Instructions to use R136a1/MM-ReMM-L2-20B-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use R136a1/MM-ReMM-L2-20B-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="R136a1/MM-ReMM-L2-20B-exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("R136a1/MM-ReMM-L2-20B-exl2")
model = AutoModelForCausalLM.from_pretrained("R136a1/MM-ReMM-L2-20B-exl2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use R136a1/MM-ReMM-L2-20B-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "R136a1/MM-ReMM-L2-20B-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "R136a1/MM-ReMM-L2-20B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/R136a1/MM-ReMM-L2-20B-exl2

SGLang

How to use R136a1/MM-ReMM-L2-20B-exl2 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 "R136a1/MM-ReMM-L2-20B-exl2" \
    --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": "R136a1/MM-ReMM-L2-20B-exl2",
		"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 "R136a1/MM-ReMM-L2-20B-exl2" \
        --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": "R136a1/MM-ReMM-L2-20B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use R136a1/MM-ReMM-L2-20B-exl2 with Docker Model Runner:
```
docker model run hf.co/R136a1/MM-ReMM-L2-20B-exl2
```

R136a1 commited on Oct 17, 2023

Commit

b5e78cf

1 Parent(s): d7e6d06

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -9,13 +9,13 @@ language:
 ## Model details
-Quantized at 3.18bpw with hb 6, This one can actually go full 4K context on 16GB VRAM, will redo the other 20b models later
 Perplexity:
 Base = 6.9504
-3.23 h8 = 7.0138
 Dataset = [wikitext](https://huggingface.co/datasets/wikitext/resolve/refs%2Fconvert%2Fparquet/wikitext-2-v1/test/0000.parquet)

 ## Model details
+Quantized at 3.18bpw with hb 6, This one can actually go full 4K context on 16GB VRAM, will redo the other 20b models later.
 Perplexity:
 Base = 6.9504
+3.18 h6 = 7.0138
 Dataset = [wikitext](https://huggingface.co/datasets/wikitext/resolve/refs%2Fconvert%2Fparquet/wikitext-2-v1/test/0000.parquet)