Instructions to use Echelon-AI/medbotlm-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Echelon-AI/medbotlm-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="Echelon-AI/medbotlm-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Echelon-AI/medbotlm-v0.2")
model = AutoModelForMultimodalLM.from_pretrained("Echelon-AI/medbotlm-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Echelon-AI/medbotlm-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Echelon-AI/medbotlm-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Echelon-AI/medbotlm-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Echelon-AI/medbotlm-v0.2

SGLang

How to use Echelon-AI/medbotlm-v0.2 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 "Echelon-AI/medbotlm-v0.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Echelon-AI/medbotlm-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Echelon-AI/medbotlm-v0.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Echelon-AI/medbotlm-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Echelon-AI/medbotlm-v0.2 with Docker Model Runner:
```
docker model run hf.co/Echelon-AI/medbotlm-v0.2
```

llama3-medbotlm-v0.3

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using HPAI-BSC/Llama3-Aloe-8B-Alpha as a base.

Models Merged

The following models were included in the merge:

ruslanmv/Medical-Llama3-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ruslanmv/Medical-Llama3-8B
    parameters:
     weight: 0.50
  - model: HPAI-BSC/Llama3-Aloe-8B-Alpha
    parameters:
     weight: 0.50



base_model: HPAI-BSC/Llama3-Aloe-8B-Alpha
merge_method: task_arithmetic
dtype: bfloat16

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Echelon-AI/medbotlm-v0.2

HPAI-BSC/Llama3-Aloe-8B-Alpha

ruslanmv/Medical-Llama3-8B

Merge model

this model

Spaces using Echelon-AI/medbotlm-v0.2 9

Paper for Echelon-AI/medbotlm-v0.2

Editing Models with Task Arithmetic

Paper • 2212.04089 • Published Dec 8, 2022 • 8