Instructions to use athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE with Transformers:

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

pipe = pipeline("text-generation", model="athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE")

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

tokenizer = AutoTokenizer.from_pretrained("athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE")
model = AutoModelForCausalLM.from_pretrained("athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE

SGLang

How to use athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE 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 "athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE" \
    --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": "athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE",
		"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 "athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE" \
        --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": "athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE with Docker Model Runner:
```
docker model run hf.co/athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Ooof, my man ain't feeling so hot, I'd pass on this one for now. Inverting and merging 20b Llama 2 models works quite well, evening out the gradients between slices. However, these 13b Mistrals seem to HATE it, I assume due to the unbalanced nature of my recipe. More study is required.

Recipe

merge_method: dare_ties

base_model: athirdpath/BigMistral-13b
model: athirdpath/NeuralHermes-Mistral-13b

weight: 0.60 / density: 0.35
model: athirdpath/NeuralHermes-Mistral-13b-INV

weight: 0.40 / density: 0.30

int8_mask: true

dtype: bfloat16

Downloads last month: 17

Safetensors

Model size

13B params

Tensor type

BF16

Collection including athirdpath/NeuralHermes-Mistral-13b-DARE_blended-FAILURE

FailLabs

Collection

WITH EXPLANATIONS - Total failures and dead-ends. Learn from my mistakes. • 5 items • Updated Dec 2, 2023