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

Libraries

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

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

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

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

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

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

victormaricato commited on Oct 29, 2025

Commit

5deccd0

verified ·

1 Parent(s): 6fbfb2e

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

README.md +1 -1
adapter_config.json +6 -6
adapter_model.safetensors +2 -2
training_args.bin +2 -2
training_params.json +3 -3

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ tags:
 - text-generation
 - peft
 library_name: transformers
-base_model: affine-kraus/anthrx-gg
 widget:
   - messages:
       - role: user

 - text-generation
 - peft
 library_name: transformers
+base_model: Marco0/Affine-QQ
 widget:
   - messages:
       - role: user

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "affine-kraus/anthrx-gg",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "v_proj",
     "q_proj",
     "up_proj",
-    "o_proj",
-    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "Marco0/Affine-QQ",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
+    "gate_proj",
     "up_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_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 sha256:0c058d32d7bc219e6dcf6a6633fff8245e4597a0289a5e0f7c74d3f796a79575
-size 1619220744

 version https://git-lfs.github.com/spec/v1
+oid sha256:8f5376bfdb6020e444f48fa08149162b89b96bb0b8e9e6c1f064ca113272c664
+size 1685278680

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f301d11e0441f14a47c9d467bc0017a7f790b89fbbcc7d837f5ea2686681b0f
-size 6968

 version https://git-lfs.github.com/spec/v1
+oid sha256:0839725bae1c909dc2a706afd769ef80e86d5f1cf32074ad7980d82f0b6b7343
+size 5688

training_params.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-    "model": "affine-kraus/anthrx-gg",
     "project_name": "syndra-ax",
     "data_path": "victormaricato/syndra-autotrain-dataset",
     "train_split": "train",
@@ -43,7 +43,7 @@
     "text_column": "output",
     "rejected_text_column": null,
     "push_to_hub": true,
-    "username": "victormaricato",
     "unsloth": false,
-    "distributed_backend": "deepspeed"
 }

 {
+    "model": "Marco0/Affine-QQ",
     "project_name": "syndra-ax",
     "data_path": "victormaricato/syndra-autotrain-dataset",
     "train_split": "train",
     "text_column": "output",
     "rejected_text_column": null,
     "push_to_hub": true,
+    "username": "AgentGYM-exp",
     "unsloth": false,
+    "distributed_backend": null
 }