Instructions to use readerbench/RoSummary-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use readerbench/RoSummary-medium with Transformers:

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

pipe = pipeline("text-generation", model="readerbench/RoSummary-medium")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("readerbench/RoSummary-medium")
model = AutoModelForCausalLM.from_pretrained("readerbench/RoSummary-medium")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use readerbench/RoSummary-medium with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/readerbench/RoSummary-medium

SGLang

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

Docker Model Runner
How to use readerbench/RoSummary-medium with Docker Model Runner:
```
docker model run hf.co/readerbench/RoSummary-medium
```

MihaiAlexandru1606 commited on Oct 20, 2022

Commit

9415d6f

1 Parent(s): b6750ed

Update model

Browse files

Files changed (3) hide show

config.json +5 -2
pytorch_model.bin +3 -0
tf_model.h5 +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "readerbench/RoGPT2-medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -20,7 +20,10 @@
   "n_positions": 1024,
   "n_special": 0,
   "predict_special_tokens": true,
   "resid_pdrop": 0.1,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
@@ -32,7 +35,7 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.3.3",
   "use_cache": true,
   "vocab_size": 50257
 }

 {
+  "_name_or_path": "../../models/summary/model/RoGPT2-medium-best",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   "n_positions": 1024,
   "n_special": 0,
   "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
       "max_length": 50
     }
   },
+  "transformers_version": "4.20.1",
   "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:28935de4c39ec8b657a14f2058706be7e328f26b224222533b536ca2fb28f8a6
+size 1444562137

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:393389aa2ebdf08664ed71a46ee6e55c7bddede203474cdc5c66b45eae5a3ab2
-size 1419647464

 version https://git-lfs.github.com/spec/v1
+oid sha256:0fef62f5ec43bc709996b6107d99a57a3c53a92cf92e089357ec44b1bb712ec5
+size 1419648008