Instructions to use akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal with Transformers:

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

pipe = pipeline("text-generation", model="akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal")
model = AutoModelForCausalLM.from_pretrained("akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal

SGLang

How to use akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal 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 "akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal" \
    --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": "akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal",
		"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 "akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal" \
        --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": "akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal with Docker Model Runner:
```
docker model run hf.co/akoyaki/LeMalin-120b-2.9bpw-exl2-wbcal
```

akoyaki commited on Jan 27, 2024

Commit

967acd0

verified ·

1 Parent(s): 4022f7a

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -1

README.md CHANGED Viewed

@@ -4,4 +4,24 @@ datasets:
 - VatsaDev/worldbuild
 language:
 - en
----

 - VatsaDev/worldbuild
 language:
 - en
+---
+All glory to [Sao10K](https://huggingface.co/Sao10K/WinterGoddess-1.4x-70B-L2) (WinterGoddess), [sophosympatheia](https://huggingface.co/sophosympatheia/Midnight-Rose-70B-v1.0) (Midnight Rose), [ChuckMcSneed](https://huggingface.co/datasets/ChuckMcSneed/NeoEvalPlusN_benchmark) (Datasets), [alpindale](https://huggingface.co/alpindale/goliath-120b) (inspired by Goliath), [cg123](https://github.com/cg123/mergekit) (mergkit)
+A simple personal merge test model, merged for RP, 2.9bpw for 2x3090/2x4090 in a 4~8k context
+Tried three 120b recipes, this one performed surprisingly well, very smart and sensitive
+I haven't tested any benchmarks and I don't care, I just used it for about 6 hours for actual RP use cases (200~300 rounds in total, maximum 120 rounds in a single session), tweaking some samplers and testing the output.
+She was smart enough to grab a casual reference to a setting in 400 tokens, a girl card with a line about being cursed to be transgendered, tested wintergoliath/Goliath/LeMalin, and only LeMalin was able to Roll to the response "Complaining and loathing this cursed body".
+Can follow instructions and requests very well,```Make {{char}} talkative``` immediately makes the character eloquent.
+And she's very sensitive to parameters, in RP where asterisks are heavily used, Goliath's rep_pen starts losing asterisks at 1.2+, and LeMalin will start losing them at 1.04.
+ [The sampler setting](https://files.catbox.moe/eo425d.json) / I just simple used ST's Roleplay template
+ Personal setting for RP : ST lorebook add a lore. constant | trigger 40% | @depth | depth = 1 | Make {{char}} talkative a little, at least one speech line.\nThe following content is a record of a natural conversation between {{user}} and {{char}}:
+ I got 0 replies as {{user}} in 120 rounds of dialogue