Instructions to use Jo1uck/mamba-11b-back with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jo1uck/mamba-11b-back with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jo1uck/mamba-11b-back")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jo1uck/mamba-11b-back") model = AutoModelForCausalLM.from_pretrained("Jo1uck/mamba-11b-back", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Jo1uck/mamba-11b-back with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jo1uck/mamba-11b-back" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jo1uck/mamba-11b-back", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jo1uck/mamba-11b-back
- SGLang
How to use Jo1uck/mamba-11b-back 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 "Jo1uck/mamba-11b-back" \ --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": "Jo1uck/mamba-11b-back", "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 "Jo1uck/mamba-11b-back" \ --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": "Jo1uck/mamba-11b-back", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jo1uck/mamba-11b-back with Docker Model Runner:
docker model run hf.co/Jo1uck/mamba-11b-back
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ library_name: transformers
|
|
| 6 |
# Mamba
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
-
This repository contains the `transfromers` compatible `mamba
|
| 10 |
|
| 11 |
# Usage
|
| 12 |
|
|
@@ -30,8 +30,8 @@ You can use the classic `generate` API:
|
|
| 30 |
>>> from transformers import MambaConfig, MambaForCausalLM, AutoTokenizer
|
| 31 |
>>> import torch
|
| 32 |
|
| 33 |
-
>>> tokenizer = AutoTokenizer.from_pretrained("
|
| 34 |
-
>>> model = MambaForCausalLM.from_pretrained("
|
| 35 |
>>> input_ids = tokenizer("Hey how are you doing?", return_tensors="pt")["input_ids"]
|
| 36 |
|
| 37 |
>>> out = model.generate(input_ids, max_new_tokens=10)
|
|
|
|
| 6 |
# Mamba
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
This repository contains the `transfromers` compatible `mamba`. The checkpoints are untouched, but the full `config.json` and tokenizer are pushed to this repo.
|
| 10 |
|
| 11 |
# Usage
|
| 12 |
|
|
|
|
| 30 |
>>> from transformers import MambaConfig, MambaForCausalLM, AutoTokenizer
|
| 31 |
>>> import torch
|
| 32 |
|
| 33 |
+
>>> tokenizer = AutoTokenizer.from_pretrained("Jo1uck/mamba-11b-back")
|
| 34 |
+
>>> model = MambaForCausalLM.from_pretrained("Jo1uck/mamba-11b-back")
|
| 35 |
>>> input_ids = tokenizer("Hey how are you doing?", return_tensors="pt")["input_ids"]
|
| 36 |
|
| 37 |
>>> out = model.generate(input_ids, max_new_tokens=10)
|