Text Generation
Transformers
Safetensors
English
qwen3
clinical
medical
instruction-following
tool-calling
function-calling
KOS-V4
from-scratch
conversational
text-generation-inference
Instructions to use Kentucky-Open-Science/KOS-V4-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kentucky-Open-Science/KOS-V4-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kentucky-Open-Science/KOS-V4-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-V4-Instruct") model = AutoModelForCausalLM.from_pretrained("Kentucky-Open-Science/KOS-V4-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-V4-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-V4-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-V4-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Kentucky-Open-Science/KOS-V4-Instruct
- SGLang
How to use Kentucky-Open-Science/KOS-V4-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-V4-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-V4-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-V4-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-V4-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Kentucky-Open-Science/KOS-V4-Instruct with Docker Model Runner:
docker model run hf.co/Kentucky-Open-Science/KOS-V4-Instruct
Commit History
-
LIC
Verified signature6ddcc6f -
Update README.md
Verified signaturee23f4f4 -
Manual update
Verified signature25c83d6 -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signature2199bcf -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signaturee884e9f
-
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signature1f84a3a -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signature601d866 -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signatureb4eae0a -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signature68e3039 -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signature4d4d91b -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signaturedec0c7d -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signature792be18 -
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Verified signature2d5aa65 -
Add commercial reference baselines (GPT-3.5-turbo, Command R, Gemini 1.0 Pro), sourced/attributed
Verified signaturebddd03f -
IFEval-in-context: release dates + GPT-3.5-turbo commercial ref + Sources block
Verified signature9464d72 -
IFEval-in-context: add sourced Company + Released (contents) + precise params
Verified signature9e6b111 -
IFEval context: same-size-or-larger only (>=3B), AVG4, Llama-3.1-8B included, Phi-3.5-mini headline
Verified signaturef4a4430 -
IFEval context on the standard AVG4 metric for all models (62.7 consistent)
Verified signature7d1480b -
IFEval-in-context: use leaderboard-comparable strict-average (61.4) consistently
Verified signature2cf9f83 -
IFEval-in-context: size-fair small-model table + larger-model comparison (archived leaderboard)
Verified signaturec7be14a -
Add Scratch code-name logo
Verified signature17d74da -
Add Scratch code-name logo
Verified signaturec84026b -
Scratch code-name header + research-only disclaimer + official BFCL
Verified signatured9e349a -
Add Scratch code-name logo
Verified signatureab5b357 -
Scratch code-name header + research-only disclaimer + official BFCL
Verified signature668921d -
Add Scratch code-name logo
Verified signature750a9ba -
Rebrand to KOS-V4; David-vs-Goliath GPT-3.5 framing; complete peer tables
Verified signatureb765fc1 -
Rebrand to KOS-V4; David-vs-Goliath GPT-3.5 framing; complete peer tables
Verified signature265c752 -
Rebrand to KOS-V4; David-vs-Goliath GPT-3.5 framing; complete peer tables
Verified signature5c918b6 -
Rebrand to KOS-V4; David-vs-Goliath GPT-3.5 framing; complete peer tables
Verified signature88708fd -
Rebrand to KOS-V4; David-vs-Goliath GPT-3.5 framing; complete peer tables
Verified signature61e1232 -
Prepend shared kos-v4 family headline (data-fraction positioning)
Verified signature42d1f43 -
Prepend shared kos-v4 family headline (data-fraction positioning)
Verified signature46d3c7b -
fix family links (grounded specialists)
Verified signature509d918 -
world-class model card (specs, pretrain hp+data, SFT/RL, benchmarks, compute footprint)
Verified signature3203081 -
add model-card YAML metadata
Verified signature881ab86 -
pin torch_dtype=bfloat16
Verified signature1c1db45 -
kos-v4 initial release (private, under review)
Verified signature7e7cd29 -
initial commit
Verified signature3939c53