Create README.md

README.md

@@ -0,0 +1,137 @@
+---
+library_name: transformers
+tags:
+- falcon-h1
+license: other
+license_name: falcon-llm-license
+license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
+---
+
+#  Table of Contents
+
+0. [TL;DR](#TL;DR)
+1. [Model Details](#model-details)
+2. [Training Details](#training-details)
+3. [Usage](#usage)
+4. [Evaluation](#evaluation)
+5. [Citation](#citation)
+
+# TL;DR
+
+# Model Details
+
+## Model Description
+
+- **Developed by:** [https://www.tii.ae](https://www.tii.ae)
+- **Model type:** Causal decoder-only
+- **Architecture:** Hybrid Transformers + Mamba architecture
+- **Language(s) (NLP):** English, Multilingual
+- **License:** Falcon-LLM License
+
+# Training details
+
+For more details about the training protocol of this model, please refer to the [Falcon-H1 technical blogpost](https://falcon-lm.github.io/blog/falcon-h1/).
+
+# Usage
+
+Currently to use this model you can either rely on Hugging Face `transformers`, `vLLM` or our custom fork of `llama.cpp` library.
+
+## Inference
+
+Make sure to install the latest version of `transformers` or `vllm`, eventually install these packages from source:
+
+```bash
+pip install git+https://github.com/huggingface/transformers.git
+```
+
+Refer to [the official vLLM documentation for more details on building vLLM from source](https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html#build-wheel-from-source).
+
+### 🤗 transformers
+
+Refer to the snippet below to run H1 models using 🤗 transformers:
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "tiiuae/Falcon-H1-1B-Base"
+
+model = AutoModelForCausalLM.from_pretrained(
+  model_id,
+  torch_dtype=torch.bfloat16,
+  device_map="auto"
+)
+
+# Perform text generation
+```
+
+### vLLM
+
+For vLLM, simply start a server by executing the command below:
+
+```
+# pip install vllm
+vllm serve tiiuae/Falcon-H1-1B-Instruct --tensor-parallel-size 2 --data-parallel-size 1
+```
+
+### `llama.cpp`
+
+While we are working on integrating our architecture directly into `llama.cpp` library, you can install our fork of the library and use it directly: https://github.com/tiiuae/llama.cpp-Falcon-H1 
+Use the same installing guidelines as `llama.cpp`.
+
+# Evaluation
+
+Falcon-H1 series perform very well on a variety of tasks, including reasoning tasks. 
+
+| Tasks | Falcon-H1-1.5B | Qwen3-1.7B | Qwen2.5-1.5B | Gemma3-1B | Llama3.2-1B | Falcon3-1B |
+| --- | --- | --- | --- | --- | --- | --- |
+| **General**  | | | | | |
+| BBH | **46.47** | 35.18 | 42.41 | 35.86 | 33.21 | 34.47 |
+| ARC-C | 42.06 | 34.81 | 40.53 | 34.13 | 34.64 | **43.09** |
+| TruthfulQA | 45.98 | **49.39** | 47.05 | 42.17 | 42.08 | 42.31 |
+| HellaSwag | **63.33** | 49.27 | 62.23 | 42.24 | 55.3 | 58.53 |
+| MMLU | **62.03** | 57.04 | 59.76 | 40.87 | 45.93 | 46.1 |
+| **Math**  | | | | | |
+| GSM8k | **74.98** | 69.83 | 57.47 | 42.38 | 44.28 | 44.05 |
+| MATH-500 | **74.0** | 73.0 | 48.4 | 45.4 | 13.2 | 19.8 |
+| AMC-23 | 43.59 | **46.09** | 24.06 | 19.22 | 7.19 | 6.87 |
+| AIME-24 | 11.25 | **12.5** | 2.29 | 0.42 | 1.46 | 0.41 |
+| AIME-25 | **9.58** | 8.12 | 1.25 | 1.25 | 0.0 | 0.21 |
+| **Science**  | | | | | |
+| GPQA | 26.34 | 27.68 | 26.26 | **28.19** | 26.59 | 26.76 |
+| GPQA_Diamond | **35.19** | 33.33 | 25.59 | 21.55 | 25.08 | 31.31 |
+| MMLU-Pro | **37.8** | 23.54 | 28.35 | 14.46 | 16.2 | 18.49 |
+| MMLU-stem | **64.13** | 54.3 | 54.04 | 35.39 | 39.16 | 39.64 |
+| **Code**  | | | | | |
+| HumanEval | **68.29** | 67.68 | 56.1 | 40.85 | 34.15 | 22.56 |
+| HumanEval+ | **61.59** | 60.96 | 50.61 | 37.2 | 29.88 | 20.73 |
+| MBPP | **64.81** | 58.73 | **64.81** | 57.67 | 33.6 | 20.63 |
+| MBPP+ | **56.35** | 49.74 | 56.08 | 50.0 | 29.37 | 17.2 |
+| LiveCodeBench | **17.61** | 14.87 | 12.52 | 5.09 | 2.35 | 0.78 |
+| CRUXEval | **39.57** | 18.88 | 34.76 | 12.7 | 0.06 | 15.58 |
+| **Instruction Following**  | | | | | |
+| IFEval | **80.66** | 70.77 | 45.33 | 61.48 | 55.34 | 54.26 |
+| Alpaca-Eval | **28.18** | 21.89 | 9.54 | 17.87 | 9.38 | 6.98 |
+| MTBench | **8.46** | 7.61 | 7.1 | 7.03 | 6.37 | 6.03 |
+| LiveBench | 34.13 | **40.73** | 21.65 | 18.79 | 14.97 | 14.1 |
+
+You can check more in detail on our [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1/), detailed benchmarks.
+
+# Useful links
+
+- View [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1/).
+- Feel free to join [our discord server](https://discord.gg/fwXpMyGc) if you have any questions or to interact with our researchers and developers.
+
+# Citation
+
+If the Falcon-H1 family of models were helpful to your work, feel free to give us a cite.
+
+```
+@misc{tiifalconh1,
+    title = {Falcon-H1},
+    author = {Falcon-LLM Team},
+    month = {May},
+    url = {https://falcon-lm.github.io/blog/falcon-h1},
+    year = {2025}
+}
+```