Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+model.onnx.data filter=lfs diff=lfs merge=lfs -text

ConvertOnnx.py

@@ -0,0 +1,32 @@
+# /// script
+# requires-python = ">=3.12"
+# dependencies = [
+#     "onnx-ir",
+#     "onnxruntime-genai",
+#     "torch",
+#     "tqdm>=4.67.1",
+#     "transformers>=5.0.0",
+# ]
+# optional-dependencies = { cuda = [
+#     "torch==2.2.*+cu121",
+#     "onnxruntime-genai-cuda",
+#   ] }
+# ///
+from onnxruntime_genai.models.builder import create_model
+import os
+choices=["int4", "bf16", "fp16", "fp32"]
+choices=["cpu", "cuda", "dml", "webgpu", "NvTensorRtRtx"]
+
+from huggingface_hub import snapshot_download
+model_path = snapshot_download("tiiuae/Falcon3-7B-Base",local_dir="/teamspace/studios/this_studio/model")
+
+create_model(model_name=model_path,
+             input_path=model_path,
+             output_dir="onnx",
+             precision="fp16",
+             execution_provider="cpu",
+             cache_dir=os.path.join(os.getcwd(), "model_cache"),
+             extra_options={ "hf_token": os.getenv("hf", "true")})
+
+
+

README.md

@@ -0,0 +1,230 @@
+---
+language:
+- en
+- fr
+- es
+- pt
+tags:
+- falcon3
+- onnx
+- onnxruntime-genai
+license: other
+license_name: falcon-llm-license
+license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
+library_name: onnxruntime-genai
+base_model:
+- tiiuae/Falcon3-7B-Base
+---
+
+<div align="center">
+    <img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/general/falco3-logo.png" alt="drawing" width="500"/>
+</div>
+
+# Falcon3-7B-Base
+
+**Falcon3** family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B.
+
+This repository contains the **Falcon3-7B-Base**. It achieves state of art results (at the time of release) on reasoning, language understanding, instruction following, code and mathematics tasks.
+Falcon3-7B-Base supports 4 languages (english, french, spanish, portuguese) and a context length up to 32K.
+
+⚠️ **This is a raw, pretrained model, which should be further finetuned for most usecases.** 
+
+## Model Details
+- Architecture
+  - transformer based causal decoder only architecture
+  - 28 decoder blocks
+  - grouped query attention (GQA) for faster inference: 12 query heads and 4 KV heads
+  - wider head dimension: 256
+  - high RoPE value to support long context understanding: 1000042
+  - 32k context length
+  - 131k vocab size
+- Pretrained on 14 Teratokens of datasets comprising of web, code, STEM, high quality and mutlilingual data using 1024 H100 GPU chips
+- 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
+import torch
+from transformers import pipeline
+
+pipe = pipeline(
+    "text-generation", 
+    model="tiiuae/Falcon3-7B-Base", 
+    torch_dtype=torch.bfloat16, 
+    device_map="auto"
+)
+response = pipe("Question: How many hours in one day? Answer: ")
+print(response[0]['generated_text'])
+```
+
+</details>
+
+<br>
+
+## Benchmarks
+We report in the following table our internal pipeline benchmarks.
+ - We use [lm-evaluation harness](https://github.com/EleutherAI/lm-evaluation-harness).
+ - We report **raw scores**.
+ - We use same batch-size across all models.
+
+
+
+<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="width: 7%;">
+        <col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
+    </colgroup>
+    <thead>
+        <tr>
+            <th>Category</th>
+            <th>Benchmark</th>
+            <th>Llama3.1-8B</th>
+            <th>Qwen2-7B</th>
+            <th>Qwen2.5-7B</th>
+            <th>gemma-2-9b</th>
+            <th>Falcon3-7B-Base</th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td rowspan="3">General</td>
+            <td>MMLU (5-shot)</td>
+            <td>65.2</td>
+            <td>70.4</td>
+            <td>74.2</td>
+            <td>-</td>
+            <td>67.5</td>
+        </tr>
+        <tr>
+            <td>MMLU-PRO (5-shot)</td>
+            <td>32.7</td>
+            <td>42.1</td>
+            <td>43.5</td>
+            <td>-</td>
+            <td>39.2</td>
+        </tr>
+        <tr>
+            <td>IFEval</td>
+            <td>12.0</td>
+            <td>30.6</td>
+            <td>33.9</td>
+            <td>-</td>
+            <td>34.3</td>
+        </tr>
+        <tr>
+            <td rowspan="2">Math</td>
+            <td>GSM8K (5-shot)</td>
+            <td>49.4</td>
+            <td>77.9</td>
+            <td>82.9</td>
+            <td>-</td>
+            <td>76.2</td>
+        </tr>
+        <tr>
+            <td>MATH(4-shot)</td>
+            <td>4.1</td>
+            <td>17.5</td>
+            <td>15.5</td>
+            <td>-</td>
+            <td>18.0</td>
+        </tr>
+        <tr>
+            <td rowspan="4">Reasoning</td>
+            <td>Arc Challenge (25-shot)</td>
+            <td>53.4</td>
+            <td>57.4</td>
+            <td>59.0</td>
+            <td>-</td>
+            <td>59.6</td>
+        </tr>
+        <tr>
+            <td>GPQA (0-shot)</td>
+            <td>31.0</td>
+            <td>31.9</td>
+            <td>33.0</td>
+            <td>-</td>
+            <td>35.5</td>
+        </tr>
+        <tr>
+            <td>MUSR (0-shot)</td>
+            <td>38.0</td>
+            <td>44.1</td>
+            <td>44.2</td>
+            <td>-</td>
+            <td>47.3</td>
+        </tr>
+        <tr>
+            <td>BBH (3-shot)</td>
+            <td>46.5</td>
+            <td>53.3</td>
+            <td>54.0</td>
+            <td>-</td>
+            <td>51.0</td>
+        </tr>
+        <tr>
+            <td rowspan="4">CommonSense Understanding</td>
+            <td>PIQA (0-shot)</td>
+            <td>80.3</td>
+            <td>79.8</td>
+            <td>78.7</td>
+            <td>-</td>
+            <td>77.7</td>
+        </tr>
+        <tr>
+            <td>SciQ (0-shot)</td>
+            <td>96.3</td>
+            <td>95.9</td>
+            <td>96.6</td>
+            <td>-</td>
+            <td>95.3</td>
+        </tr>
+        <tr>
+            <td>Winogrande (0-shot)</td>
+            <td>74.0</td>
+            <td>72.1</td>
+            <td>72.9</td>
+            <td>-</td>
+            <td>71.0</td>
+        </tr>
+        <tr>
+            <td>OpenbookQA (0-shot)</td>
+            <td>33.4</td>
+            <td>35.2</td>
+            <td>33.6</td>
+            <td>-</td>
+            <td>31.4</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 Falcon3 family were helpful to your work, feel free to give us a cite.
+
+```
+@misc{Falcon3,
+    title = {Falcon 3 family of Open Foundation Models},
+    author = {TII Team},
+    month = {December},
+    year = {2024}
+}
+```

genai_config.json

@@ -0,0 +1,50 @@
+{
+    "model": {
+        "bos_token_id": 11,
+        "context_length": 32768,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": []
+            },
+            "filename": "model.onnx",
+            "head_size": 256,
+            "hidden_size": 3072,
+            "inputs": {
+                "input_ids": "input_ids",
+                "attention_mask": "attention_mask",
+                "position_ids": "position_ids",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 12,
+            "num_hidden_layers": 28,
+            "num_key_value_heads": 4
+        },
+        "eos_token_id": 11,
+        "pad_token_id": 11,
+        "type": "llama",
+        "vocab_size": 131072
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": null,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 32768,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": false,
+        "repetition_penalty": 1.0,
+        "temperature": null,
+        "top_k": null,
+        "top_p": null
+    }
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0aec238f20910c50a3109345c38fb3a232f847ec2a9f4b427e2c6e9e76a7a9
+size 656606

model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e82bab3cb51ded6663ee418f2ac5e69775745521a7db8af152ffe55dd4d4453
+size 14927921152

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_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<<"
+  ],
+  "is_local": true,
+  "model_max_length": 32768,
+  "tokenizer_class": "TokenizersBackend"
+}