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

Libraries

How to use mlsquare/mamba_pico_small_dt_proj with Transformers:

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

pipe = pipeline("text-generation", model="mlsquare/mamba_pico_small_dt_proj")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mlsquare/mamba_pico_small_dt_proj", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mlsquare/mamba_pico_small_dt_proj with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mlsquare/mamba_pico_small_dt_proj

SGLang

How to use mlsquare/mamba_pico_small_dt_proj 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 "mlsquare/mamba_pico_small_dt_proj" \
    --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": "mlsquare/mamba_pico_small_dt_proj",
		"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 "mlsquare/mamba_pico_small_dt_proj" \
        --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": "mlsquare/mamba_pico_small_dt_proj",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

SaiNikhileshReddy commited on Apr 12, 2024

Commit

93bfa19

verified ·

1 Parent(s): c62cedf

Update adapter from client

Browse files

Files changed (2) hide show

adapter_config.json +1 -0
config.json +1 -1

adapter_config.json CHANGED Viewed

@@ -9,6 +9,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},

   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},

config.json CHANGED Viewed

@@ -2,7 +2,7 @@
     "username": "convolutionboi",
     "fullname": "chaudhuri",
     "org_id": "mlsquare",
-    "time": "2024-03-17 14:57:34",
     "hf_model_path": "mlsquare/pico_seshu_test",
     "hf_tokenizer_path": "google/byt5-large",
     "target_modules": [

     "username": "convolutionboi",
     "fullname": "chaudhuri",
     "org_id": "mlsquare",
+    "time": "2024-04-12 09:05:47",
     "hf_model_path": "mlsquare/pico_seshu_test",
     "hf_tokenizer_path": "google/byt5-large",
     "target_modules": [