Instructions to use ArthurZ/mamba-790m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArthurZ/mamba-790m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ArthurZ/mamba-790m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ArthurZ/mamba-790m") model = AutoModelForCausalLM.from_pretrained("ArthurZ/mamba-790m") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ArthurZ/mamba-790m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ArthurZ/mamba-790m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ArthurZ/mamba-790m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ArthurZ/mamba-790m
- SGLang
How to use ArthurZ/mamba-790m 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 "ArthurZ/mamba-790m" \ --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": "ArthurZ/mamba-790m", "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 "ArthurZ/mamba-790m" \ --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": "ArthurZ/mamba-790m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ArthurZ/mamba-790m with Docker Model Runner:
docker model run hf.co/ArthurZ/mamba-790m
Upload MambaForCausalLM
Browse files- config.json +2 -2
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
],
|
| 6 |
"bos_token_id": 1,
|
| 7 |
"conv_kernel": 4,
|
| 8 |
-
"d_model":
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"expand": 2,
|
| 11 |
"fused_add_norm": true,
|
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"layer_norm_epsilon": 1e-05,
|
| 17 |
"model_type": "mamba",
|
| 18 |
"n_layer": 48,
|
| 19 |
-
"num_hidden_layers":
|
| 20 |
"pad_vocab_size_multiple": 8,
|
| 21 |
"residual_in_fp32": true,
|
| 22 |
"rms_norm": true,
|
|
|
|
| 5 |
],
|
| 6 |
"bos_token_id": 1,
|
| 7 |
"conv_kernel": 4,
|
| 8 |
+
"d_model": 2048,
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"expand": 2,
|
| 11 |
"fused_add_norm": true,
|
|
|
|
| 16 |
"layer_norm_epsilon": 1e-05,
|
| 17 |
"model_type": "mamba",
|
| 18 |
"n_layer": 48,
|
| 19 |
+
"num_hidden_layers": 48,
|
| 20 |
"pad_vocab_size_multiple": 8,
|
| 21 |
"residual_in_fp32": true,
|
| 22 |
"rms_norm": true,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebcfe054512122da4d54f83c3422a1c82cdd7788398ca0ddac6963c1aaa3071f
|
| 3 |
+
size 1591179496
|