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
Commercial IFEval AVG4 baselines: tiered Verified/Reported/Estimate list with citations
Browse files
README.md
CHANGED
|
@@ -215,20 +215,25 @@ Every model is scored on the **same standard metric, IFEval AVG4** (mean of the
|
|
| 215 |
the official IFEval implementation, `google-research/instruction_following_eval`). For open models, AVG4 is computed
|
| 216 |
identically from the archived **Open LLM Leaderboard** results (`open-llm-leaderboard/results`), and **company,
|
| 217 |
parameters, and release date are taken from `open-llm-leaderboard/contents`**. GPT-3.5-turbo is a **commercial
|
| 218 |
-
reference**
|
| 219 |
-
|
|
|
|
| 220 |
|
| 221 |
| model | company | released | params | IFEval AVG4 |
|
| 222 |
| :-- | :-- | :-- | :-- | :-- |
|
| 223 |
-
|
|
| 224 |
| Llama-3.2-3B-Instruct | Meta | Sep 2024 | 3.2B | 76.6 |
|
| 225 |
| Qwen2.5-3B-Instruct | Alibaba | Sep 2024 | 3.0B | 66.0 |
|
|
|
|
| 226 |
| Phi-3-medium-4k-instruct | Microsoft | May 2024 | 14.0B | 65.7 |
|
| 227 |
| **KOS-V4-Instruct (ours)** | **Univ. of Kentucky** | **Jul 2026** | **3.0B** | **62.7** |
|
| 228 |
| Yi-1.5-9B-Chat | 01.AI | May 2024 | 8.8B | 62.7 |
|
| 229 |
-
|
|
| 230 |
-
| *GPT-3.5-turbo* (commercial ref) | OpenAI | 2023 | 20B (est.) | 60.7 |
|
| 231 |
| Phi-3.5-mini-instruct | Microsoft | Aug 2024 | 3.8B | 60.5 |
|
|
|
|
|
|
|
|
|
|
| 232 |
| Mistral-7B-Instruct-v0.2 | Mistral AI | Dec 2023 | 7.2B | 57.5 |
|
| 233 |
| Phi-3-mini-4k-instruct | Microsoft | Apr 2024 | 3.8B | 57.1 |
|
| 234 |
| Mistral-7B-Instruct-v0.3 | Mistral AI | May 2024 | 7.2B | 56.6 |
|
|
@@ -243,12 +248,14 @@ than KOS-V4 are excluded. Calibration: our harness measures Qwen2.5-3B at AVG4 6
|
|
| 243 |
disclosed the parameter count of GPT-3.5-turbo; the roughly 20B consensus comes from leaked research documents and
|
| 244 |
industry estimates.
|
| 245 |
|
| 246 |
-
**Reading.** At **3B**, KOS-V4 (62.7) **edges the original commercial ChatGPT (GPT-3.5-turbo, 60.7)**
|
| 247 |
-
Yi-1.5, and
|
| 248 |
-
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
|
|
|
|
|
|
|
| 252 |
|
| 253 |
**Commercial baselines (IFEval AVG4, same metric as the table above).** KOS-V4's 62.7 sits at the top of the original
|
| 254 |
commercial-API tier and below the 2024 frontier. Rows are grouped by evidence quality. **Verified** = AVG4 computed
|
|
|
|
| 215 |
the official IFEval implementation, `google-research/instruction_following_eval`). For open models, AVG4 is computed
|
| 216 |
identically from the archived **Open LLM Leaderboard** results (`open-llm-leaderboard/results`), and **company,
|
| 217 |
parameters, and release date are taken from `open-llm-leaderboard/contents`**. GPT-3.5-turbo is a **commercial
|
| 218 |
+
reference** and the rows tagged **(commercial, est.)** are estimates from the tiered commercial baseline block below,
|
| 219 |
+
clearly labeled est.; **GPT-3.5-turbo (commercial ref)** uses its reported AVG4. Models smaller than KOS-V4 are
|
| 220 |
+
excluded. Calibration: our harness measures Qwen2.5-3B at AVG4 65.4 vs the leaderboard's 66.0.
|
| 221 |
|
| 222 |
| model | company | released | params | IFEval AVG4 |
|
| 223 |
| :-- | :-- | :-- | :-- | :-- |
|
| 224 |
+
| *GPT-4o-mini* (commercial, est.) | OpenAI | Jul 2024 | undisclosed | 82 (est.) |
|
| 225 |
| Llama-3.2-3B-Instruct | Meta | Sep 2024 | 3.2B | 76.6 |
|
| 226 |
| Qwen2.5-3B-Instruct | Alibaba | Sep 2024 | 3.0B | 66.0 |
|
| 227 |
+
| *Mistral-Large* (commercial, est.) | Mistral AI | Feb 2024 | undisclosed | 66 (est.) |
|
| 228 |
| Phi-3-medium-4k-instruct | Microsoft | May 2024 | 14.0B | 65.7 |
|
| 229 |
| **KOS-V4-Instruct (ours)** | **Univ. of Kentucky** | **Jul 2026** | **3.0B** | **62.7** |
|
| 230 |
| Yi-1.5-9B-Chat | 01.AI | May 2024 | 8.8B | 62.7 |
|
| 231 |
+
| *GPT-3.5-turbo-0613* (commercial, est.) | OpenAI | Jun 2023 | 20B (est.) | 61 (est.) |
|
| 232 |
+
| *GPT-3.5-turbo* (commercial ref) | OpenAI | Mar 2023 | 20B (est.) | 60.7 |
|
| 233 |
| Phi-3.5-mini-instruct | Microsoft | Aug 2024 | 3.8B | 60.5 |
|
| 234 |
+
| *Command-R* (commercial, est.) | Cohere | Mar 2024 | 35B | 60 (est.) |
|
| 235 |
+
| *Gemini-1.0-Pro* (commercial, est.) | Google | Dec 2023 | undisclosed | 58 (est.) |
|
| 236 |
+
| *Mistral-Medium* (commercial, est.) | Mistral AI | Dec 2023 | undisclosed | 58 (est.) |
|
| 237 |
| Mistral-7B-Instruct-v0.2 | Mistral AI | Dec 2023 | 7.2B | 57.5 |
|
| 238 |
| Phi-3-mini-4k-instruct | Microsoft | Apr 2024 | 3.8B | 57.1 |
|
| 239 |
| Mistral-7B-Instruct-v0.3 | Mistral AI | May 2024 | 7.2B | 56.6 |
|
|
|
|
| 248 |
disclosed the parameter count of GPT-3.5-turbo; the roughly 20B consensus comes from leaked research documents and
|
| 249 |
industry estimates.
|
| 250 |
|
| 251 |
+
**Reading.** At **3B**, KOS-V4 (62.7) **edges the original commercial ChatGPT (GPT-3.5-turbo, 60.7)** and its estimated
|
| 252 |
+
June-2023 snapshot (61), ties the 8.8B Yi-1.5, and clears the estimated commercial tier of Command-R, Gemini-1.0-Pro
|
| 253 |
+
and Mistral-Medium. It outscores every 7B-14B open instruct model below it, including both Mistral-7B-Instruct
|
| 254 |
+
releases, **Meta's Llama-3.1-8B**, Llama-2-13b-chat, gemma-1.1-7b-it, Zephyr-7B and Qwen1.5-7B. **The newest major
|
| 255 |
+
model it beats is Microsoft's Phi-3.5-mini-instruct (August 2024, 60.5).** Ahead of it sit three open models
|
| 256 |
+
(Llama-3.2-3B, Qwen2.5-3B, Phi-3-medium-14B) and two commercial estimates (GPT-4o-mini, Mistral-Large).
|
| 257 |
+
(Llama-3.1-8B's leaderboard IFEval is lower than its scores on some later evaluations; it is shown here as the archived
|
| 258 |
+
value.)
|
| 259 |
|
| 260 |
**Commercial baselines (IFEval AVG4, same metric as the table above).** KOS-V4's 62.7 sits at the top of the original
|
| 261 |
commercial-API tier and below the 2024 frontier. Rows are grouped by evidence quality. **Verified** = AVG4 computed
|