Instructions to use sakaltcommunity/wasser-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sakaltcommunity/wasser-4b with Transformers:

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

pipe = pipeline("text-generation", model="sakaltcommunity/wasser-4b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sakaltcommunity/wasser-4b")
model = AutoModelForCausalLM.from_pretrained("sakaltcommunity/wasser-4b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sakaltcommunity/wasser-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sakaltcommunity/wasser-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sakaltcommunity/wasser-4b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sakaltcommunity/wasser-4b

SGLang

How to use sakaltcommunity/wasser-4b 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 "sakaltcommunity/wasser-4b" \
    --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": "sakaltcommunity/wasser-4b",
		"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 "sakaltcommunity/wasser-4b" \
        --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": "sakaltcommunity/wasser-4b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sakaltcommunity/wasser-4b with Docker Model Runner:
```
docker model run hf.co/sakaltcommunity/wasser-4b
```

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using rinna/japanese-gpt-neox-3.6b as a base.

Models Merged

The following models were included in the merge:

rinna/bilingual-gpt-neox-4b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: rinna/bilingual-gpt-neox-4b
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: rinna/japanese-gpt-neox-3.6b
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: float16

Downloads last month: 2

Safetensors

Model size

4B params

Tensor type

F16

Model tree for sakaltcommunity/wasser-4b

rinna/bilingual-gpt-neox-4b

rinna/japanese-gpt-neox-3.6b

Merge model

this model

Space using sakaltcommunity/wasser-4b 1

Paper for sakaltcommunity/wasser-4b

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19