Instructions to use VishnuPJ/MalayaLLM_7B_Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VishnuPJ/MalayaLLM_7B_Base with Transformers:

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

pipe = pipeline("text-generation", model="VishnuPJ/MalayaLLM_7B_Base")

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

tokenizer = AutoTokenizer.from_pretrained("VishnuPJ/MalayaLLM_7B_Base")
model = AutoModelForCausalLM.from_pretrained("VishnuPJ/MalayaLLM_7B_Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VishnuPJ/MalayaLLM_7B_Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VishnuPJ/MalayaLLM_7B_Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VishnuPJ/MalayaLLM_7B_Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/VishnuPJ/MalayaLLM_7B_Base

SGLang

How to use VishnuPJ/MalayaLLM_7B_Base 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 "VishnuPJ/MalayaLLM_7B_Base" \
    --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": "VishnuPJ/MalayaLLM_7B_Base",
		"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 "VishnuPJ/MalayaLLM_7B_Base" \
        --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": "VishnuPJ/MalayaLLM_7B_Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use VishnuPJ/MalayaLLM_7B_Base with Docker Model Runner:
```
docker model run hf.co/VishnuPJ/MalayaLLM_7B_Base
```

MalayaLLM_7B_Base

Commit History

Jan 31, 2024

14:16
Update README.md

VishnuPJ

Verified signature
3de582c
13:52
Update README.md

VishnuPJ

Verified signature
df13eb5
13:42
Update README.md

VishnuPJ

Verified signature
f332658
13:40
Update README.md

VishnuPJ

Verified signature
8b52af7
13:36
Update README.md

VishnuPJ

Verified signature
241c33f
13:36
Update README.md

VishnuPJ

Verified signature
b570717
13:32
Update README.md

VishnuPJ

Verified signature
715074a
13:27
Update README.md⁠

VishnuPJ

Verified signature
dfcbe17
13:06
Create README.md⁠

VishnuPJ

Verified signature
6e42ee2

Jan 24, 2024

10:21
Upload tokenizer

VishnuPJ

Verified signature
5a12e8d
10:17
Upload LlamaForCausalLM

VishnuPJ

Verified signature
4076444
10:07
initial commit

VishnuPJ

Verified signature
94e24d0

Commit History

Jan 31, 2024

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md⁠

Create README.md⁠

Jan 24, 2024

Upload tokenizer

Upload LlamaForCausalLM

initial commit