Instructions to use augmxnt/shisa-7b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use augmxnt/shisa-7b-v1 with Transformers:

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

pipe = pipeline("text-generation", model="augmxnt/shisa-7b-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("augmxnt/shisa-7b-v1")
model = AutoModelForCausalLM.from_pretrained("augmxnt/shisa-7b-v1")
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 augmxnt/shisa-7b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "augmxnt/shisa-7b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "augmxnt/shisa-7b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/augmxnt/shisa-7b-v1

SGLang

How to use augmxnt/shisa-7b-v1 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 "augmxnt/shisa-7b-v1" \
    --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": "augmxnt/shisa-7b-v1",
		"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 "augmxnt/shisa-7b-v1" \
        --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": "augmxnt/shisa-7b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use augmxnt/shisa-7b-v1 with Docker Model Runner:
```
docker model run hf.co/augmxnt/shisa-7b-v1
```

llama.cpp doesn't work w/ Shisa, has a bug that affects certain BPE tokenizers like ours

by leonardlin - opened Dec 7, 2023

Discussion

leonardlin

AUGMXNT org Dec 7, 2023

•

edited Dec 8, 2023

GGUFs can be created, but currently llama.cpp has a known bug that causes it to crash with certain tokenizers:

GGML_ASSERT: llama.cpp:2683: codepoints_from_utf8(word).size() > 0
Aborted (core dumped)

This bug was reported in September and October 2023 and seems to also affect at least ELYZA-japanese-Llama-2-7b-fast-instruct and InternLM

I did some poking and submitted a new issue, and those looking to see the status (or wanting to have a poke) can look here: https://github.com/ggerganov/llama.cpp/issues/4360

leonardlin

AUGMXNT org Dec 8, 2023

Looks like there is a (rather involved) workaround for this llama.cpp's handling of extended unicode here: https://github.com/ggerganov/llama.cpp/issues/4360#issuecomment-1846617653

Just leaving it for those who really need to use llama.cpp for some reason (GPTQ and AWQ quants both tested to work fine).

alexkoo300

Dec 9, 2023

•

edited Dec 9, 2023

Thanks Leonard. I was just in the middle of trying to convert shisa to gguf. Good to hear the other quant methods were ok.

leonardlin

AUGMXNT org Dec 10, 2023

@alexkoo300 Take a look at https://huggingface.co/mmnga/shisa-7b-v1-gguf - mmnga managed to use a modify conversion to merge/use spm instead of bpe. Seems to work!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment