Upload tokenizer_config.json

README.md

@@ -1,248 +1,3 @@
----
-language:
-- en
-- fr
-- es
-- pt
-tags:
-- falcon3
-base_model: tiiuae/Falcon3-7B-Base
-license: other
-license_name: falcon-llm-license
-license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
-library_name: transformers
----
-
-<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-Instruct
-
-**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-Instruct**. It achieves state of art results (at the time of release) on reasoning, language understanding, instruction following, code and mathematics tasks.
-Falcon3-7B-Instruct supports 4 languages (english, french, spanish, portuguese) and a context length up to 32K.
-
-## Model Details
-- Architecture
-  - Transformer based causal decoder only architecture
-  - 28 decoder blocks
-  - Grouped query attention (GQA) for faster inference: 12 query heads and 4 key value heads
-  - Wider head dimension: 256
-  - High RoPE value to support long context understanding: 1000042
-  - Uses SwiGLU and RMSNorm
-  - 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
-- Postrained on 1.2 million samples of STEM, conversations, 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/Falcon3-7B-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.
- - We use [lm-evaluation harness](https://github.com/EleutherAI/lm-evaluation-harness).
- - We report **raw scores** obtained by applying chat template **without fewshot_as_multiturn** (unlike Llama3.1).
- - 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="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
-    </colgroup>
-    <thead>
-        <tr>
-            <th>Category</th>
-            <th>Benchmark</th>
-            <th>Llama-3.1-8B-Instruct</th>
-            <th>Qwen2.5-7B-Instruct</th>
-            <th>Falcon3-7B-Instruct</th>
-        </tr>
-    </thead>
-    <tbody>
-        <tr>
-            <td rowspan="3">General</td>
-            <td>MMLU (5-shot)</td>
-            <td>55.9</td>
-            <td><b>72.4</b></td>
-            <td>68</td>
-        </tr>
-        <tr>
-            <td>MMLU-PRO (5-shot)</td>
-            <td>21.8</td>
-            <td>35.8</td>
-            <td><b>40.7</b></td>
-        </tr>
-        <tr>
-            <td>IFEval</td>
-            <td><b>78.8</b></td>
-            <td>74.7</td>
-            <td>76.5</td>
-        </tr>
-        <tr>
-            <td rowspan="3">Math</td>
-            <td>GSM8K (5-shot)</td>
-            <td>78.1</td>
-            <td>77.5</td>
-            <td><b>79.1</b></td>
-        </tr>
-        <tr>
-            <td>GSM8K (8-shot, COT)</td>
-            <td>79.8</td>
-            <td>72.7</td>
-            <td><b>80.9</b></td>
-        </tr>
-        <tr>
-            <td>MATH Lvl-5 (4-shot)</td>
-            <td>10.4</td>
-            <td>26</td>
-            <td><b>29.4</b></td>
-        </tr>
-        <tr>
-            <td rowspan="5">Reasoning</td>
-            <td>Arc Challenge (25-shot)</td>
-            <td>46.6</td>
-            <td>55.7</td>
-            <td><b>65.9</b></td>
-        </tr>
-        <tr>
-            <td>GPQA (0-shot)</td>
-            <td><b>33.6</b></td>
-            <td>31.9</td>
-            <td>32</td>
-        </tr>
-        <tr>
-            <td>GPQA (0-shot, COT)</td>
-            <td>9.6</td>
-            <td>13.8</td>
-            <td><b>22.3</b></td>
-        </tr>
-        <tr>
-            <td>MUSR (0-shot)</td>
-            <td>38.6</td>
-            <td>40.7</td>
-            <td><b>46.4</b></td>
-        </tr>
-        <tr>
-            <td>BBH (3-shot)</td>
-            <td>43.7</td>
-            <td><b>53.9</b></td>
-            <td>52.4</td>
-        </tr>
-        <tr>
-            <td rowspan="4">CommonSense Understanding</td>
-            <td>PIQA (0-shot)</td>
-            <td><b>78.9</b></td>
-            <td>73.7</td>
-            <td>78.8</td>
-        </tr>
-        <tr>
-            <td>SciQ (0-shot)</td>
-            <td>80.2</td>
-            <td>50.9</td>
-            <td><b>94.7</b></td>
-        </tr>
-        <tr>
-            <td>Winogrande (0-shot)</td>
-            <td>-</td>
-            <td>-</td>
-            <td>70.4</td>
-        </tr>
-        <tr>
-            <td>OpenbookQA (0-shot)</td>
-            <td><b>46.2</b></td>
-            <td>42.4</td>
-            <td>45.8</td>
-        </tr>
-        <tr>
-            <td rowspan="2">Instructions following</td>
-            <td>MT-Bench (avg)</td>
-            <td>7.9</td>
-            <td><b>8.5</b></td>
-            <td>8.4</td>
-        </tr>
-        <tr>
-            <td>Alpaca (WC)</td>
-            <td>26.6</td>
-            <td><b>31.5</b></td>
-            <td>26.1</td>
-        </tr>
-        <tr>
-            <td>Tool use</td>
-            <td>BFCL AST (avg)</td>
-            <td>90.6</td>
-            <td><b>91.4</b></td>
-            <td>72.3</td>
-        </tr>
-    </tbody>
-</table>
-
-
-## Technical Report
-Coming soon....
-
-## Citation
-If Falcon3 family were helpful to your work, feel free to give us a cite.
-
-```
-@misc{Falcon3,
-    title = {The Falcon 3 family of Open Models},
-    author = {TII Team},
-    month = {December},
-    year = {2024}
-}
-```
+---
+license: apache-2.0
+---

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "Iheb-Chaabane/falcon3-7b-explore-dpo-bs-64",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,6 +10,7 @@
   "head_dim": 256,
   "hidden_act": "silu",
   "hidden_size": 3072,
+  "initializer_range": 0.02,
   "intermediate_size": 23040,
   "max_position_embeddings": 32768,
   "mlp_bias": false,
@@ -24,5 +26,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "vocab_size": 131072
+  "vocab_size": 131080
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e279c8c6075600e5dc795364efff8897de0f0c22a1d2d8db79a70adf8edb3f
-size 4938900432
+oid sha256:ada95243d59a5b8a5d60ea7bec7907ca20b92bb124d5054b51792fe059b72195
+size 4938949584

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d6600f34e9972eed3201425ba75c2d58f574655f373ea8b86ddfa37d391f2a
+oid sha256:c0f167f4dc5fb028251a03f67ce36bef07a163084fbd8f7d63ca043d770ab9ca
 size 4942085160

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96480584a0b5bd09c556e53d952146008bb423e5e12ea9bbd0b60d62f9a2f72
+oid sha256:11a6edf04d6b4ab1044d88107eb8a4c71d6378c7d232c3c668870ceae1d2a80c
 size 4224838512

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b84ea911989e21ebf4ac05018171f73016d8ae72b7904e89289be0b4672a403
-size 805306496
+oid sha256:4be476e54f6ce54be4690cb9b7241959fd2096ab9a4b97648679e1fce43c575b
+size 805355648

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14911113216
+    "total_size": 14911199232
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",

special_tokens_map.json

@@ -32,7 +32,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|pad|>",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -18212,7 +18212,16 @@
     },
     {
       "id": 2023,
-      "content": "<|pad|>",
+      "content": ">>UNUSED_1897<<",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 131072,
+      "content": "<pad>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -20280,7 +20289,7 @@
       ">>UNUSED_1894<<": 2020,
       ">>UNUSED_1895<<": 2021,
       ">>UNUSED_1896<<": 2022,
-      "<|pad|>": 2023,
+      ">>UNUSED_1897<<": 2023,
       "!": 2024,
       "\"": 2025,
       "#": 2026,

tokenizer_config.json

@@ -16186,7 +16186,15 @@
       "special": true
     },
     "2023": {
-      "content": "<|pad|>",
+      "content": ">>UNUSED_1897<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "131072": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -16219,15 +16227,11 @@
     ">>PASSWORD<<",
     ">>KEY<<"
   ],
-  "chat_template": "{% if tools %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\nYou are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the functions can be used, point it out and refuse to answer. \nIf the given question lacks the parameters required by the function, also point it out.\n\n You have access to the following tools:\n<tools>'  + tools|tojson + '</tools>\n\nThe output MUST strictly adhere to the following format, and NO other text MUST be included.\nThe example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make the tool calls an empty list [].\n<tool_call>[\n{\"name\": \"function_name1\", \"arguments\": {\"argument1\": \"value1\", \"argument2\": \"value2\"}},\n... (more tool calls as required)\n]</tool_call>' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}{% else %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}{% endif %}",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n'  + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "extra_special_tokens": {},
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
   "model_max_length": 32768,
-  "pad_token": "<|pad|>",
+  "pad_token": "<pad>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }
+