Instructions to use InferenceIllusionist/TeTO-MS-8x7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InferenceIllusionist/TeTO-MS-8x7b with Transformers:

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

pipe = pipeline("text-generation", model="InferenceIllusionist/TeTO-MS-8x7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("InferenceIllusionist/TeTO-MS-8x7b")
model = AutoModelForCausalLM.from_pretrained("InferenceIllusionist/TeTO-MS-8x7b")
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

vLLM

How to use InferenceIllusionist/TeTO-MS-8x7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InferenceIllusionist/TeTO-MS-8x7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InferenceIllusionist/TeTO-MS-8x7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/InferenceIllusionist/TeTO-MS-8x7b

SGLang

How to use InferenceIllusionist/TeTO-MS-8x7b 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 "InferenceIllusionist/TeTO-MS-8x7b" \
    --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": "InferenceIllusionist/TeTO-MS-8x7b",
		"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 "InferenceIllusionist/TeTO-MS-8x7b" \
        --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": "InferenceIllusionist/TeTO-MS-8x7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use InferenceIllusionist/TeTO-MS-8x7b with Docker Model Runner:
```
docker model run hf.co/InferenceIllusionist/TeTO-MS-8x7b
```

TeTO-MS-8x7b

Tesoro + Typhon + OpenGPT

Presenting a Model Stock experiment combining the unique strengths from the following 8x7b Mixtral models:

Tess-2.0-Mixtral-8x7B-v0.2 / migtissera / General Purpose
Typhon-Mixtral-v1 / Sao10K / Creative & Story Completion
Open_Gpt4_8x7B_v0.2 / rombodawg / Conversational

Weighted (iMat) GGUFS: https://huggingface.co/Quant-Cartel/TeTO-MS-8x7b-iMat-GGUF

EXL2 rpcal courtesy of Quant Cartel: https://huggingface.co/Quant-Cartel/TeTO-MS-8x7b-exl2-rpcal

Recommended Template

Basic: Alpaca Format
Advanced: See context/instruct/sampler settings in our new Recommended Settings repo.
Huge shout out to rAIfle for his original work on the Wizard 8x22b templates which were modified for this model.

Methodology

[I]nnovative layer-wise weight averaging technique surpasses state-of-the-art model methods such as Model Soup, utilizing only two fine-tuned models. This strategy can be aptly coined Model Stock, highlighting its reliance on selecting a minimal number of models to draw a more optimized-averaged model (From arXiv:2403.19522)

Methodology and merging process was based on the following paper - Model Stock: All we need is just a few fine-tuned models
Initial model selection was based on top performing models of Mixtral architecture covering a variety of use cases and skills
Base model (Mixtral Instruct 8x7b v0.1) was chosen after outperforming two other potential base models in terms of MMLU benchmark performance.

Output

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Mixtral-8x7B-v0.1-Instruct as a base.

Models Merged

The following models were included in the merge:

migtissera_Tess-2.0-Mixtral-8x7B-v0.2
rombodawg_Open_Gpt4_8x7B_v0.2
Sao10K_Typhon-Mixtral-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: models/migtissera_Tess-2.0-Mixtral-8x7B-v0.2
  - model: models/Sao10K_Typhon-Mixtral-v1
  - model: models/rombodawg_Open_Gpt4_8x7B_v0.2 
merge_method: model_stock
base_model: models/Mixtral-8x7B-v0.1-Instruct
dtype: float16

Appendix - Llama.cpp MMLU Benchmark Results*

These results were calculated via perplexity.exe from llama.cpp using the following params:

.\perplexity -m .\models\TeTO-8x7b-MS-v0.03\TeTO-MS-8x7b-Q6_K.gguf -bf .\evaluations\mmlu-test.bin --multiple-choice -c 8192 -t 23 -ngl 200

* V0.01 (4 model / Mixtral Base):
    Final result: 43.3049 +/- 0.4196
    Random chance: 25.0000 +/- 0.3667


* V0.02 (3 model / Tess Mixtral Base):
    Final result: 43.8356 +/- 0.4202
    Random chance: 25.0000 +/- 0.3667


* V0.03 (4 model / Mixtral Instruct Base):
    Final result: 45.7004 +/- 0.4219
    Random chance: 25.0000 +/- 0.3667

*Please be advised metrics above are not representative of final HF benchmark scores for reasons given here

Downloads last month: 9

Safetensors

Model size

47B params

Tensor type

F16

Collection including InferenceIllusionist/TeTO-MS-8x7b

Merges

Collection

3 items • Updated Sep 13, 2024 • 1

Paper for InferenceIllusionist/TeTO-MS-8x7b

Model Stock: All we need is just a few fine-tuned models

Paper • 2403.19522 • Published Mar 28, 2024 • 15