Instructions to use crumb/Ducky-MoMoe-prototype-e4-ul2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use crumb/Ducky-MoMoe-prototype-e4-ul2 with Transformers:

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

pipe = pipeline("text-generation", model="crumb/Ducky-MoMoe-prototype-e4-ul2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("crumb/Ducky-MoMoe-prototype-e4-ul2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use crumb/Ducky-MoMoe-prototype-e4-ul2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "crumb/Ducky-MoMoe-prototype-e4-ul2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "crumb/Ducky-MoMoe-prototype-e4-ul2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/crumb/Ducky-MoMoe-prototype-e4-ul2

SGLang

How to use crumb/Ducky-MoMoe-prototype-e4-ul2 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 "crumb/Ducky-MoMoe-prototype-e4-ul2" \
    --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": "crumb/Ducky-MoMoe-prototype-e4-ul2",
		"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 "crumb/Ducky-MoMoe-prototype-e4-ul2" \
        --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": "crumb/Ducky-MoMoe-prototype-e4-ul2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use crumb/Ducky-MoMoe-prototype-e4-ul2 with Docker Model Runner:
```
docker model run hf.co/crumb/Ducky-MoMoe-prototype-e4-ul2
```

crumb commited on Aug 12, 2023

Commit

2e1b45d

1 Parent(s): 0950265

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -15,12 +15,12 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "switchgpt2",
-  "n_ctx": 2048,
   "n_embd": 512,
   "n_head": 16,
   "n_inner": null,
   "n_layer": 8,
-  "n_positions": 2048,
   "num_experts": 4,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "switchgpt2",
+  "n_ctx": 1024,
   "n_embd": 512,
   "n_head": 16,
   "n_inner": null,
   "n_layer": 8,
+  "n_positions": 1024,
   "num_experts": 4,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,