Instructions to use AgentGYM-exp/syndra-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AgentGYM-exp/syndra-large with Transformers:

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

pipe = pipeline("text-generation", model="AgentGYM-exp/syndra-large")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AgentGYM-exp/syndra-large", device_map="auto")

PEFT
How to use AgentGYM-exp/syndra-large with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AgentGYM-exp/syndra-large with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AgentGYM-exp/syndra-large

SGLang

How to use AgentGYM-exp/syndra-large 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 "AgentGYM-exp/syndra-large" \
    --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": "AgentGYM-exp/syndra-large",
		"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 "AgentGYM-exp/syndra-large" \
        --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": "AgentGYM-exp/syndra-large",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AgentGYM-exp/syndra-large with Docker Model Runner:
```
docker model run hf.co/AgentGYM-exp/syndra-large
```

victormaricato commited on Oct 29, 2025

Commit

5a9e8be

verified ·

1 Parent(s): f77aba9

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

adapter_config.json +5 -5
adapter_model.safetensors +1 -1
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "o_proj",
-    "gate_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "o_proj",
+    "down_proj",
+    "q_proj",
     "k_proj",
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44fa7906ac11fbcb6ac864e424f2a4cce345aa77dcca72fcdf2217fc8825291
 size 1685278680

 version https://git-lfs.github.com/spec/v1
+oid sha256:a33803a3b00d0ef8a63bac4a8f639fd89071c4a7deca5513764ad7af8796e593
 size 1685278680

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ba6bc6a8b856e4798035cf87c584df0dc96777f7204055776976f1571af1bd2
 size 5688

 version https://git-lfs.github.com/spec/v1
+oid sha256:2ca9e068f19038ff38a6f748933d6e6f8ccafc4996dcd0edde0e7bd94e62dd28
 size 5688