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

Libraries

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

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

pipe = pipeline("text-generation", model="Kentucky-Open-Science/KOS-V5-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("Kentucky-Open-Science/KOS-V5-Instruct")
model = AutoModelForCausalLM.from_pretrained("Kentucky-Open-Science/KOS-V5-Instruct", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kentucky-Open-Science/KOS-V5-Instruct 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-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kentucky-Open-Science/KOS-V5-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use Kentucky-Open-Science/KOS-V5-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 "Kentucky-Open-Science/KOS-V5-Instruct" \
    --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": "Kentucky-Open-Science/KOS-V5-Instruct",
		"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 "Kentucky-Open-Science/KOS-V5-Instruct" \
        --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": "Kentucky-Open-Science/KOS-V5-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

codybum commited on Jul 24

Commit

c554a92

verified ·

1 Parent(s): cea427e

Add Retrieval & embeddings section + link to KOS-V5-Retriever adapter

Browse files

Files changed (1) hide show

README.md +16 -0

README.md CHANGED Viewed

@@ -309,6 +309,20 @@ that several of these models are non-English-first (Finnish, Italian, French, Po
 measured on English benchmarks, which understates their designed capability. On parametric knowledge (MMLU) the
 larger, more heavily trained models still lead.
 ## Known regressions and limitations
 > These are disclosed deliberately. A high benchmark score does not make this checkpoint production-ready.
@@ -374,6 +388,8 @@ print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
 ## Related models
 - [**KOS-V5-Base**](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Base) — the from-scratch pretrained
   foundation this model is tuned from (3.72B, 235.2B tokens).
 - [**KOS-V4-Instruct**](https://huggingface.co/Kentucky-Open-Science/KOS-V4-Instruct) — previous generation

 measured on English benchmarks, which understates their designed capability. On parametric knowledge (MMLU) the
 larger, more heavily trained models still lead.
+## Retrieval & embeddings
+Beyond generation, KOS-V5-Instruct **also serves as a dense text retriever.** A companion **LoRA adapter** —
+[**KOS-V5-Retriever**](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Retriever) — converts
+this model into an embedding model (llm2vec-style: bidirectional attention + mean-pooling + a contrastively-trained
+rank-32 LoRA), with these base weights **frozen and unchanged**.
+On the **official BEIR SciFact** benchmark (the `beir` library + pytrec_eval — the public-leaderboard scorer),
+**zero-shot** (training excluded SciFact, verified clean), it scores **NDCG@10 = 0.7007** (Recall@10 0.864) — a
+**strong dense retriever**, above BM25 (0.665) and within the GTR/E5/BGE band (0.70–0.76). The adapter is
+hot-swappable: attach it for retrieval, detach it for generation. See the
+[adapter card](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Retriever) for the encode recipe and
+the full retrieval details.
 ## Known regressions and limitations
 > These are disclosed deliberately. A high benchmark score does not make this checkpoint production-ready.
 ## Related models
+- [**KOS-V5-Retriever**](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Retriever) — a LoRA
+  **retrieval/embedding adapter** for this model (llm2vec; official BEIR SciFact NDCG@10 **0.70**, zero-shot).
 - [**KOS-V5-Base**](https://huggingface.co/Kentucky-Open-Science/KOS-V5-Base) — the from-scratch pretrained
   foundation this model is tuned from (3.72B, 235.2B tokens).
 - [**KOS-V4-Instruct**](https://huggingface.co/Kentucky-Open-Science/KOS-V4-Instruct) — previous generation