Instructions to use rootti/model-248 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rootti/model-248 with Transformers:

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

pipe = pipeline("text-generation", model="rootti/model-248")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rootti/model-248")
model = AutoModelForCausalLM.from_pretrained("rootti/model-248")
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 rootti/model-248 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rootti/model-248"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rootti/model-248",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rootti/model-248

SGLang

How to use rootti/model-248 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 "rootti/model-248" \
    --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": "rootti/model-248",
		"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 "rootti/model-248" \
        --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": "rootti/model-248",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rootti/model-248 with Docker Model Runner:
```
docker model run hf.co/rootti/model-248
```

model-248 / README.md

rootti

Duplicate from Doomate/Affine-re-5DAGsDentUAs6Uh9SYJ2uLEQvYRWu1Euqai97AHF3A7RiGoT

42f21b7 about 1 month ago

preview code

Raw

History Blame Contribute Delete

871 Bytes

metadata

base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

nntoan_prexpert_80-20

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear merge method using /root/sn120/model_path1 as a base.

Models Merged

The following models were included in the merge:

/root/sn120/model_path2

Configuration

The following YAML configuration was used to produce this model:

# Linear merge: prexpert (80%) + nntoan209 (20%)
merge_method: linear
dtype: bfloat16

base_model: /root/sn120/model_path1

parameters:
  normalize: true

models:
  - model: /root/sn120/model_path1
    parameters:
      weight: 0.80
  - model: /root/sn120/model_path2
    parameters:
      weight: 0.20