Instructions to use Kentucky-Open-Science/KOS-V5-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kentucky-Open-Science/KOS-V5-Base with Transformers:

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

pipe = pipeline("text-generation", model="Kentucky-Open-Science/KOS-V5-Base")

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

tokenizer = AutoTokenizer.from_pretrained("Kentucky-Open-Science/KOS-V5-Base")
model = AutoModelForCausalLM.from_pretrained("Kentucky-Open-Science/KOS-V5-Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kentucky-Open-Science/KOS-V5-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kentucky-Open-Science/KOS-V5-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kentucky-Open-Science/KOS-V5-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kentucky-Open-Science/KOS-V5-Base

SGLang

How to use Kentucky-Open-Science/KOS-V5-Base 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 "Kentucky-Open-Science/KOS-V5-Base" \
    --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": "Kentucky-Open-Science/KOS-V5-Base",
		"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 "Kentucky-Open-Science/KOS-V5-Base" \
        --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": "Kentucky-Open-Science/KOS-V5-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kentucky-Open-Science/KOS-V5-Base with Docker Model Runner:
```
docker model run hf.co/Kentucky-Open-Science/KOS-V5-Base
```

KOS-V5-Base / config.json

codybum

transformers 4.x + 5.x compatibility: dual RoPE schema (flat rope_theta + nested rope_parameters), model_input_names; verified on 4.57.1 and 5.2.0

051bb07 verified 3 months ago

Raw History Blame Contribute Delete

1.66 kB

	{
	"architectures": [
	"Qwen3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 0,
	"dtype": "bfloat16",
	"eos_token_id": 0,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2560,
	"initializer_range": 0.02,
	"intermediate_size": 9728,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 32768,
	"max_window_layers": 36,
	"model_type": "qwen3",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 25000.0,
	"rope_type": "default"
	},
	"sliding_window": null,
	"tie_word_embeddings": true,
	"transformers_version": "5.2.0",
	"use_cache": true,
	"use_sliding_window": false,
	"vocab_size": 32000,
	"rope_theta": 25000.0,
	"rope_scaling": null,
	"torch_dtype": "bfloat16"
	}