Instructions to use michaelw37/sc28 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use michaelw37/sc28 with Transformers:

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

pipe = pipeline("text-generation", model="michaelw37/sc28")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("michaelw37/sc28")
model = AutoModelForCausalLM.from_pretrained("michaelw37/sc28", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use michaelw37/sc28 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "michaelw37/sc28"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "michaelw37/sc28",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/michaelw37/sc28

SGLang

How to use michaelw37/sc28 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 "michaelw37/sc28" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "michaelw37/sc28",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "michaelw37/sc28" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "michaelw37/sc28",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use michaelw37/sc28 with Docker Model Runner:
```
docker model run hf.co/michaelw37/sc28
```

Michael commited on Apr 18, 2024

Commit

8a50a27

verified ·

1 Parent(s): 8d05c95

Upload StableLmForCausalLM

Browse files

Files changed (2) hide show

config.json +2 -2
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/hlw3/ckpt/llmhub/hf/stablelm-28/",
   "architectures": [
     "StableLmForCausalLM"
   ],
@@ -23,7 +23,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.1",
-  "use_cache": false,
   "use_qkv_bias": true,
   "vocab_size": 100352
 }

 {
+  "_name_or_path": "/home/hlw3/ckpt/llmhub/hf/sc28",
   "architectures": [
     "StableLmForCausalLM"
   ],
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.1",
+  "use_cache": true,
   "use_qkv_bias": true,
   "vocab_size": 100352
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25059f300377600f74cc35041252f1ffedb27642fa710c7b5e23aeba426aa28
 size 3289069520

 version https://git-lfs.github.com/spec/v1
+oid sha256:d1e06247869fed1807fce340635c9e3022ea71328d127ee9e804a32afcd7920b
 size 3289069520