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
```

KOS-V5-Instruct

Commit History

Sep 22

14:12
Update README.md

codybum

Verified signature
f61a416

Jul 24

23:20
Add Retrieval & embeddings section + link to KOS-V5-Retriever adapter

codybum

Verified signature
c554a92

Jul 22

13:51
Card: RESTORE full model card (logo, specs, pre/post-training, medical foundation, IFEval-in-context, quickstart, deployment) that a prior push had gutted; all numbers = leg-T step 40 on consistent official harnesses (IFEval 72.19 pristine, BFCL 85/84/80.5, peer 84.71)

codybum

Verified signature
cea427e
02:06
Card: peer Qwen3-4B-2507 IFEval = 84.71 (exact, pristine-harness canonical value)

codybum

Verified signature
d204d6f

Jul 21

22:44
Card: restore full peer comparison (Qwen3-4B-2507) that was wrongly stripped; update KOS column to leg-T (BFCL now above peer, IFEval/knowledge honest vs peer)

codybum

Verified signature
505b3cc
22:15
Card: knowledge benchmarks re-measured on this checkpoint (MMLU 0.4512, PubMedQA 0.706, MedQA 0.3802, MedMCQA 0.3648) — jobs 202025/202026

codybum

Verified signature
91c9261
21:54
KOS-V5-Instruct 2026-07-21: recover tool calling via official-BFCL GRPO (leg T, step 40)⁠

codybum

Verified signature
7188bdc

Jul 20

22:05
Card: Catbird logo + intro, official BFCL results

codybum

Verified signature
d94783b
21:50
Card: Catbird logo + intro, official BFCL results

codybum

Verified signature
966c763
20:16
KOS-V5-Instruct 2026-07-20: v2mix SFT + official-IFEval GRPO (leg A, step 164)⁠

codybum

Verified signature
e8d1a9b

Jul 18

22:23
Card: Catbird logo + intro, official BFCL results

codybum

Verified signature
a7a4ce7
22:19
Card: Catbird logo + intro, official BFCL results

codybum

Verified signature
fa7fe5e
21:56
Card: Catbird logo + intro, official BFCL results

codybum

Verified signature
ce4e6c6
21:49
Card: Catbird logo + intro, official BFCL results

codybum

Verified signature
6b3cb60
21:49
Add Catbird logo (matches KOS-V5-Base)

codybum

Verified signature
bb1d93a
21:31
Card: tool/function calling recorded as NOT EVALUATED

codybum

Verified signature
5058350
21:27
KOS-V5-Instruct (Catbird) — IF-GRPO step 888

codybum

Verified signature
41f25fa
21:26
initial commit

codybum

Verified signature
2029af3

Commit History

Sep 22

Update README.md

Jul 24

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

Jul 22

Card: RESTORE full model card (logo, specs, pre/post-training, medical foundation, IFEval-in-context, quickstart, deployment) that a prior push had gutted; all numbers = leg-T step 40 on consistent official harnesses (IFEval 72.19 pristine, BFCL 85/84/80.5, peer 84.71)

Card: peer Qwen3-4B-2507 IFEval = 84.71 (exact, pristine-harness canonical value)

Jul 21

Card: restore full peer comparison (Qwen3-4B-2507) that was wrongly stripped; update KOS column to leg-T (BFCL now above peer, IFEval/knowledge honest vs peer)

Card: knowledge benchmarks re-measured on this checkpoint (MMLU 0.4512, PubMedQA 0.706, MedQA 0.3802, MedMCQA 0.3648) — jobs 202025/202026

KOS-V5-Instruct 2026-07-21: recover tool calling via official-BFCL GRPO (leg T, step 40)⁠

Jul 20

Card: Catbird logo + intro, official BFCL results

Card: Catbird logo + intro, official BFCL results

KOS-V5-Instruct 2026-07-20: v2mix SFT + official-IFEval GRPO (leg A, step 164)⁠

Jul 18

Card: Catbird logo + intro, official BFCL results

Card: Catbird logo + intro, official BFCL results

Card: Catbird logo + intro, official BFCL results

Card: Catbird logo + intro, official BFCL results

Add Catbird logo (matches KOS-V5-Base)

Card: tool/function calling recorded as NOT EVALUATED

KOS-V5-Instruct (Catbird) — IF-GRPO step 888

initial commit