Instructions to use eworojoshua/vas-01-exp1a-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eworojoshua/vas-01-exp1a-7b with Transformers:

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

pipe = pipeline("text-generation", model="eworojoshua/vas-01-exp1a-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eworojoshua/vas-01-exp1a-7b")
model = AutoModelForCausalLM.from_pretrained("eworojoshua/vas-01-exp1a-7b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eworojoshua/vas-01-exp1a-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eworojoshua/vas-01-exp1a-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eworojoshua/vas-01-exp1a-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eworojoshua/vas-01-exp1a-7b

SGLang

How to use eworojoshua/vas-01-exp1a-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 "eworojoshua/vas-01-exp1a-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eworojoshua/vas-01-exp1a-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "eworojoshua/vas-01-exp1a-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eworojoshua/vas-01-exp1a-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use eworojoshua/vas-01-exp1a-7b with Docker Model Runner:
```
docker model run hf.co/eworojoshua/vas-01-exp1a-7b
```

vas-01-exp1a-7b / README.md

eworojoshua

Upload folder using huggingface_hub

c1d6b22 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

2.23 kB

	---
	base_model:
	- Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
	- jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.5
	- Qwen/Qwen2.5-Math-7B-Instruct
	- Aashraf995/Qwen-Evo-7B
	- jeffmeloy/Qwen2.5-7B-olm-v1.0
	- sometimesanotion/Qwen2.5-7B-Gordion-v0.1-Reason
	- Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
	library_name: transformers
	tags:
	- mergekit
	- merge

	---
	# merge

	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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview](https://huggingface.co/Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview) as a base.

	### Models Merged

	The following models were included in the merge:
	* [Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2](https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2)
	* [jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.5](https://huggingface.co/jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.5)
	* [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)
	* [Aashraf995/Qwen-Evo-7B](https://huggingface.co/Aashraf995/Qwen-Evo-7B)
	* [jeffmeloy/Qwen2.5-7B-olm-v1.0](https://huggingface.co/jeffmeloy/Qwen2.5-7B-olm-v1.0)
	* [sometimesanotion/Qwen2.5-7B-Gordion-v0.1-Reason](https://huggingface.co/sometimesanotion/Qwen2.5-7B-Gordion-v0.1-Reason)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	name: Vas-01-exp1a-7b
	merge_method: model_stock
	base_model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
	tokenizer_source: base
	dtype: bfloat16
	out_dtype: bfloat16
	parameters:
	int8_mask: true
	normalize: true
	rescale: false
	models:
	- model: Qwen/Qwen2.5-Math-7B-Instruct
	- model: sometimesanotion/Qwen2.5-7B-Gordion-v0.1-Reason
	- model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.5
	- model: jeffmeloy/Qwen2.5-7B-olm-v1.0
	- model: Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
	- model: Aashraf995/Qwen-Evo-7B
	```