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 18

Commit

fa7fe5e

verified ·

1 Parent(s): ce4e6c6

Card: Catbird logo + intro, official BFCL results

Browse files

Files changed (1) hide show

README.md +23 -1

README.md CHANGED Viewed

@@ -81,7 +81,8 @@ Hugging Face Open LLM Leaderboard publishes as "IFEval."
 | 55.9 | GPT-3.5-turbo-1106 (the original ChatGPT) | OpenAI, ~10,000-GPU supercomputer |
 KOS-V5-Instruct **improves on KOS-V4-Instruct across every benchmark measured**: IFEval strict-avg
-**61.6 → 67.01** (+5.4), MMLU **0.2782 → 0.3720** (+9.4), and official BFCL function-calling
 **72.75/73.00/60.50 → 83.25/78.50/73.50** (+10.5 / +5.5 / +13.0). It clears both the original GPT-3.5-turbo
 generation and the commercially trained Qwen2.5-3B on instruction following.
@@ -158,6 +159,25 @@ The 9 medical subjects of MMLU, extracted from the same official 5-shot run:
 **+10.8 points over KOS-V4-Instruct**, and above the model's own full-MMLU average (0.3720) — the medical
 subjects are where it is strongest.
 > ⚠️ **Why the MCQ numbers understate this model.** Our own measurements show KOS models place very little
 > probability mass on MCQ answer *letters*: the format, not the knowledge, is the bottleneck. A model that ranks
 > **1 of 17** at modelling clinical text while scoring modestly on multiple-choice is exhibiting exactly that gap.
@@ -173,6 +193,8 @@ subjects are where it is strongest.
   **Google** verifier (`instructions_registry`, 25 instruction types).
 - **MMLU** — stock `mmlu` group, official 57 subjects / 14,042 test items, 5-shot from `dev` (`first_n`),
   loglikelihood over A–D, metric `acc` (not `acc_norm`), **no chat template**.
 | benchmark | KOS-V5-Instruct | KOS-V4-Instruct | Δ |
 | :-- | --: | --: | --: |

 | 55.9 | GPT-3.5-turbo-1106 (the original ChatGPT) | OpenAI, ~10,000-GPU supercomputer |
 KOS-V5-Instruct **improves on KOS-V4-Instruct across every benchmark measured**: IFEval strict-avg
+**61.6 → 67.01** (+5.4), MMLU **0.2782 → 0.3720** (+9.4), medical QA (**PubMedQA 0.7200**, MedQA 0.3370,
+MedMCQA 0.3282 — all up on V4), and official BFCL function-calling
 **72.75/73.00/60.50 → 83.25/78.50/73.50** (+10.5 / +5.5 / +13.0). It clears both the original GPT-3.5-turbo
 generation and the commercially trained Qwen2.5-3B on instruction following.
 **+10.8 points over KOS-V4-Instruct**, and above the model's own full-MMLU average (0.3720) — the medical
 subjects are where it is strongest.
+### Medical QA benchmarks (official suites)
+Official `medqa_4options`, `medmcqa` and `pubmedqa` from the same pristine lm-evaluation-harness,
+5-shot, loglikelihood, metric `acc` — every model below scored in the same run on the same day.
+| medical benchmark | **KOS-V5-Instruct** | KOS-V4-Instruct | YuLan-Mini-Instruct | marin-8b-instruct | Qwen3-4B-Instruct-2507 |
+| :-- | --: | --: | --: | --: | --: |
+| params | **3.7B** | 3.0B | 2.4B | 8.0B | 4.0B |
+| **PubMedQA** | **0.7200** | 0.6860 | 0.6960 | 0.7500 | 0.7720 |
+| MedQA (USMLE, 4-option) | **0.3370** | 0.2820 | 0.3511 | 0.4878 | 0.6159 |
+| MedMCQA | **0.3282** | 0.2778 | 0.3856 | 0.4961 | 0.5804 |
+**KOS-V5-Instruct improves on KOS-V4-Instruct on all three** (+5.5 MedQA, +5.0 MedMCQA, +3.4 PubMedQA).
+**PubMedQA is the standout: 0.7200**, within 3 points of Stanford's Marin-8B at **less than half the
+parameters**, and ahead of YuLan-Mini. PubMedQA tests comprehension of **biomedical literature** — the closest
+of these three to what the base was actually trained on. The USMLE-style exam MCQs (MedQA, MedMCQA) are where
+the answer-letter bottleneck below bites hardest.
 > ⚠️ **Why the MCQ numbers understate this model.** Our own measurements show KOS models place very little
 > probability mass on MCQ answer *letters*: the format, not the knowledge, is the bottleneck. A model that ranks
 > **1 of 17** at modelling clinical text while scoring modestly on multiple-choice is exhibiting exactly that gap.
   **Google** verifier (`instructions_registry`, 25 instruction types).
 - **MMLU** — stock `mmlu` group, official 57 subjects / 14,042 test items, 5-shot from `dev` (`first_n`),
   loglikelihood over A–D, metric `acc` (not `acc_norm`), **no chat template**.
+- **Medical QA** — stock `medqa_4options`, `medmcqa`, `pubmedqa` tasks, 5-shot, loglikelihood, metric `acc`,
+  no chat template.
 | benchmark | KOS-V5-Instruct | KOS-V4-Instruct | Δ |
 | :-- | --: | --: | --: |