Update README.md (#8)

- Update README.md (2bbe448b850e983a400c833a636f977a0af79e3a)

README.md

@@ -1,4 +1,3 @@
-
 ---
 license: apache-2.0
 language:
@@ -7,20 +6,17 @@ language:
 
 # **K2-V2**
 
-📚 [Tech Report](https://www.llm360.ai/reports/K2_V2_report.pdf ) - 📝 [Code](github_url) - 🏢 [Project Page](https://huggingface.co/LLM360/K2-V2)
-
-<img src="figures/banner.png" alt="k2-banner-placeholder"/>
-
-<br>
+<img src="figures/K2.LOGO.PRIMARY.RGB.png" width="100" alt="K2-V2 model logo"/>
 
-K2-V2 is our best fully open source model to date and ranked among the best open weight models of its class. As the latest base model in the LLM360's strongest project family, K2 features a dense architecture with 70 billion parameters. 
+📚 [Tech Report](https://www.llm360.ai/reports/K2_V2_report.pdf) - 📝 [Code](https://github.com/llm360/k2v2_train) - 🏢 [Project Page](https://huggingface.co/LLM360/K2-V2) 
 
-<img src="figures/sft-models.png" width="400" alt="k2-sft-aime"/>
+K2-V2 is our most capable fully open model to date, and one of the strongest open-weight models in its class. It uses a 70B-parameter dense transformer architecture and represents the latest advancement in the LLM360 model family.
 
-Beyond standard competencies like knowledge and conversation, K2 provides advanced capabilities, including long context consistency, deep mathematical knowledge, and reasoning behaviors. These serve as foundational building blocks that enable sophisticated downstream use cases, such as solving complex math problems and executing agentic workflows.
+<img src="figures/sft-models.png" width="400" alt="K2-V2 SFT results"/>
 
+Beyond standard competencies such as factual knowledge and conversational ability, K2-V2 demonstrates strong long-context consistency, deep mathematical understanding, and robust reasoning skills. These capabilities serve as building blocks for sophisticated downstream applications, such as solving complex math problems and executing agentic workflows.
 
-<img src="figures/base-models.png" width="400" alt="k2-base-gpqa"/>
+<img src="figures/base-models.png" width="400" alt="K2-V2 GPQA results"/>
 
 ---
 
@@ -29,8 +25,8 @@ Beyond standard competencies like knowledge and conversation, K2 provides advanc
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("llm360/k2-v2", device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained("llm360/k2-v2")
+model = AutoModelForCausalLM.from_pretrained("LLM360/K2-V2", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("LLM360/K2-V2")
 
 prompt = "Explain why the derivative of sin(x) is cos(x)."
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
@@ -42,11 +38,10 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ## **Evaluation Summary**
 
+Below we report performance across general, reasoning, mathematical, and coding benchmarks. Scores for K2-V2 checkpoints (base → mid-4) demonstrate the impact of staged mid-training on reasoning quality.
+
 | Task / Model | base | mid-1 | mid-2 | mid-3 | mid-4 | Qwen2.5-72B | Llama3.0-70B | Llama3.1-70B | Olmo3-32B |
 |--------------|------|-------|-------|-------|-------|--------------|---------------|---------------|------------|
-| **Architecture** | Dense | Dense | Dense | Dense | Dense | Dense | Dense | Dense | Dense |
-| **# Total Params** | 70B | 70B | 70B | 70B | 70B | 72B | 70B | 70B | 32B |
-| **# Activated Params** | 70B | 70B | 70B | 70B | 70B | 72B | 70B | 70B | 32B |
 | **General Tasks** | | | | | | | | | |
 | **MMLU** | 74.3 | 74.4 | 73.5 | 75.0 | 75.2 | **86.1** | <u>79.5</u> | 79.3 | 75.2 |
 | **MMLU-Pro** | 43.7 | 46.8 | 48.1 | **59.8** | 57.0 | <u>58.1</u> | 52.8 | 53.8 | 49.6 |
@@ -64,30 +59,20 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 | **Coding Tasks** | | | | | | | | | |
 | **MBPP** | 57.6 | 57.8 | 58.2 | 59.8 | 61.8 | **75.4** | <u>69.2</u> | 64.4 | 60.2 |
 | **HUMANEVAL** | 50.0 | 51.2 | <u>53.7</u> | **54.3** | **54.3** | **54.3** | 42.1 | 50.6 | 36.0 |
-| **Logic Puzzles** | | | | | | | | | |
-| **COUNTDOWN** | 1.3 | <u>53.3</u> | 53.1 | 35.9 | **75.6** | 6.0 | 1.0 | 0.5 | 23.2 |
-| **KK-4 PEOPLE** | 4.8 | 44.9 | <u>68.0</u> | 64.5 | **92.9** | 26.1 | 4.2 | 7.6 | 42.4 |
-| **KK-8 PEOPLE** | 0.5 | 23.2 | 41.3 | <u>51.6</u> | **82.8** | 5.7 | 1.1 | 1.3 | 13.0 |
-| **ORDER-15 ITEMS** | 4.7 | 30.7 | 47.2 | <u>55.8</u> | **87.6** | 37.0 | 3.5 | 4.5 | 25.0 |
-| **ORDER-30 ITEMS** | 0.0 | 0.3 | 3.0 | <u>34.1</u> | **40.3** | 0.7 | 0.2 | 0.1 | 0.6 |
-| **Instruction Following** | | | | | | | | | |
-| **IFEVAL** | 17.4 | 26.2 | 28.5 | <u>34.5</u> | 26.7 | **40.3** | 15.1 | 17.4 | 13.2 |
-| **Arabic** | | | | | | | | | |
-| **MMLU-Arabic** | 65.4 | 66.1 | 64.5 | 66.6 | 65.5 | **74.1** | 65.0 | <u>66.8</u> | 47.8 |
 
 
-Please refer to our [Tech Report](arxiv_url) for detailed evaluation results.
+Please refer to our [Tech Report](https://www.llm360.ai/reports/K2_V2_report.pdf) for detailed evaluation results.
 
 ---
 
 ## **Datasets & Mixtures**
 
-K2 training is organized into three stages, each using a transparent, publicly released mixture:
+K2-V2 training is organized into three stages, each using a transparent, publicly released mixture:
 
 ### **Pretraining Mix**
 
-* Large-scale natural text corpus (web, books, code, multilingual)
-* Balanced mixture optimized for stable scaling and broad knowledge
+* Large-scale natural text corpus spanning web content, books, code, and multilingual sources
+* Mixture designed for stable scaling and broad general-knowledge coverage
 * ~12T tokens
 
 ### **Mid-Training Mix**
@@ -102,10 +87,13 @@ K2 training is organized into three stages, each using a transparent, publicly r
 
 All mixtures, filtering rules, and data sources are fully released for reproducibility.
 
+Please refer to our [Tech Report](https://www.llm360.ai/reports/K2_V2_report.pdf) for detailed datasets and mixtures information.
+
 ---
 
 ## **Model Description**
-- **Model type:** Language model with transformer architecture
+- **Model type:** K2-V2 follows a standard decoder-only transformer with grouped-query attention and RMSNorm.
+- **Training stage:** Pre-training
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
 
@@ -114,22 +102,46 @@ All mixtures, filtering rules, and data sources are fully released for reproduci
 | ----------- | ----------- |
 | Total Parameters      | 70B       |
 | Hidden Size   | 8,192        |
-| Intermediate Size (MLPs)   | 28,672        |
+| Intermediate Size (FFN)   | 28,672        |
 | Number of Attention Heads   | 64        |
-| Number of Hidden Layers  | 80        |
-| RMSNorm ɛ  | 1e^-5        |
-| Max Pre-training Seq Length   | 8,192        |
+| Number of Layers  | 80        |
+| RMSNorm ɛ  | 1e-5        |
+| Pre-training Seq Length   | 8,192        |
 | Max Mid-training Seq Length   | 524,288        |
 | Vocab Size | 250,000 |
 
+
+---
+
+## **Intended Use**
+
+K2-V2 is designed for:
+
+* research on large language models and reasoning
+* downstream fine-tuning (e.g., instruction following, agents, domain models)
+* experimentation with long-context architectures
+* open, transparent benchmarking of LLM scaling
+
+K2-V2 is **not** instruction-tuned. For aligned conversational use, please see **K2-V2-Instruct**.
+
 ---
 
-## Citation & Acknowledgment
+## **Limitations**
 
-If you use our dataset in your research, please cite our [K2-V2 paper](LINK):
+* May generate incorrect or hallucinated content, especially when asked about facts not seen during training
+* Not optimized for safety, moderation, or refusal behavior (base model)
+* Long-context performance depends on prompt quality and retrieval structure
+* Primarily trained on English; multilingual capabilities are limited
+* Inference cost is high due to the 70B parameter size
+
+---
+
+## Citation
+
+If you use K2-V2 in your research, please cite the following:
 
 ```
-@misc{llm360@k2v2,
+@misc{llm360_k2v2_2025,
   title         = {K2-V2: A 360-Open, Reasoning-Enhanced Open Foundation Model},
   author        = {K2 Team},
   year          = {2025},
@@ -138,5 +150,3 @@ If you use our dataset in your research, please cite our [K2-V2 paper](LINK):
   primaryClass  = {cs.CL}
 }
 ```
-
-