Instructions to use HelpMumHQ/MamaBot-Llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HelpMumHQ/MamaBot-Llama with Transformers:

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

pipe = pipeline("text-generation", model="HelpMumHQ/MamaBot-Llama")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HelpMumHQ/MamaBot-Llama")
model = AutoModelForCausalLM.from_pretrained("HelpMumHQ/MamaBot-Llama", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HelpMumHQ/MamaBot-Llama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HelpMumHQ/MamaBot-Llama

SGLang

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

Docker Model Runner
How to use HelpMumHQ/MamaBot-Llama with Docker Model Runner:
```
docker model run hf.co/HelpMumHQ/MamaBot-Llama
```

HelpMum-Personal commited on Aug 3, 2024

Commit

36fce91

verified ·

1 Parent(s): 3c15195

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ MamaBot-Llama-1 is an opensource fine-tuned large language model developed by He
 ### Model Sources
-- **Repository:** [MamaBot-Llama-1 on Hugging Face](https://huggingface.co/HelpMumHQ/mamabot-llama-1)
 ## Uses
@@ -60,7 +60,7 @@ Use the code below to get started with the model.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model_id = "HelpMumHQ/mamabot-llama-1"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id)
@@ -150,13 +150,13 @@ The training and inference were conducted using the Hugging Face Transformers li
   author = {HelpMum},
   title = {MamaBot-Llama-1},
   year = {2024},
-  howpublished = {\url{https://huggingface.co/HelpMumHQ/mamabot-llama-1}},
 }
 ```
 **APA:**
-HelpMum. (2024). MamaBot-Llama-1. Retrieved from https://huggingface.co/HelpMumHQ/mamabot-llama-1
 ## Model Card Contact

 ### Model Sources
+- **Repository:** [MamaBot-Llama-1 on Hugging Face](https://huggingface.co/HelpMum-Personal/mamabot-llama-1)
 ## Uses
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_id = "HelpMum-Personal/mamabot-llama-1"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id)
   author = {HelpMum},
   title = {MamaBot-Llama-1},
   year = {2024},
+  howpublished = {\url{https://huggingface.co/HelpMum-Personal/mamabot-llama-1}},
 }
 ```
 **APA:**
+HelpMum. (2024). MamaBot-Llama-1. Retrieved from https://huggingface.co/HelpMum-Personal/mamabot-llama-1
 ## Model Card Contact