Upload folder using huggingface_hub

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 262272
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159720082fa6d2192b3844b8de0f9aceddc5f1c93c86aa3b47d65660d3bd3790
+size 4295753374

results_2025-11-10T14-37-30.649691.json

@@ -0,0 +1,126 @@
+{
+  "config_general": {
+    "lighteval_sha": "?",
+    "num_fewshot_seeds": 1,
+    "max_samples": null,
+    "job_id": 0,
+    "start_time": 7279654.007121416,
+    "end_time": 7279821.151050477,
+    "total_evaluation_time_secondes": "167.14392906147987",
+    "model_name": "/scratch/project_462000353/mikakois/multisynt/train/nemotron-cc-translated-100B-opus-mt-ron/hf_ckpts/checkpoint_0047684/",
+    "model_sha": "",
+    "model_dtype": null,
+    "model_size": "8.0 GB",
+    "generation_parameters": {
+      "early_stopping": null,
+      "repetition_penalty": null,
+      "frequency_penalty": null,
+      "length_penalty": null,
+      "presence_penalty": null,
+      "max_new_tokens": null,
+      "min_new_tokens": null,
+      "seed": null,
+      "stop_tokens": null,
+      "temperature": null,
+      "top_k": null,
+      "min_p": null,
+      "top_p": null,
+      "truncate_prompt": null,
+      "response_format": null
+    }
+  },
+  "results": {
+    "lighteval|belebele_ron_Latn_cf|0": {
+      "acc_norm_token": 0.3688888888888889,
+      "acc_norm_token_stderr": 0.016092401309766666,
+      "acc_norm": 0.3933333333333333,
+      "acc_norm_stderr": 0.016292044853162806
+    },
+    "all": {
+      "acc_norm_token": 0.3688888888888889,
+      "acc_norm_token_stderr": 0.016092401309766666,
+      "acc_norm": 0.3933333333333333,
+      "acc_norm_stderr": 0.016292044853162806
+    }
+  },
+  "versions": {
+    "lighteval|belebele_ron_Latn_cf|0": 0
+  },
+  "config_tasks": {
+    "lighteval|belebele_ron_Latn_cf": {
+      "name": "belebele_ron_Latn_cf",
+      "prompt_function": "prompt_fn",
+      "hf_repo": "facebook/belebele",
+      "hf_subset": "ron_Latn",
+      "metric": [
+        {
+          "metric_name": "acc_norm_token",
+          "higher_is_better": true,
+          "category": "8",
+          "use_case": "1",
+          "sample_level_fn": "compute",
+          "corpus_level_fn": "mean"
+        },
+        {
+          "metric_name": "acc_norm",
+          "higher_is_better": true,
+          "category": "8",
+          "use_case": "1",
+          "sample_level_fn": "compute",
+          "corpus_level_fn": "mean"
+        }
+      ],
+      "hf_revision": null,
+      "hf_filter": null,
+      "hf_avail_splits": [
+        "test"
+      ],
+      "trust_dataset": false,
+      "evaluation_splits": [
+        "test"
+      ],
+      "few_shots_split": null,
+      "few_shots_select": null,
+      "generation_size": null,
+      "generation_grammar": null,
+      "stop_sequence": [],
+      "num_samples": null,
+      "suite": [
+        "lighteval"
+      ],
+      "original_num_docs": 900,
+      "effective_num_docs": 900,
+      "must_remove_duplicate_docs": false,
+      "version": 0
+    }
+  },
+  "summary_tasks": {
+    "lighteval|belebele_ron_Latn_cf|0": {
+      "hashes": {
+        "hash_examples": "fef451071a0c7023",
+        "hash_full_prompts": "fef451071a0c7023",
+        "hash_input_tokens": "426394cbb19d2c9e",
+        "hash_cont_tokens": "11a0dd41ada83637"
+      },
+      "truncated": 0,
+      "non_truncated": 900,
+      "padded": 3559,
+      "non_padded": 41,
+      "effective_few_shots": 0.0,
+      "num_truncated_few_shots": 0
+    }
+  },
+  "summary_general": {
+    "hashes": {
+      "hash_examples": "e3f9cbae7ab205cf",
+      "hash_full_prompts": "e3f9cbae7ab205cf",
+      "hash_input_tokens": "e6c9d0ee713f4c1b",
+      "hash_cont_tokens": "56068b4a890645a4"
+    },
+    "truncated": 0,
+    "non_truncated": 900,
+    "padded": 3559,
+    "non_padded": 41,
+    "num_truncated_few_shots": 0
+  }
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074