Instructions to use stabilityai/stablelm-base-alpha-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stabilityai/stablelm-base-alpha-7b with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/stablelm-base-alpha-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-base-alpha-7b")
model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-base-alpha-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stabilityai/stablelm-base-alpha-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stabilityai/stablelm-base-alpha-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/stablelm-base-alpha-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stabilityai/stablelm-base-alpha-7b

SGLang

How to use stabilityai/stablelm-base-alpha-7b 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 "stabilityai/stablelm-base-alpha-7b" \
    --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": "stabilityai/stablelm-base-alpha-7b",
		"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 "stabilityai/stablelm-base-alpha-7b" \
        --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": "stabilityai/stablelm-base-alpha-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stabilityai/stablelm-base-alpha-7b with Docker Model Runner:
```
docker model run hf.co/stabilityai/stablelm-base-alpha-7b
```

jon-tow commited on Apr 11, 2023

Commit

aa47087

1 Parent(s): 7c2ad08

Create README.md

Browse files

Files changed (1) hide show

README.md +40 -0

README.md ADDED Viewed

	@@ -0,0 +1,40 @@

+Model Info:
+- Size: 7B
+- Dataset: The Pile v2
+  - `contaminated(P3) + lower_code(5%) + wiki(fixed) + books3(fixed & broken)`
+- Batch size (in tokens): 8M
+- Checkpoint path (AWS East): `/fsx/ckpts/7b_tok=neox_data=pilev2-recontam_lower-code_bs=8m_tp=4_pp=1_init=wang-small-init/global_step69000_hf`
+Notes:
+- Trained for 36k steps with incorrectly tokenized Books3 dataset (GPT-2 tokenizer instead of NeoX tokenizer)
+- tp=2 (not 4)
+W&B Report: https://stability.wandb.io/stability-llm/stable-lm/reports/StableLM-7B-alpha---Vmlldzo2MjA
+Usage:
+```python
+import transformers
+model = transformers.AutoModelForCausalLM.from_pretrained("CarperAI/7b-alpha")
+tokenizer = transformers.AutoTokenizer.from_pretrained("CarperAI/7b-alpha")
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.paddding_side = "left"
+prompts = [
+    "User1: The dog sat on a man's lap and barked 3 times.\nUser2: How many times did the dog bark?"
+    "Curious Person Question: A group of genetically identical individuals is called what?\nSmart Person Answer: a clone\n\nCurious Person Question: Who proposed the theory of evolution by natural selection?\nSmart Person Answer:"
+]
+batch_encoding = tokenizer(prompts, return_tensors="pt", padding=True)
+print(f"Generating {len(prompts)} prompts...")
+samples = model.generate(
+    **batch_encoding,
+    max_new_tokens=64,
+    temperature=0.0,
+    do_sample=False,
+)
+samples = tokenizer.batch_decode(samples, skip_special_tokens=True)
+for i, sample in enumerate(samples):
+    print(f"Prompt: {prompts[i]}\nSample: {sample}\n")
+```