Instructions to use FWKV/Myosotis-1.1-base-step_4k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FWKV/Myosotis-1.1-base-step_4k with Transformers:

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

pipe = pipeline("text-generation", model="FWKV/Myosotis-1.1-base-step_4k", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("FWKV/Myosotis-1.1-base-step_4k", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FWKV/Myosotis-1.1-base-step_4k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FWKV/Myosotis-1.1-base-step_4k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FWKV/Myosotis-1.1-base-step_4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FWKV/Myosotis-1.1-base-step_4k

SGLang

How to use FWKV/Myosotis-1.1-base-step_4k 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 "FWKV/Myosotis-1.1-base-step_4k" \
    --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": "FWKV/Myosotis-1.1-base-step_4k",
		"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 "FWKV/Myosotis-1.1-base-step_4k" \
        --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": "FWKV/Myosotis-1.1-base-step_4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FWKV/Myosotis-1.1-base-step_4k with Docker Model Runner:
```
docker model run hf.co/FWKV/Myosotis-1.1-base-step_4k
```

Myosotis-1.1 (pretrain step 4000)

The model is heavily undertrained, but for who cares theres the eval

Tasks	Version	Filter	Metric		Value		Stderr
arc_challenge	1	none	acc	↑	0.1630	±	0.0108
		none	acc_norm	↑	0.2125	±	0.0120
arc_easy	1	none	acc	↑	0.3030	±	0.0094
		none	acc_norm	↑	0.2879	±	0.0093
hellaswag	1	none	acc	↑	0.2562	±	0.0044
		none	acc_norm	↑	0.2472	±	0.0043
piqa	1	none	acc	↑	0.5435	±	0.0116
		none	acc_norm	↑	0.5277	±	0.0116

Downloads last month: 414

Safetensors

Model size

0.1B params

Tensor type

F32