Instructions to use hrezaei/T5Lae-Large-WeightedLoss-InstructMixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hrezaei/T5Lae-Large-WeightedLoss-InstructMixed with Transformers:

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

pipe = pipeline("text-generation", model="hrezaei/T5Lae-Large-WeightedLoss-InstructMixed")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("hrezaei/T5Lae-Large-WeightedLoss-InstructMixed", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hrezaei/T5Lae-Large-WeightedLoss-InstructMixed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hrezaei/T5Lae-Large-WeightedLoss-InstructMixed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hrezaei/T5Lae-Large-WeightedLoss-InstructMixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hrezaei/T5Lae-Large-WeightedLoss-InstructMixed

SGLang

How to use hrezaei/T5Lae-Large-WeightedLoss-InstructMixed 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 "hrezaei/T5Lae-Large-WeightedLoss-InstructMixed" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hrezaei/T5Lae-Large-WeightedLoss-InstructMixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "hrezaei/T5Lae-Large-WeightedLoss-InstructMixed" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hrezaei/T5Lae-Large-WeightedLoss-InstructMixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hrezaei/T5Lae-Large-WeightedLoss-InstructMixed with Docker Model Runner:
```
docker model run hf.co/hrezaei/T5Lae-Large-WeightedLoss-InstructMixed
```

hrezaei commited on Oct 25, 2025

Commit

646c212

verified ·

1 Parent(s): 94a61a3

Training in progress, epoch 0

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Oct24_09-19-11_gpu24.viking2.yor.alces.network/events.out.tfevents.1761294199.gpu24.viking2.yor.alces.network.1159958.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c001ecbd2e85f6b3dd636a5ac586e71252f2f03b01dd3a24d713ea9d75f47a
 size 3001072424

 version https://git-lfs.github.com/spec/v1
+oid sha256:2750ed6b34f149749f56008ad1c617150aa85685e7e37c26281d7b6038a27e94
 size 3001072424

runs/Oct24_09-19-11_gpu24.viking2.yor.alces.network/events.out.tfevents.1761294199.gpu24.viking2.yor.alces.network.1159958.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c04e19802e283202a8d91bce62b5de61c587c91cf7d58cc615421fc59f52c83
-size 388606

 version https://git-lfs.github.com/spec/v1
+oid sha256:2c6e3843dff27a281659127280e5d0872249c62e92b01a13ff43ad0730335ddc
+size 580045