Instructions to use appvoid/arco-2-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use appvoid/arco-2-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="appvoid/arco-2-instruct")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("appvoid/arco-2-instruct") model = AutoModelForCausalLM.from_pretrained("appvoid/arco-2-instruct") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use appvoid/arco-2-instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "appvoid/arco-2-instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "appvoid/arco-2-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/appvoid/arco-2-instruct
- SGLang
How to use appvoid/arco-2-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 "appvoid/arco-2-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": "appvoid/arco-2-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 "appvoid/arco-2-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": "appvoid/arco-2-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use appvoid/arco-2-instruct with Docker Model Runner:
docker model run hf.co/appvoid/arco-2-instruct
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,38 +9,6 @@ library_name: transformers
|
|
| 9 |
tags:
|
| 10 |
- mergekit
|
| 11 |
- merge
|
| 12 |
-
|
| 13 |
---
|
| 14 |
-
# merge
|
| 15 |
-
|
| 16 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 17 |
-
|
| 18 |
-
## Merge Details
|
| 19 |
-
### Merge Method
|
| 20 |
-
|
| 21 |
-
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [appvoid/arco-2](https://huggingface.co/appvoid/arco-2) as a base.
|
| 22 |
-
|
| 23 |
-
### Models Merged
|
| 24 |
-
|
| 25 |
-
The following models were included in the merge:
|
| 26 |
-
* [appvoid/palmer-004-turbo](https://huggingface.co/appvoid/palmer-004-turbo)
|
| 27 |
-
* [appvoid/text-arco](https://huggingface.co/appvoid/text-arco)
|
| 28 |
-
* [appvoid/arco-reflection](https://huggingface.co/appvoid/arco-reflection)
|
| 29 |
-
* [appvoid/arco-2-reasoning-20k](https://huggingface.co/appvoid/arco-2-reasoning-20k)
|
| 30 |
-
|
| 31 |
-
### Configuration
|
| 32 |
-
|
| 33 |
-
The following YAML configuration was used to produce this model:
|
| 34 |
|
| 35 |
-
|
| 36 |
-
models:
|
| 37 |
-
- model: appvoid/arco-reflection
|
| 38 |
-
- model: appvoid/text-arco
|
| 39 |
-
- model: appvoid/arco-2-reasoning-20k
|
| 40 |
-
- model: appvoid/palmer-004-turbo
|
| 41 |
-
merge_method: model_stock
|
| 42 |
-
base_model: appvoid/arco-2
|
| 43 |
-
normalize: false
|
| 44 |
-
int8_mask: true
|
| 45 |
-
dtype: float16
|
| 46 |
-
```
|
|
|
|
| 9 |
tags:
|
| 10 |
- mergekit
|
| 11 |
- merge
|
|
|
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
+
arco-2-instruct (codenamed as arco-exp-17) is a merge of reflection models that improved instruction accuracy a little better than the original one.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|