-shot) \| 55.63 \|
	\| Winogrande (5-shot) \| 77.19 \|
	\| GSM8K (5-shot) \| 10.92 \|
	\| DROP (3-shot) \| 22.33 \|