Instructions to use giannisan/multitroll26 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use giannisan/multitroll26 with Transformers:

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

pipe = pipeline("text-generation", model="giannisan/multitroll26")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("giannisan/multitroll26")
model = AutoModelForCausalLM.from_pretrained("giannisan/multitroll26")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use giannisan/multitroll26 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "giannisan/multitroll26"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "giannisan/multitroll26",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/giannisan/multitroll26

SGLang

How to use giannisan/multitroll26 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 "giannisan/multitroll26" \
    --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": "giannisan/multitroll26",
		"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 "giannisan/multitroll26" \
        --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": "giannisan/multitroll26",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use giannisan/multitroll26 with Docker Model Runner:
```
docker model run hf.co/giannisan/multitroll26
```

multitroll26 / README.md

giannisan

Update README.md

8480c71 verified about 2 years ago

preview code

Raw

History Blame Contribute Delete

1.48 kB

metadata

base_model:
  - MTSAIR/multi_verse_model
  - BarraHome/Mistroll-7B-v2.2
  - yam-peleg/Experiment26-7B
library_name: transformers
license: apache-2.0
language:
  - en

multitroll26

This is a merge of pre-trained language models created using mergekit. Experiment of merging top 3 7B models on the OpenLLm leaderboard (as of 5/30/2024)

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using BarraHome/Mistroll-7B-v2.2 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: BarraHome/Mistroll-7B-v2.2
    # no parameters necessary for base model
  - model: yam-peleg/Experiment26-7B
    parameters:
      weight: 0.4
      density: 0.7
  - model: MTSAIR/multi_verse_model
    parameters:
      weight: 0.6
      density: 0.7
merge_method: dare_ties
base_model: BarraHome/Mistroll-7B-v2.2
parameters:
  int8_mask: true
dtype: bfloat16

eval coming soon