Instructions to use khrisintw/TAIDE-Chat-TaskArithmetic-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use khrisintw/TAIDE-Chat-TaskArithmetic-7B with Transformers:

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

pipe = pipeline("text-generation", model="khrisintw/TAIDE-Chat-TaskArithmetic-7B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("khrisintw/TAIDE-Chat-TaskArithmetic-7B")
model = AutoModelForCausalLM.from_pretrained("khrisintw/TAIDE-Chat-TaskArithmetic-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use khrisintw/TAIDE-Chat-TaskArithmetic-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/khrisintw/TAIDE-Chat-TaskArithmetic-7B

SGLang

How to use khrisintw/TAIDE-Chat-TaskArithmetic-7B 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 "khrisintw/TAIDE-Chat-TaskArithmetic-7B" \
    --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": "khrisintw/TAIDE-Chat-TaskArithmetic-7B",
		"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 "khrisintw/TAIDE-Chat-TaskArithmetic-7B" \
        --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": "khrisintw/TAIDE-Chat-TaskArithmetic-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use khrisintw/TAIDE-Chat-TaskArithmetic-7B with Docker Model Runner:
```
docker model run hf.co/khrisintw/TAIDE-Chat-TaskArithmetic-7B
```

TAIDE-Chat-TaskArithmetic-7B / README.md

khrisintw

Update README.md

4e61fac verified over 2 years ago

preview code

Raw History Blame Contribute Delete

1.2 kB

---
base_model:
- NousResearch/Llama-2-7b-chat-hf
- NousResearch/Llama-2-7b-hf
- taide/TAIDE-LX-7B
library_name: transformers
tags:
- mergekit
- merge
license: mit
---
# merged

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) as a base.

### Models Merged

The following models were included in the merge:
* [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf)
* [taide/TAIDE-LX-7B](https://huggingface.co/taide/TAIDE-LX-7B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: NousResearch/Llama-2-7b-hf
dtype: bfloat16
merge_method: task_arithmetic
slices:
- sources:
  - layer_range: [0, 32]
    model: taide/TAIDE-LX-7B
    parameters:
      weight: 1.0
  - layer_range: [0, 32]
    model: NousResearch/Llama-2-7b-chat-hf
    parameters:
      weight: 1.0
  - layer_range: [0, 32]
    model: NousResearch/Llama-2-7b-hf
```

	---
	base_model:
	- NousResearch/Llama-2-7b-chat-hf
	- NousResearch/Llama-2-7b-hf
	- taide/TAIDE-LX-7B
	library_name: transformers
	tags:
	- mergekit
	- merge
	license: mit
	---
	# merged

	This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

	## Merge Details
	### Merge Method

	This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) as a base.

	### Models Merged

	The following models were included in the merge:
	* [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf)
	* [taide/TAIDE-LX-7B](https://huggingface.co/taide/TAIDE-LX-7B)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	base_model: NousResearch/Llama-2-7b-hf
	dtype: bfloat16
	merge_method: task_arithmetic
	slices:
	- sources:
	- layer_range: [0, 32]
	model: taide/TAIDE-LX-7B
	parameters:
	weight: 1.0
	- layer_range: [0, 32]
	model: NousResearch/Llama-2-7b-chat-hf
	parameters:
	weight: 1.0
	- layer_range: [0, 32]
	model: NousResearch/Llama-2-7b-hf
	```