Instructions to use NousResearch/Redmond-Puffin-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Redmond-Puffin-13B with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Redmond-Puffin-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Redmond-Puffin-13B")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Redmond-Puffin-13B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/Redmond-Puffin-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Redmond-Puffin-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Redmond-Puffin-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NousResearch/Redmond-Puffin-13B

SGLang

How to use NousResearch/Redmond-Puffin-13B 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 "NousResearch/Redmond-Puffin-13B" \
    --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": "NousResearch/Redmond-Puffin-13B",
		"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 "NousResearch/Redmond-Puffin-13B" \
        --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": "NousResearch/Redmond-Puffin-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NousResearch/Redmond-Puffin-13B with Docker Model Runner:
```
docker model run hf.co/NousResearch/Redmond-Puffin-13B
```

karan4d commited on Jul 22, 2023

Commit

92ef4bc

1 Parent(s): 4d07599

Update config.json

Browse files

"pretraining_tp": 2 should be 1 otherwise on 4.31 transformers you cant load it in BnB 4-bit anymore
Details here : https://github.com/huggingface/transformers/issues/24961"
~henk717

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -15,7 +15,7 @@
   "num_hidden_layers": 40,
   "num_key_value_heads": 40,
   "pad_token_id": 0,
-  "pretraining_tp": 2,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,

   "num_hidden_layers": 40,
   "num_key_value_heads": 40,
   "pad_token_id": 0,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,