Instructions to use intlsy/opt-175b-hyperparam with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use intlsy/opt-175b-hyperparam with Transformers:

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

pipe = pipeline("text-generation", model="intlsy/opt-175b-hyperparam")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("intlsy/opt-175b-hyperparam")
model = AutoModelForCausalLM.from_pretrained("intlsy/opt-175b-hyperparam")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use intlsy/opt-175b-hyperparam with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "intlsy/opt-175b-hyperparam"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "intlsy/opt-175b-hyperparam",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/intlsy/opt-175b-hyperparam

SGLang

How to use intlsy/opt-175b-hyperparam 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 "intlsy/opt-175b-hyperparam" \
    --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": "intlsy/opt-175b-hyperparam",
		"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 "intlsy/opt-175b-hyperparam" \
        --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": "intlsy/opt-175b-hyperparam",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use intlsy/opt-175b-hyperparam with Docker Model Runner:
```
docker model run hf.co/intlsy/opt-175b-hyperparam
```

intlsy commited on Apr 29, 2024

Commit

ffebc72

verified ·

1 Parent(s): b2e147e

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -0

config.json CHANGED Viewed

@@ -1,5 +1,6 @@
 {
   "_name_or_path": "intlsy/opt-175b-hyperparam",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
@@ -18,6 +19,7 @@
   "model_type": "opt",
   "num_attention_heads": 96,
   "num_hidden_layers": 96,
   "pad_token_id": 1,
   "prefix": "</s>",
   "torch_dtype": "float16",

 {
   "_name_or_path": "intlsy/opt-175b-hyperparam",
+  "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
   "model_type": "opt",
   "num_attention_heads": 96,
   "num_hidden_layers": 96,
+  "output_projection": true,
   "pad_token_id": 1,
   "prefix": "</s>",
   "torch_dtype": "float16",