falcon3 release

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,267 @@
+---
+language:
+- en
+- fr
+- es
+- pt
+tags:
+- falcon3
+base_model: tiiuae/Falcon3-1B-Base
+license: other 
+license_name: falcon-llm-license 
+license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
+---
+
+<div align="center">
+    <img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/general/falco3-logo.png" alt="drawing" width="500"/>
+</div>
+
+# Falcon3-1B-Instruct
+
+**Falcon3** family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.
+
+This repository contains the **Falcon3-1B-Instruct**. It achieves strong results on reasoning, language understanding, instruction following, code and mathematics tasks.
+Falcon3-1B-Instruct supports 4 languages (English, French, Spanish, Portuguese) and a context length of up to 8K.
+
+## Model Details
+- Architecture
+  - Transformer-based causal decoder-only architecture
+  - 18 decoder blocks
+  - Grouped Query Attention (GQA) for faster inference: 8 query heads and 4 key-value heads
+  - Wider head dimension: 256
+  - High RoPE value to support long context understanding: 1000042
+  - Uses SwiGLU and RMSNorm
+  - 8K context length
+  - 131K vocab size
+- Pruned and healed using larger Falcon models (3B and 7B respectively) on only 80 Gigatokens of datasets comprising of web, code, STEM, high quality and multilingual data using 256 H100 GPU chips
+- Posttrained on 1.2 million samples of STEM, conversational, code, safety and function call data
+- Supports EN, FR, ES, PT
+- Developed by [Technology Innovation Institute](https://www.tii.ae)
+- License: TII Falcon-LLM License 2.0
+- Model Release Date: December 2024
+
+
+## Getting started
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "tiiuae/Falcon3-1B-Instruct"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "How many hours in one day?"
+messages = [
+    {"role": "system", "content": "You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=1024
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+```
+
+</details>
+
+<br>
+
+## Benchmarks
+We report in the following table our internal pipeline benchmarks:
+
+<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
+    <colgroup>
+        <col style="width: 10%;">
+        <col style="width: 10%;">
+        <col style="width: 7%;">
+        <col style="width: 7%;">
+        <col style="width: 7%;">
+        <col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
+    </colgroup>
+    <thead>
+        <tr>
+            <th>Category</th>
+            <th>Benchmark</th>
+            <th>Llama-3.2-1B</th>
+            <th>Qwen2.5-1.5B</th>
+            <th>SmolLM2-1.7B</th>
+            <th>Falcon3-1B-Instruct</th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td rowspan="3">General</td>
+            <td>MMLU (5-shot)</td>
+            <td>23.4</td>
+            <td><b>58.4</b></td>
+            <td>48.4</td>
+            <td>43.9</td>
+        </tr>
+        <tr>
+            <td>MMLU-PRO (5-shot)</td>
+            <td>11.3</td>
+            <td><b>21.3</b></td>
+            <td>17.2</td>
+            <td>18.6</td>
+        </tr>
+        <tr>
+            <td>IFEval</td>
+            <td><b>55.8</b></td>
+            <td>44.4</td>
+            <td>53.0</td>
+            <td>54.4</td>
+        </tr>
+        <tr>
+            <td rowspan="3">Math</td>
+            <td>GSM8K (5-shot)</td>
+            <td>37.4</td>
+            <td><b>57.2</b></td>
+            <td>43.4</td>
+            <td>38.6</td>
+        </tr>
+        <tr>
+            <td>GSM8K (8-shot, COT)</td>
+            <td>35.6</td>
+            <td><b>62.2</b></td>
+            <td>47.2</td>
+            <td>41.8</td>
+        </tr>
+        <tr>
+            <td>MATH Lvl-5 (4-shot)</td>
+            <td><b>3.9</b></td>
+            <td>0.2</td>
+            <td>0.1</td>
+            <td>1.0</td>
+        </tr>
+        <tr>
+            <td rowspan="6">Reasoning</td>
+            <td>Arc Challenge (25-shot)</td>
+            <td>34.1</td>
+            <td>47.0</td>
+            <td><b>47.6</b></td>
+            <td>45.9</td>
+        </tr>
+        <tr>
+            <td>GPQA (0-shot)</td>
+            <td>25.3</td>
+            <td><b>29.6</b></td>
+            <td>28.7</td>
+            <td>26.5</td>
+        </tr>
+        <tr>
+            <td>GPQA (0-shot, COT)</td>
+            <td>13.2</td>
+            <td>9.2</td>
+            <td>16.0</td>
+            <td><b>21.3</b></td>
+        </tr>
+        <tr>
+            <td>MUSR (0-shot)</td>
+            <td>32.4</td>
+            <td>36.8</td>
+            <td>33.0</td>
+            <td><b>40.7</b></td>
+        </tr>
+        <tr>
+            <td>BBH (3-shot)</td>
+            <td>30.3</td>
+            <td><b>38.5</b></td>
+            <td>33.1</td>
+            <td>35.1</td>
+        </tr>
+        <tr>
+            <td>BBH (3-shot, COT)</td>
+            <td>0.0</td>
+            <td>20.3</td>
+            <td>0.8</td>
+            <td><b>30.5</b></td>
+        </tr>
+        <tr>
+            <td rowspan="5">CommonSense Understanding</td>
+            <td>PIQA (0-shot)</td>
+            <td>72.1</td>
+            <td>73.2</td>
+            <td><b>74.4</b></td>
+            <td>72.0</td>
+        </tr>
+        <tr>
+            <td>SciQ (0-shot)</td>
+            <td>61.8</td>
+            <td>69.5</td>
+            <td>71.4</td>
+            <td><b>86.8</b></td>
+        </tr>
+        <tr>
+            <td>Winogrande (0-shot)</td>
+            <td>-</td>
+            <td>-</td>
+            <td>-</td>
+            <td><b>60.2</b></td>
+        </tr>
+        <tr>
+            <td>OpenbookQA (0-shot)</td>
+            <td>40.2</td>
+            <td>40.4</td>
+            <td><b>42.8</b></td>
+            <td>40.0</td>
+        </tr>
+        <tr>
+            <td>MT-Bench (avg)</td>
+            <td>5.4</td>
+            <td><b>7.1</b></td>
+            <td>6.1</td>
+            <td>5.5</td>
+        </tr>
+        <tr>
+            <td rowspan="1">Instructions following</td>
+            <td>Alpaca (WC)</td>
+            <td><b>8.6</b></td>
+            <td><b>8.6</b></td>
+            <td>5.4</td>
+            <td>6.1</td>
+        </tr>
+    </tbody>
+</table>
+
+## Useful links
+- View our [release blogpost](https://huggingface.co/blog/falcon3).
+- Feel free to join [our discord server](https://discord.gg/fwXpMyGc) if you have any questions or to interact with our researchers and developers.
+
+## Technical Report
+Coming soon....
+
+## Citation
+If the Falcon3 family of models were helpful to your work, feel free to give us a cite.
+ 
+```
+@misc{Falcon3,
+    title = {The Falcon 3 Family of Open Models},
+    url = {https://huggingface.co/blog/falcon3},
+    author = {Falcon-LLM Team},
+    month = {December},
+    year = {2024}
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 11,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000042,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f551b3271b550bfcf7c65282cdc8b3627c6ba8887e6dfa7492809f7b16cb087
+size 3338836632

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>EMAIL_ADDRESS<<",
+    ">>IP_ADDRESS<<",
+    "<|startoftext|>",
+    ">>IP_ADDRESS_0<<",
+    ">>IP_ADDRESS_1<<",
+    ">>IP_ADDRESS_2<<",
+    ">>IP_ADDRESS_3<<",
+    ">>IP_ADDRESS_4<<",
+    ">>IP_ADDRESS_5<<",
+    ">>IP_ADDRESS_6<<",
+    ">>IP_ADDRESS_7<<",
+    ">>IP_ADDRESS_8<<",
+    ">>IP_ADDRESS_9<<",
+    ">>PASSWORD<<",
+    ">>KEY<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}