Instructions to use Aculi/InternLM2-Chat-20B-ToxicRP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aculi/InternLM2-Chat-20B-ToxicRP with Transformers:

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

pipe = pipeline("text-generation", model="Aculi/InternLM2-Chat-20B-ToxicRP")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aculi/InternLM2-Chat-20B-ToxicRP")
model = AutoModelForCausalLM.from_pretrained("Aculi/InternLM2-Chat-20B-ToxicRP")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Aculi/InternLM2-Chat-20B-ToxicRP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aculi/InternLM2-Chat-20B-ToxicRP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aculi/InternLM2-Chat-20B-ToxicRP",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Aculi/InternLM2-Chat-20B-ToxicRP

SGLang

How to use Aculi/InternLM2-Chat-20B-ToxicRP 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 "Aculi/InternLM2-Chat-20B-ToxicRP" \
    --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": "Aculi/InternLM2-Chat-20B-ToxicRP",
		"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 "Aculi/InternLM2-Chat-20B-ToxicRP" \
        --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": "Aculi/InternLM2-Chat-20B-ToxicRP",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Aculi/InternLM2-Chat-20B-ToxicRP with Docker Model Runner:
```
docker model run hf.co/Aculi/InternLM2-Chat-20B-ToxicRP
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

InternLM2-chat-20B-ToxicRP-QLORA-Merged

This Model was Finetuned by me, using the Machine Power of g4rg. Big Thanks to all people that helped me. Do whatever you want with this Model, just dont do anything illegal.

GGUF here: Aculi/InternLM2-Chat-20B-ToxicRP-GGUF

Have fun

This Model uses CHATML btw.

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

output/intervitens_internlm2-limarp-chat-20b-2 + Fischerboot/InternLM2-ToxicRP-QLORA-4Bit

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 48]
    model: output/intervitens_internlm2-limarp-chat-20b-2+Fischerboot/InternLM2-ToxicRP-QLORA-4Bit