Instructions to use darsadilab/zagros-1.0-quick with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use darsadilab/zagros-1.0-quick with Transformers:

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

pipe = pipeline("text-generation", model="darsadilab/zagros-1.0-quick")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("darsadilab/zagros-1.0-quick", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use darsadilab/zagros-1.0-quick with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "darsadilab/zagros-1.0-quick"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "darsadilab/zagros-1.0-quick",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/darsadilab/zagros-1.0-quick

SGLang

How to use darsadilab/zagros-1.0-quick 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 "darsadilab/zagros-1.0-quick" \
    --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": "darsadilab/zagros-1.0-quick",
		"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 "darsadilab/zagros-1.0-quick" \
        --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": "darsadilab/zagros-1.0-quick",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use darsadilab/zagros-1.0-quick with Docker Model Runner:
```
docker model run hf.co/darsadilab/zagros-1.0-quick
```

nebulaResearch commited on Sep 24, 2025

Commit

4e5d76c

verified ·

1 Parent(s): 8968ca3

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -33

README.md CHANGED Viewed

@@ -14,39 +14,6 @@ tags:
 - persian
 - mixture-of-experts
 - moe
-model-index:
-- name: Zagros-1.0-Quick
-  results:
-  - task:
-      type: translation
-      name: Persian-English Translation
-    dataset:
-      type: wmt
-      name: WMT Persian-English
-    metrics:
-    - name: BLEU
-      type: bleu
-      value: 35.2
-  - task:
-      type: text-generation
-      name: Persian Summarization
-    dataset:
-      type: custom
-      name: Persian Summarization Dataset
-    metrics:
-    - name: ROUGE-L
-      type: rouge
-      value: 0.68
-  - task:
-      type: sentiment-analysis
-      name: Persian Sentiment Analysis
-    dataset:
-      type: custom
-      name: Persian Sentiment Dataset
-    metrics:
-    - name: F1
-      type: f1
-      value: 0.93
 library_name: transformers
 pipeline_tag: text-generation
 ---

 - persian
 - mixture-of-experts
 - moe
 library_name: transformers
 pipeline_tag: text-generation
 ---