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

ce4e6c6

verified ·

1 Parent(s): 6b3cb60

Card: Catbird logo + intro, official BFCL results

Browse files

Files changed (1) hide show

README.md +10 -8

README.md CHANGED Viewed

@@ -260,14 +260,16 @@ English benchmarks, which understates their designed capability.
 > These are disclosed deliberately. A high IFEval score does not make this checkpoint production-ready.
-- **Tool / function calling is measured and improved** — see the BFCL table above. It does score below the
-  *SFT seed's* previously reported 87.0 on `multiple`; that 87.0 is a number our own records have since
-  declared **invalid** (it was inflated by benchmark contamination and collapsed to 7.0 once the affected
-  records were removed), so it is not a meaningful reference point. Against the **published** KOS-V4-Instruct
-  figures, this model is better on all three categories.
-- **Fabrication roughly doubled** on our internal gate (**14.4% → 28%**) during GRPO. That gate is itself under
-  review because it measures on pretraining-distribution text, so the magnitude is uncertain — but the direction
-  is a real concern and is the main reason this artifact is private.
 - **Optimising a verifiable reward moved a verifiable metric.** GRPO maximised the official IFEval checker, and
   IFEval went up. Improvement on *unrelated* capabilities should not be assumed from this number.
 - **MMLU 0.3720 is above chance (0.25) but modest.** This is not a knowledge model; it should not be used as a

 > These are disclosed deliberately. A high IFEval score does not make this checkpoint production-ready.
+- **Tool / function calling is measured and improved** — see the BFCL table above. Note that GRPO did not
+  optimise for it; the reward ran the IFEval checker only, so this is carried SFT capability. Comparisons to
+  earlier internal KOS tool-calling figures are deliberately omitted: several were measured against benchmark
+  data the model had been trained on and are recorded in our own audit as **invalid**. The comparison here is
+  against the **published** KOS-V4-Instruct numbers only.
+- **Hallucination / fabrication: NOT INDEPENDENTLY MEASURED.** An internal gate reported an increase during
+  GRPO, but that gate measures on pretraining-distribution text and is under review, so **no figure from it is
+  reported here.** No official hallucination benchmark has been run on this checkpoint. Treat fabrication
+  behaviour as **unmeasured**, and note that RL against a format-verifiable reward is a plausible mechanism for
+  making a model more confidently wrong. This is a principal reason the artifact is private.
 - **Optimising a verifiable reward moved a verifiable metric.** GRPO maximised the official IFEval checker, and
   IFEval went up. Improvement on *unrelated* capabilities should not be assumed from this number.
 - **MMLU 0.3720 is above chance (0.25) but modest.** This is not a knowledge model; it should not be used as a