Instructions to use michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps with Transformers:

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

pipe = pipeline("text-generation", model="michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps

SGLang

How to use michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps 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 "michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps" \
    --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": "michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps",
		"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 "michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps" \
        --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": "michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps with Docker Model Runner:
```
docker model run hf.co/michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps
```

# Fast-Inference with Ctranslate2

Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.

quantized version of OpenAssistant/pythia-12b-sft-v8-7k-steps

pip install hf-hub-ctranslate2>=2.0.6

Converted on 2023-05-19 using

ct2-transformers-converter --model OpenAssistant/pythia-12b-sft-v8-7k-steps --output_dir /home/feil_m/tmp-ct2fast-pythia-12b-sft-v8-7k-steps --force --copy_files tokenizer.json README.md tokenizer_config.json generation_config.json special_tokens_map.json .gitattributes --quantization float16

Checkpoint compatible to ctranslate2>=3.13.0 and hf-hub-ctranslate2>=2.0.6

compute_type=int8_float16 for device="cuda"
compute_type=int8 for device="cpu"

from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer

model_name = "michaelfeil/ct2fast-pythia-12b-sft-v8-7k-steps"
# use either TranslatorCT2fromHfHub or GeneratorCT2fromHfHub here, depending on model.
model = GeneratorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name, 
        device="cuda",
        compute_type="int8_float16",
        tokenizer=AutoTokenizer.from_pretrained("OpenAssistant/pythia-12b-sft-v8-7k-steps")
)
outputs = model.generate(
    text=["How do you call a fast Flan-ingo?", "User: How are you doing? Bot:"],
)
print(outputs)

Licence and other remarks:

This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

Original description

base model: OpenAssistant/pythia-12b-pre-v8-12.5k-steps
wandb: https://wandb.ai/open-assistant/supervised-finetuning/runs/pcw1ejda
sampling report

pythia-12b-sft-8:
  dtype: fp16
  log_dir: "pythia_log_12b"
  learning_rate: 6e-6
  model_name: OpenAssistant/pythia-12b-pre-v8-12.5k-steps
  output_dir: pythia_model_12b
  weight_decay: 0.0
  residual_dropout: 0.0
  max_length: 2048
  use_flash_attention: true
  warmup_steps: 100
  gradient_checkpointing: true
  gradient_accumulation_steps: 2
  per_device_train_batch_size: 4
  per_device_eval_batch_size: 4
  eval_steps: 251
  save_steps: 500
  num_train_epochs: 8
  save_total_limit: 4
  num_train_epochs: 8
  save_total_limit: 3
  use_custom_sampler: true
  sort_by_length: false
  save_strategy: steps
  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: 2023-05-06_OASST_labels.jsonl.gz
        val_split: 0.05
    - vicuna:
        val_split: 0.05
        max_val_set: 800
        fraction: 0.4
    - 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
    - red_pajama:
        fraction: 0.05
        max_val_set: 1000
    - wizardlm_70k:
        val_split: 0.05
        max_val_set: 500
        fraction: 0.4
    - poem_instructions:
        fraction: 0.5
        val_split: 0.025

Downloads last month: 11