Instructions to use pankajmathur/model_101 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/model_101 with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/model_101")

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

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/model_101")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/model_101", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pankajmathur/model_101 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajmathur/model_101"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajmathur/model_101",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pankajmathur/model_101

SGLang

How to use pankajmathur/model_101 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 "pankajmathur/model_101" \
    --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": "pankajmathur/model_101",
		"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 "pankajmathur/model_101" \
        --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": "pankajmathur/model_101",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pankajmathur/model_101 with Docker Model Runner:
```
docker model run hf.co/pankajmathur/model_101
```

pankajmathur commited on Nov 9, 2023

Commit

7fde4e7

1 Parent(s): 6ec0b1d

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -86,9 +86,9 @@ Below shows a code example on how to use this model
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-tokenizer = AutoTokenizer.from_pretrained("psmathur/model_007")
 model = AutoModelForCausalLM.from_pretrained(
-  "psmathur/model_007",
   torch_dtype=torch.float16,
   load_in_8bit=True,
   low_cpu_mem_usage=True,

 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+tokenizer = AutoTokenizer.from_pretrained("pankajmathur/model_007")
 model = AutoModelForCausalLM.from_pretrained(
+  "pankajmathur/model_007",
   torch_dtype=torch.float16,
   load_in_8bit=True,
   low_cpu_mem_usage=True,