Instructions to use localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ")
model = AutoModelForCausalLM.from_pretrained("localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ

SGLang

How to use localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ 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 "localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ" \
    --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": "localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ",
		"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 "localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ" \
        --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": "localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ with Docker Model Runner:
```
docker model run hf.co/localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ
```

OpenAssistant LLaMA 30B SFT 7 GPTQ

From: https://huggingface.co/OpenAssistant/oasst-sft-7-llama-30b-xor

Model	Bits	Group Size	Act Order (desc_act)	File Size	ExLlama Compatible?	Made With	Description
OpenAssistant-SFT-7-LLaMA-30B-GPTQ-4bit--1g.act.order	4	None	True	16.94 GB	True	GPTQ-for-LLaMa	Most compatible. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa.

OpenAssistant LLaMA 30B SFT 7

Configuration

llama-30b-sft-7:
  dtype: fp16
  log_dir: "llama_log_30b"
  learning_rate: 1e-5
  model_name: /home/ubuntu/Open-Assistant/model/model_training/.saved/llama-30b-super-pretrain/checkpoint-3500
  #model_name: OpenAssistant/llama-30b-super-pretrain
  output_dir: llama_model_30b
  deepspeed_config: configs/zero3_config_sft.json
  weight_decay: 0.0
  residual_dropout: 0.0
  max_length: 2048
  use_flash_attention: true
  warmup_steps: 20
  gradient_checkpointing: true
  gradient_accumulation_steps: 12
  per_device_train_batch_size: 2
  per_device_eval_batch_size: 3
  eval_steps: 101
  save_steps: 485
  num_train_epochs: 4
  save_total_limit: 3
  use_custom_sampler: true
  sort_by_length: false
  #save_strategy: steps
  save_strategy: epoch
  datasets:
    - oasst_export:
        lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk"
        input_file_path: 2023-04-12_oasst_release_ready_synth.jsonl.gz
        val_split: 0.05
    - vicuna:
        val_split: 0.05
        max_val_set: 800
        fraction: 1.0
    - dolly15k:
        val_split: 0.05
        max_val_set: 300
    - grade_school_math_instructions:
        val_split: 0.05
    - code_alpaca:
        val_split: 0.05
        max_val_set: 250

OASST dataset paper: https://arxiv.org/abs/2304.07327

Downloads last month: 4

Paper for localmodels/OpenAssistant-LLaMA-30B-SFT-7-GPTQ

OpenAssistant Conversations -- Democratizing Large Language Model Alignment

Paper • 2304.07327 • Published Apr 14, 2023 • 10