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

Libraries

How to use AlexWortega/instruct_rugptMedium with Transformers:

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

pipe = pipeline("text-generation", model="AlexWortega/instruct_rugptMedium")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlexWortega/instruct_rugptMedium")
model = AutoModelForCausalLM.from_pretrained("AlexWortega/instruct_rugptMedium")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AlexWortega/instruct_rugptMedium with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AlexWortega/instruct_rugptMedium

SGLang

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

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

AlexWortega commited on Mar 20, 2023

Commit

a7d5287

1 Parent(s): 90d89a1

Upload model

Browse files

Files changed (2) hide show

config.json +1 -1
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ckpts11/sft_0_70000/",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

 {
+  "_name_or_path": "ckpts11/sft_0_65000/",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b837ae1527bcc55004db32326152cff1b8b360cfda5827d516b71ee8dbcda8ee
-size 1524285725

 version https://git-lfs.github.com/spec/v1
+oid sha256:9e11331edf881259e1ae8bdedb8ba4a5b6cf33f9b7d03813e82cb48a411df961
+size 1524280989