Upload folder using huggingface_hub

README.md

@@ -20,7 +20,7 @@ tags:
 - meta
 - pytorch
 - llama
-- llama-4
+- llama4
 extra_gated_prompt: >-
     **LLAMA 4 COMMUNITY LICENSE AGREEMENT**
 
@@ -176,7 +176,7 @@ Please, make sure you have transformers `v4.51.0` installed, or upgrade using `p
 from transformers import AutoProcessor, Llama4ForConditionalGeneration
 import torch
 
-model_id = "meta-llama/Llama-4-Maverick-17B-128E-Instruct"
+model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
 
 processor = AutoProcessor.from_pretrained(model_id)
 model = Llama4ForConditionalGeneration.from_pretrained(
@@ -269,7 +269,7 @@ In this section, we report the results for Llama 4 relative to our previous mode
 | Image Understanding | ChartQA | 0 | relaxed\_accuracy |  |  | 88.8 | 90.0 |
 |  | DocVQA (test) | 0 | anls |  |  | 94.4 | 94.4 |
 | Coding | LiveCodeBench (10/01/2024-02/01/2025) | 0 | pass@1 | 33.3 | 27.7 | 32.8 | 43.4 |
-| Reasoning & Knowledge | MMLU Pro | 0 | macro\_avg/em | 68.9 | 73.4 | 74.3 | 80.5 |
+| Reasoning & Knowledge | MMLU Pro | 0 | macro\_avg/acc | 68.9 | 73.4 | 74.3 | 80.5 |
 |  | GPQA Diamond | 0 | accuracy | 50.5 | 49.0 | 57.2 | 69.8 |
 | Multilingual | MGSM | 0 | average/em | 91.1 | 91.6 | 90.6 | 92.3 |
 | Long context | MTOB (half book) eng-\>kgv/kgv-\>eng | \- | chrF | Context window is 128K |  | 42.2/36.6 | 54.0/46.4 |

config.json

@@ -37,8 +37,8 @@
     "pad_token_id": 200018,
     "rms_norm_eps": 1e-05,
     "rope_scaling": {
-      "factor": 8.0,
-      "high_freq_factor": 4.0,
+      "factor": 16.0,
+      "high_freq_factor": 1.0,
       "low_freq_factor": 1.0,
       "original_max_position_embeddings": 8192,
       "rope_type": "llama3"

special_tokens_map.json

@@ -1,5 +1,5 @@
 {
   "bos_token": "<|begin_of_text|>",
   "eos_token": "<|eot|>",
-  "pad_token": "<|finetune_right_pad_id|>"
+  "pad_token": "<|finetune_right_pad|>"
 }

tokenizer_config.json

@@ -9071,14 +9071,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "201134": {
-      "content": "<|finetune_right_pad_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<|begin_of_text|>",
@@ -9091,7 +9083,7 @@
     "attention_mask"
   ],
   "model_max_length": 10485760,
-  "pad_token": "<|finetune_right_pad_id|>",
+  "pad_token": "<|finetune_right_pad|>",
   "processor_class": "Llama4Processor",
   "tokenizer_class": "PreTrainedTokenizer"
 }