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

Libraries

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

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AgentGYM-exp/syndra-small", dtype="auto")

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

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AgentGYM-exp/syndra-small"
# 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-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

victormaricato commited on Oct 29, 2025

Commit

c970b07

verified ·

1 Parent(s): 019ce89

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

adapter_config.json +4 -4
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": [
-    "gate_proj",
     "o_proj",
-    "k_proj",
-    "up_proj",
     "q_proj",
     "v_proj",
-    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "o_proj",
     "q_proj",
     "v_proj",
+    "gate_proj",
+    "k_proj",
+    "up_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:e7a353cf946174ac9416f9cf808fe3509119a16ba9bf55890aeed6d65c15dc77
 size 1685278680

 version https://git-lfs.github.com/spec/v1
+oid sha256:888877225faef69e97254c9e5b7905b01c2f01c8c490b4d9213453ada86c1de6
 size 1685278680

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12499673a65a2aa4b303698f5e65f636b5e154e31b1ab270d97e618fa89858f5
 size 5688

 version https://git-lfs.github.com/spec/v1
+oid sha256:17fe382a83622b1a5dc77a27c7b61f87735b142d014b6c42902cf5afa27d75f8
 size 5688