Instructions to use q-future/co-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use q-future/co-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="q-future/co-instruct", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("q-future/co-instruct", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use q-future/co-instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "q-future/co-instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "q-future/co-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/q-future/co-instruct
- SGLang
How to use q-future/co-instruct 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 "q-future/co-instruct" \ --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": "q-future/co-instruct", "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 "q-future/co-instruct" \ --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": "q-future/co-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use q-future/co-instruct with Docker Model Runner:
docker model run hf.co/q-future/co-instruct
Update modeling_llama2.py
Browse files- modeling_llama2.py +1 -1
modeling_llama2.py
CHANGED
|
@@ -16,7 +16,7 @@ import sys
|
|
| 16 |
dir_path = os.path.dirname(os.path.realpath(__file__))
|
| 17 |
sys.path.insert(0, dir_path)
|
| 18 |
|
| 19 |
-
from .modeling_attn_mask_utils import _prepare_4d_causal_attention_mask,
|
| 20 |
|
| 21 |
import transformers
|
| 22 |
from transformers.models.llama.modeling_llama import *
|
|
|
|
| 16 |
dir_path = os.path.dirname(os.path.realpath(__file__))
|
| 17 |
sys.path.insert(0, dir_path)
|
| 18 |
|
| 19 |
+
from .modeling_attn_mask_utils import _prepare_4d_causal_attention_mask, _prepare_4d_causal_attention_mask_for_sdpa
|
| 20 |
|
| 21 |
import transformers
|
| 22 |
from transformers.models.llama.modeling_llama import *
|