Instructions to use lamm-mit/BioinspiredLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lamm-mit/BioinspiredLLM with Transformers:

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

pipe = pipeline("text-generation", model="lamm-mit/BioinspiredLLM")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lamm-mit/BioinspiredLLM")
model = AutoModelForCausalLM.from_pretrained("lamm-mit/BioinspiredLLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lamm-mit/BioinspiredLLM with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lamm-mit/BioinspiredLLM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lamm-mit/BioinspiredLLM:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lamm-mit/BioinspiredLLM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lamm-mit/BioinspiredLLM:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf lamm-mit/BioinspiredLLM:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf lamm-mit/BioinspiredLLM:Q4_K_M

Use Docker

docker model run hf.co/lamm-mit/BioinspiredLLM:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use lamm-mit/BioinspiredLLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lamm-mit/BioinspiredLLM:Q4_K_M

SGLang

How to use lamm-mit/BioinspiredLLM 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 "lamm-mit/BioinspiredLLM" \
    --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": "lamm-mit/BioinspiredLLM",
		"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 "lamm-mit/BioinspiredLLM" \
        --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": "lamm-mit/BioinspiredLLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use lamm-mit/BioinspiredLLM with Ollama:
```
ollama run hf.co/lamm-mit/BioinspiredLLM:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use lamm-mit/BioinspiredLLM with Docker Model Runner:
```
docker model run hf.co/lamm-mit/BioinspiredLLM:Q4_K_M
```

Lemonade

How to use lamm-mit/BioinspiredLLM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lamm-mit/BioinspiredLLM:Q4_K_M

Run and chat with the model

lemonade run user.BioinspiredLLM-Q4_K_M

List all available models

lemonade list

Atomic Chat

mjbuehler commited on Jan 9, 2024

Commit

4b8fad9

1 Parent(s): 3eba84c

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ tags:
 - biological materials
 - bioinspiration
 - machine learning
-- generative AI
 ---
 # BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and Bio-Inspired Materials
@@ -25,7 +25,7 @@ model = PeftModel.from_pretrained('lamm-mit/BioinspiredLLM')
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 ```
-Variants of the model are included, featuring various GGUF versions for use withm llama.cpp, for instance.
 Generate:
 ```

 - biological materials
 - bioinspiration
 - machine learning
+- generative
 ---
 # BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and Bio-Inspired Materials
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 ```
+Variants of the model are included, featuring various GGUF versions for use withm llama.cpp, for instance. In LM Studio, choose the "ChatML" prompt template.
 Generate:
 ```