Instructions to use Technoculture/Medmerge-tulu-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Technoculture/Medmerge-tulu-70b with Transformers:

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

pipe = pipeline("text-generation", model="Technoculture/Medmerge-tulu-70b")

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

tokenizer = AutoTokenizer.from_pretrained("Technoculture/Medmerge-tulu-70b")
model = AutoModelForCausalLM.from_pretrained("Technoculture/Medmerge-tulu-70b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Technoculture/Medmerge-tulu-70b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Technoculture/Medmerge-tulu-70b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Technoculture/Medmerge-tulu-70b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Technoculture/Medmerge-tulu-70b

SGLang

How to use Technoculture/Medmerge-tulu-70b 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 "Technoculture/Medmerge-tulu-70b" \
    --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": "Technoculture/Medmerge-tulu-70b",
		"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 "Technoculture/Medmerge-tulu-70b" \
        --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": "Technoculture/Medmerge-tulu-70b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Technoculture/Medmerge-tulu-70b with Docker Model Runner:
```
docker model run hf.co/Technoculture/Medmerge-tulu-70b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Medmerge-tulu-70b

Medmerge-tulu-70b is a merge of the following models:

Open LLM Leaderboard

Model Name	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
tulu-2-dpo-70b	72.1	88.99	69.84	65.78	83.27	62.62
Medmerge-tulu-70b	67.81	87.46	70.1	47.89	83.43	56.56

Performance

Clinical Camel demonstrates competitive performance on medical benchmarks.

Table: Five-Shot Performance of Clinical Camel-70B (C70), GPT3.5, GPT4, and Med-PaLM 2 on Various Medical Datasets

Dataset	Medmerge-tulu-70b	ClinicalCamel-70B	GPT3.5	GPT4	Med-PaLM 2
MMLU Anatomy	66.6	65.2	60.7	80.0	77.8
MMLU Clinical Knowledge	72.0	72.8	68.7	86.4	88.3
MMLU College Biology	84.7	81.2	72.9	93.8	94.4
MMLU College Medicine	64.2	68.2	63.6	76.3	80.9
MMLU Medical Genetics	76.0	69.0	68.0	92.0	90.0
MMLU Professional Medicine	75.7	75.0	69.8	93.8	95.2
MedMCQA		54.2	51.0	72.4	71.3
MedQA (USMLE)		60.7	53.6	81.4	79.7
PubMedQA		77.9	60.2	74.4	79.2
USMLE Sample Exam		64.3	58.5	86.6	-

🧩 Configuration

models:
  - model: NousResearch/Llama-2-70b-hf
    # no parameters necessary for base model
  - model: wanglab/ClinicalCamel-70B
    parameters:
      weight: 0.08
      density: 0.45
  - model: epfl-llm/meditron-70b
    parameters:
      weight: 0.08
      density: 0.45
  - model: allenai/tulu-2-dpo-70b
    parameters:
      weight: 0.08
      density: 0.45
merge_method: dare_ties
base_model: NousResearch/Llama-2-70b-hf
parameters:
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Technoculture/Medmerge-tulu-70b"
messages = [{"role": "user", "content": "I am feeling sleepy these days"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 46

Safetensors

Model size

69B params

Tensor type

BF16

Model tree for Technoculture/Medmerge-tulu-70b

Quantizations

2 models

Collection including Technoculture/Medmerge-tulu-70b

Medical Merges

Collection

Playful merges that try to improve small medical LMs by merging them with models with higher reasoning capabilities. • 29 items • Updated Mar 2 • 3