Instructions to use pszemraj/opt-350m-multiprompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/opt-350m-multiprompt with Transformers:

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

pipe = pipeline("text-generation", model="pszemraj/opt-350m-multiprompt")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pszemraj/opt-350m-multiprompt")
model = AutoModelForCausalLM.from_pretrained("pszemraj/opt-350m-multiprompt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pszemraj/opt-350m-multiprompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pszemraj/opt-350m-multiprompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/opt-350m-multiprompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pszemraj/opt-350m-multiprompt

SGLang

How to use pszemraj/opt-350m-multiprompt 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 "pszemraj/opt-350m-multiprompt" \
    --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": "pszemraj/opt-350m-multiprompt",
		"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 "pszemraj/opt-350m-multiprompt" \
        --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": "pszemraj/opt-350m-multiprompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pszemraj/opt-350m-multiprompt with Docker Model Runner:
```
docker model run hf.co/pszemraj/opt-350m-multiprompt
```

pszemraj commited on Nov 13, 2022

Commit

fb7d1f7

1 Parent(s): 0c788ea

End of training

Browse files

Files changed (6) hide show

all_results.json +14 -0
config.json +1 -1
eval_results.json +9 -0
pytorch_model.bin +2 -2
train_results.json +8 -0
trainer_state.json +0 -0

all_results.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+    "epoch": 4.0,
+    "eval_loss": 1.6668897867202759,
+    "eval_runtime": 102.7014,
+    "eval_samples": 13319,
+    "eval_samples_per_second": 129.687,
+    "eval_steps_per_second": 16.212,
+    "perplexity": 5.295671489170355,
+    "train_loss": 1.9931427570304485,
+    "train_runtime": 30194.781,
+    "train_samples": 253694,
+    "train_samples_per_second": 33.608,
+    "train_steps_per_second": 0.131
+}

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "prefix": "</s>",
-  "torch_dtype": "float32",
   "transformers_version": "4.25.0.dev0",
   "use_cache": true,
   "vocab_size": 50272,

   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "prefix": "</s>",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.25.0.dev0",
   "use_cache": true,
   "vocab_size": 50272,

eval_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 4.0,
+    "eval_loss": 1.6668897867202759,
+    "eval_runtime": 102.7014,
+    "eval_samples": 13319,
+    "eval_samples_per_second": 129.687,
+    "eval_steps_per_second": 16.212,
+    "perplexity": 5.295671489170355
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2648d976595b9b0cfbad08b91da10fda8b0c838456789fe0b413346c60ba274b
-size 1324917277

 version https://git-lfs.github.com/spec/v1
+oid sha256:743eb512852251be08a75f53fcbdc54da6810c302f91b9f948513d6064ebc538
+size 662524445

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 4.0,
+    "train_loss": 1.9931427570304485,
+    "train_runtime": 30194.781,
+    "train_samples": 253694,
+    "train_samples_per_second": 33.608,
+    "train_steps_per_second": 0.131
+}

trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff