Instructions to use chargoddard/mixtralmerge-8x7B-rebalanced-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chargoddard/mixtralmerge-8x7B-rebalanced-test with Transformers:

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

pipe = pipeline("text-generation", model="chargoddard/mixtralmerge-8x7B-rebalanced-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("chargoddard/mixtralmerge-8x7B-rebalanced-test")
model = AutoModelForMultimodalLM.from_pretrained("chargoddard/mixtralmerge-8x7B-rebalanced-test")
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 chargoddard/mixtralmerge-8x7B-rebalanced-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chargoddard/mixtralmerge-8x7B-rebalanced-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chargoddard/mixtralmerge-8x7B-rebalanced-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chargoddard/mixtralmerge-8x7B-rebalanced-test

SGLang

How to use chargoddard/mixtralmerge-8x7B-rebalanced-test 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 "chargoddard/mixtralmerge-8x7B-rebalanced-test" \
    --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": "chargoddard/mixtralmerge-8x7B-rebalanced-test",
		"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 "chargoddard/mixtralmerge-8x7B-rebalanced-test" \
        --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": "chargoddard/mixtralmerge-8x7B-rebalanced-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chargoddard/mixtralmerge-8x7B-rebalanced-test with Docker Model Runner:
```
docker model run hf.co/chargoddard/mixtralmerge-8x7B-rebalanced-test
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a dumb experiment - don't expect it to be good!

I merged a few Mixtral models together then tuned only the routing parameters. There was a pretty steep drop in loss with only a bit of training - went from ~0.99 to ~.7 over about ten million tokens.

I'm hoping this after-the-fact balancing will have reduced some of the nasty behavior typical of current tunes. But maybe it just made it even dumber! We'll see.

Uses ChatML format.

Will update with more details if it turns out promising.

Downloads last month: 775

Safetensors

Model size

47B params

Tensor type

BF16

Model tree for chargoddard/mixtralmerge-8x7B-rebalanced-test

Quantizations

2 models

chargoddard
/

mixtralmerge-8x7B-rebalanced-test

Model tree for chargoddard/mixtralmerge-8x7B-rebalanced-test

Dataset used to train chargoddard/mixtralmerge-8x7B-rebalanced-test