Instructions to use CrossBaseArithmetic/arithmetic-model-L1_H16_D64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CrossBaseArithmetic/arithmetic-model-L1_H16_D64 with Transformers:

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

pipe = pipeline("text-generation", model="CrossBaseArithmetic/arithmetic-model-L1_H16_D64")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CrossBaseArithmetic/arithmetic-model-L1_H16_D64")
model = AutoModelForCausalLM.from_pretrained("CrossBaseArithmetic/arithmetic-model-L1_H16_D64", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CrossBaseArithmetic/arithmetic-model-L1_H16_D64 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CrossBaseArithmetic/arithmetic-model-L1_H16_D64"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CrossBaseArithmetic/arithmetic-model-L1_H16_D64",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CrossBaseArithmetic/arithmetic-model-L1_H16_D64

SGLang

How to use CrossBaseArithmetic/arithmetic-model-L1_H16_D64 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 "CrossBaseArithmetic/arithmetic-model-L1_H16_D64" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CrossBaseArithmetic/arithmetic-model-L1_H16_D64",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "CrossBaseArithmetic/arithmetic-model-L1_H16_D64" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CrossBaseArithmetic/arithmetic-model-L1_H16_D64",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CrossBaseArithmetic/arithmetic-model-L1_H16_D64 with Docker Model Runner:
```
docker model run hf.co/CrossBaseArithmetic/arithmetic-model-L1_H16_D64
```

maansi-sathish commited on Jun 24

Commit

d6d51cc

verified ·

1 Parent(s): 8fe7096

Training in progress, epoch 1

Browse files

Files changed (5) hide show

config.json +1 -1
generation_config.json +1 -1
model.safetensors +1 -1
tokenizer_config.json +0 -1
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -28,7 +28,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "tie_word_embeddings": true,
-  "transformers_version": "5.12.0",
   "use_cache": false,
   "vocab_size": 23
 }

   "summary_type": "cls_index",
   "summary_use_proj": true,
   "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
   "use_cache": false,
   "vocab_size": 23
 }

generation_config.json CHANGED Viewed

@@ -7,6 +7,6 @@
   "output_attentions": false,
   "output_hidden_states": false,
   "pad_token_id": 0,
-  "transformers_version": "5.12.0",
   "use_cache": true
 }

   "output_attentions": false,
   "output_hidden_states": false,
   "pad_token_id": 0,
+  "transformers_version": "5.0.0",
   "use_cache": true
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f0fec579615810a89cdd15565b219e950e86d09ea3b42df873aeb2d30f7618
 size 273368

 version https://git-lfs.github.com/spec/v1
+oid sha256:56a2266dd61c7bd6780a316169a0cfba85f48c1d21e8ab5c9b1f776e021ca22d
 size 273368

tokenizer_config.json CHANGED Viewed

@@ -3,7 +3,6 @@
   "bos_token": "<bos>",
   "eos_token": "<eos>",
   "is_local": false,
-  "local_files_only": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "TokenizersBackend",

   "bos_token": "<bos>",
   "eos_token": "<eos>",
   "is_local": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "TokenizersBackend",

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda4e796ba5f0ad0a10452716a4ab478201fe2887144ee16e0f1a0c7f914e5f7
 size 5265

 version https://git-lfs.github.com/spec/v1
+oid sha256:2a5c1ad0663d06a2bd3a7d3553a54e126550afa5b448ed85890df1983c5a5ade
 size 5265