Instructions to use state-spaces/mamba-130m-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use state-spaces/mamba-130m-hf with Transformers:

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

pipe = pipeline("text-generation", model="state-spaces/mamba-130m-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("state-spaces/mamba-130m-hf")
model = AutoModelForCausalLM.from_pretrained("state-spaces/mamba-130m-hf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use state-spaces/mamba-130m-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "state-spaces/mamba-130m-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "state-spaces/mamba-130m-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/state-spaces/mamba-130m-hf

SGLang

How to use state-spaces/mamba-130m-hf 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 "state-spaces/mamba-130m-hf" \
    --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": "state-spaces/mamba-130m-hf",
		"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 "state-spaces/mamba-130m-hf" \
        --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": "state-spaces/mamba-130m-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use state-spaces/mamba-130m-hf with Docker Model Runner:
```
docker model run hf.co/state-spaces/mamba-130m-hf
```

ArthurZ HF Staff commited on Mar 6, 2024

Commit

40e5d2b

verified ·

1 Parent(s): b4f5851

Upload tokenizer

Browse files

Files changed (3) hide show

special_tokens_map.json +1 -0
tokenizer.json +6 -1
tokenizer_config.json +1 -0

special_tokens_map.json CHANGED Viewed

@@ -13,6 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json CHANGED Viewed

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

 {
   "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json CHANGED Viewed

@@ -206,6 +206,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }