Instructions to use simonko912/oasst-max-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use simonko912/oasst-max-v1 with Transformers:

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

pipe = pipeline("text-generation", model="simonko912/oasst-max-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("simonko912/oasst-max-v1")
model = AutoModelForCausalLM.from_pretrained("simonko912/oasst-max-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use simonko912/oasst-max-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "simonko912/oasst-max-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "simonko912/oasst-max-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/simonko912/oasst-max-v1

SGLang

How to use simonko912/oasst-max-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 "simonko912/oasst-max-v1" \
    --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": "simonko912/oasst-max-v1",
		"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 "simonko912/oasst-max-v1" \
        --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": "simonko912/oasst-max-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use simonko912/oasst-max-v1 with Docker Model Runner:
```
docker model run hf.co/simonko912/oasst-max-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Simple merges of my diffrent models, then finetuned for 500 steps using lora and oasst1.

Merge kit info below:

stacked_model

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  # oasst2-llama repeated 3×
  - sources:
      - model: simonko912/oasst2-llama
        layer_range: [0, 12]
  - sources:
      - model: simonko912/oasst2-llama
        layer_range: [0, 12]
  - sources:
      - model: simonko912/oasst2-llama
        layer_range: [0, 12]

  # oasst-big-llama
  - sources:
      - model: simonko912/oasst-big-llama
        layer_range: [0, 12]

  # oasst1-llama
  - sources:
      - model: simonko912/oasst1-llama
        layer_range: [0, 12]

merge_method: passthrough
dtype: bfloat16