Instructions to use IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit with Transformers:

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

pipe = pipeline("text-generation", model="IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit")
model = AutoModelForCausalLM.from_pretrained("IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit")
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 IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit

SGLang

How to use IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit 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 "IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit" \
    --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": "IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit",
		"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 "IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit" \
        --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": "IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit with Docker Model Runner:
```
docker model run hf.co/IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit
```

pr1

by radm - opened Jun 17, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-8

radm

Jun 17, 2024

No description provided.

IlyaGusev

Owner Jun 17, 2024

Что-то PR пустой

update awq80afc25f

radm changed pull request status to open Jun 17, 2024

radm

Jun 17, 2024

заливалось долго

IlyaGusev

Owner Jun 17, 2024

•

edited Jun 17, 2024

И не дозалилось? Мне кажется одного файлика не хватает (00009)

IlyaGusev

Owner Jun 17, 2024

Или он не поменялся?

radm

Jun 18, 2024

да похоже не поменялся, прикольно

sha256sum model-00009-of-00009.safetensors
af260a67106015689c0a7430020581b44cea2de525ea8022a6c223dacb6a55d2  model-00009-of-00009.safetensors

IlyaGusev

Owner Jun 19, 2024

Спасибо, сливаю, посчитаю метрики.

IlyaGusev changed pull request status to merged Jun 19, 2024

radm

Jun 19, 2024

Возможно у тебя будет не такая разница как у меня, потому что я прогоняю по вопросам арена-хард. В любом случае напиши результат

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