Instructions to use AxisCommunity/OrionPaxAI_1.0V with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AxisCommunity/OrionPaxAI_1.0V with Transformers:

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

pipe = pipeline("text-generation", model="AxisCommunity/OrionPaxAI_1.0V")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AxisCommunity/OrionPaxAI_1.0V")
model = AutoModelForCausalLM.from_pretrained("AxisCommunity/OrionPaxAI_1.0V")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AxisCommunity/OrionPaxAI_1.0V with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AxisCommunity/OrionPaxAI_1.0V"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AxisCommunity/OrionPaxAI_1.0V",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AxisCommunity/OrionPaxAI_1.0V

SGLang

How to use AxisCommunity/OrionPaxAI_1.0V 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 "AxisCommunity/OrionPaxAI_1.0V" \
    --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": "AxisCommunity/OrionPaxAI_1.0V",
		"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 "AxisCommunity/OrionPaxAI_1.0V" \
        --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": "AxisCommunity/OrionPaxAI_1.0V",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AxisCommunity/OrionPaxAI_1.0V with Docker Model Runner:
```
docker model run hf.co/AxisCommunity/OrionPaxAI_1.0V
```

AxisCommunity commited on 21 days ago

Commit

8316445

verified ·

1 Parent(s): 3572d3a

Upload 5 files

Browse files

Files changed (6) hide show

.gitattributes +2 -0
README.md +6 -10
config.json +14 -0
pytorch_model.bin +3 -0
tokenizer.model +3 -0
tokenizer_config.json +9 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
2	+ tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -1,10 +1,6 @@
----
-language:
-- ru
-- kk
-- en
-pipeline_tag: text-generation
-tags:
-- orion-zet
-- axis-community
----

+# OrionZetAI-Nano-Alpha
+Экспериментальная языковая модель 3.4B (64 слоя).
+**Разработчик:** Axis Community
+**Локация:** Казахстан

config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "model_type": "llama",
+    "hidden_size": 5120,
+    "intermediate_size": 13824,
+    "num_hidden_layers": 64,
+    "num_attention_heads": 40,
+    "num_key_value_heads": 40,
+    "vocab_size": 32000,
+    "torch_dtype": "float16",
+    "transformers_version": "4.31.0"
+}

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5d20874c63a76b389ab5b389e2716ba09b1d37a01cb7896a92edb5c9ac8cd4dc
+size 671108523

tokenizer.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "add_bos_token": true,
+    "add_eos_token": true,
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "unk_token": "<unk>",
+    "model_max_length": 2048,
+    "tokenizer_class": "LlamaTokenizer"
+}