Instructions to use tytodd/arbor-test-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tytodd/arbor-test-2 with Transformers:

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

pipe = pipeline("text-generation", model="tytodd/arbor-test-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tytodd/arbor-test-2")
model = AutoModelForCausalLM.from_pretrained("tytodd/arbor-test-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tytodd/arbor-test-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tytodd/arbor-test-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tytodd/arbor-test-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tytodd/arbor-test-2

SGLang

How to use tytodd/arbor-test-2 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 "tytodd/arbor-test-2" \
    --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": "tytodd/arbor-test-2",
		"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 "tytodd/arbor-test-2" \
        --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": "tytodd/arbor-test-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tytodd/arbor-test-2 with Docker Model Runner:
```
docker model run hf.co/tytodd/arbor-test-2
```

tytodd commited on Nov 2, 2025

Commit

3c9c001

verified ·

1 Parent(s): fa190a1

model_checkpoint_test

Browse files

Files changed (7) hide show

model_checkpoint_test/metadata.json +4 -0
model_checkpoint_test/optimizer.pt +2 -2
model_checkpoint_test/rng_state.pth +1 -1
model_checkpoint_test/scheduler.pt +1 -1
model_checkpoint_test/trainer_state.json +6 -30
model_checkpoint_test/training_args.bin +2 -2
training_args.bin +2 -2

model_checkpoint_test/metadata.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "score": 0.0,
+  "step_index": 0
+}

model_checkpoint_test/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65705bd2a8af3869b16af29bb33330b53303d946b96e94318390cba97cc81b2e
-size 3952509771

 version https://git-lfs.github.com/spec/v1
+oid sha256:426c65fe6efafe9122c6f867160776c5ab9ca0fabf89c01b69ee9de1eb034124
+size 2297

model_checkpoint_test/rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b2d0e7e32c57f217bda640702c9a866cc251489bef3ccf66647c47e2f0ee6b
 size 14645

 version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
 size 14645

model_checkpoint_test/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1df6aa405639e3557888fcfe2436bb9a52be8517ae5231728aa34d0c5e37aa
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:24ea0cb7b47f612954454da2a06d80c327ff664c0beff3af56cbb5de08d2b6ab
 size 1465

model_checkpoint_test/trainer_state.json CHANGED Viewed

@@ -1,41 +1,17 @@
 {
   "best_global_step": null,
   "best_metric": null,
-  "best_model_checkpoint": "/home/paperspace/.arbor/storage/grpo:qwen2-0.5b-instruct:masked-penguin:20251027/checkpoints/model_checkpoint_best",
-  "epoch": 0.20634920634920634,
   "eval_steps": 500,
-  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "clip_ratio/high_max": 0.0,
-      "clip_ratio/high_mean": 0.0,
-      "clip_ratio/low_mean": 0.0,
-      "clip_ratio/low_min": 0.0,
-      "clip_ratio/region_mean": 0.0,
-      "completions/clipped_ratio": 0.0,
-      "completions/max_length": 4.0,
-      "completions/max_terminated_length": 4.0,
-      "completions/mean_length": 4.0,
-      "completions/mean_terminated_length": 4.0,
-      "completions/min_length": 4.0,
-      "completions/min_terminated_length": 4.0,
-      "epoch": 0.15873015873015872,
-      "grad_norm": 0.0,
-      "kl": 0.0,
-      "learning_rate": 9e-07,
-      "loss": 0.0,
-      "num_tokens": 4960.0,
-      "reward": -1.0,
-      "reward_std": 0.0,
-      "step": 10
-    }
-  ],
   "logging_steps": 10,
   "max_steps": 500,
-  "num_input_tokens_seen": 6448,
   "num_train_epochs": 8,
   "save_steps": 500,
   "stateful_callbacks": {
@@ -50,7 +26,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 0.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

 {
   "best_global_step": null,
   "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0,
   "eval_steps": 500,
+  "global_step": 0,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
+  "log_history": [],
   "logging_steps": 10,
   "max_steps": 500,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 500,
   "stateful_callbacks": {
       "attributes": {}
     }
   },
+  "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

model_checkpoint_test/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37311d79cdb8b23fae81f9e99e135d4bd44ca29b020b3838b33e13d534c37262
-size 7633

 version https://git-lfs.github.com/spec/v1
+oid sha256:1358766191dc7baee28883479e004089c478ffe01eb8a1acb403a49ca49b1358
+size 7697

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37311d79cdb8b23fae81f9e99e135d4bd44ca29b020b3838b33e13d534c37262
-size 7633

 version https://git-lfs.github.com/spec/v1
+oid sha256:1358766191dc7baee28883479e004089c478ffe01eb8a1acb403a49ca49b1358
+size 7697