Instructions to use Multi-Domain-Expert-Learning/osiris_12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multi-Domain-Expert-Learning/osiris_12b with Transformers:

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

pipe = pipeline("text-generation", model="Multi-Domain-Expert-Learning/osiris_12b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Multi-Domain-Expert-Learning/osiris_12b")
model = AutoModelForCausalLM.from_pretrained("Multi-Domain-Expert-Learning/osiris_12b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Multi-Domain-Expert-Learning/osiris_12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Multi-Domain-Expert-Learning/osiris_12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Multi-Domain-Expert-Learning/osiris_12b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Multi-Domain-Expert-Learning/osiris_12b

SGLang

How to use Multi-Domain-Expert-Learning/osiris_12b 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 "Multi-Domain-Expert-Learning/osiris_12b" \
    --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": "Multi-Domain-Expert-Learning/osiris_12b",
		"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 "Multi-Domain-Expert-Learning/osiris_12b" \
        --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": "Multi-Domain-Expert-Learning/osiris_12b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Multi-Domain-Expert-Learning/osiris_12b with Docker Model Runner:
```
docker model run hf.co/Multi-Domain-Expert-Learning/osiris_12b
```

Ontocord.AI commited on Jun 11, 2023

Commit

adc0575

1 Parent(s): 21e31fe

Update config.json

Browse files

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -19,7 +19,7 @@
   "n_embd": 6144,
   "n_head": 48,
   "n_inner": 24576,
-  "n_layer": 40,
   "n_positions": 8192,
   "pad_key_length": true,
   "pre_allocate_kv_cache": false,

   "n_embd": 6144,
   "n_head": 48,
   "n_inner": 24576,
+  "n_layer": 31,
   "n_positions": 8192,
   "pad_key_length": true,
   "pre_allocate_kv_cache": false,