Instructions to use MARIO-Math-Reasoning/MARIO-OVM-7B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MARIO-Math-Reasoning/MARIO-OVM-7B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="MARIO-Math-Reasoning/MARIO-OVM-7B-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MARIO-Math-Reasoning/MARIO-OVM-7B-v1")
model = AutoModelForCausalLM.from_pretrained("MARIO-Math-Reasoning/MARIO-OVM-7B-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MARIO-Math-Reasoning/MARIO-OVM-7B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MARIO-Math-Reasoning/MARIO-OVM-7B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MARIO-Math-Reasoning/MARIO-OVM-7B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MARIO-Math-Reasoning/MARIO-OVM-7B-v1

SGLang

How to use MARIO-Math-Reasoning/MARIO-OVM-7B-v1 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 "MARIO-Math-Reasoning/MARIO-OVM-7B-v1" \
    --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": "MARIO-Math-Reasoning/MARIO-OVM-7B-v1",
		"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 "MARIO-Math-Reasoning/MARIO-OVM-7B-v1" \
        --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": "MARIO-Math-Reasoning/MARIO-OVM-7B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MARIO-Math-Reasoning/MARIO-OVM-7B-v1 with Docker Model Runner:
```
docker model run hf.co/MARIO-Math-Reasoning/MARIO-OVM-7B-v1
```

kf96 commited on Jan 17, 2024

Commit

bbf5dd8

verified ·

1 Parent(s): 2505714

Upload 4 files

Browse files

Files changed (4) hide show

added_tokens.json +5 -0
config.json +29 -0
generation_config.json +7 -0
pytorch_model-00001-of-00014.bin +3 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_name_or_path": "/mnt/workspace/workgroup/minpeng.lmp/workspace/Efficient-Tuning/outputs/llemma_7b_20240113002039_from_chengxi/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "value_model": true,
+  "vocab_size": 32016
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

pytorch_model-00001-of-00014.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:41a2bb83d5df8ba4d321737c74d808083582bf6f081076e822118313b79ae101
+size 981620682