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

args.json

@@ -0,0 +1,41 @@
+{
+  "batch_size": 2,
+  "accum_iter": 4,
+  "epochs": 2,
+  "warmup_epochs": 0.001,
+  "lr": 2e-05,
+  "min_lr": 2e-05,
+  "wd": 0.1,
+  "clip_grad": 4.0,
+  "init_from": "/mnt/petrelfs/xinyi/Lumina-DiMOO/output/Lumina-DiMOO-8B-Joint-Supervised-Fine-Tuning",
+  "data_config": "/mnt/petrelfs/xinyi/Lumina-DiMOO/configs/data.yaml",
+  "cache_ann_on_disk": true,
+  "length_clustering": true,
+  "num_workers": 16,
+  "pin_mem": true,
+  "seed": 0,
+  "output_dir": "output/Lumina-DiMOO-8B-Joint-Supervised-Fine-Tuning-Final",
+  "save_interval": 1,
+  "save_iteration_interval": 200,
+  "only_save_trainable": false,
+  "ckpt_max_keep": 2,
+  "auto_resume": true,
+  "resume_path": null,
+  "model_parallel_size": 1,
+  "data_parallel": "sdp",
+  "precision": "bf16",
+  "grad_precision": "fp32",
+  "checkpointing": false,
+  "max_seq_len": 5120,
+  "mask_image_logits": false,
+  "dropout": 0.05,
+  "z_loss_weight": 1e-05,
+  "model_size": "7B",
+  "world_size": 48,
+  "rank": 0,
+  "gpu": 0,
+  "local_rank": 0,
+  "dist_url": "env://",
+  "distributed": true,
+  "dist_backend": "nccl"
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "/mnt/petrelfs/xinyi/Lumina-DiMOO/output/Lumina-DiMOO-8B-Joint-Supervised-Fine-Tuning",
+  "activation_type": "silu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "architectures": [
+    "LLaDAForMultiModalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_layer_norm": false,
+  "attention_layer_norm_with_affine": true,
+  "auto_map": {
+    "AutoConfig": "configuration_llada.LLaDAConfig",
+    "AutoModel": "modeling_llada.LLaDAModelLM",
+    "AutoModelForCausalLM": "modeling_llada.LLaDAModelLM"
+  },
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "llama",
+  "d_model": 4096,
+  "embedding_dropout": 0.0,
+  "embedding_size": 134548,
+  "eos_token_id": 126081,
+  "flash_attention": false,
+  "include_bias": false,
+  "include_qkv_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "meta",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "input_emb_norm": false,
+  "layer_norm_type": "rms",
+  "layer_norm_with_affine": true,
+  "mask_token_id": 126336,
+  "max_sequence_length": 4096,
+  "mlp_hidden_size": 12288,
+  "mlp_ratio": 4,
+  "model_type": "llada",
+  "multi_query_attention": null,
+  "n_heads": 32,
+  "n_kv_heads": 32,
+  "n_layers": 32,
+  "pad_token_id": 126081,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope": true,
+  "rope_full_precision": true,
+  "rope_theta": 500000.0,
+  "scale_logits": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "vocab_size": 134548,
+  "weight_tying": false
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 126080,
+  "eos_token_id": 126081,
+  "transformers_version": "4.46.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9df75e5cb0e4fe6bb8d9d7c8b9bda7832fb174a49962b85ac0d4cd30f6273d5
+size 4927587832

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86dc41287d14eb36093cfbdb25441dc0075d8481cf2a261291c8b2f1cd6a5a72
+size 4932693832

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55539ec412c4d0f61305646cdf64d68b890d4f86be9a06b74e0a63318ef26abb
+size 4999819560

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27100ef7fcde2ac7a15a3a7eb116eecc182b7207a14f199b12a19571b8e3314
+size 1303544192

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16163610624
+  },
+  "weight_map": {
+    "model.transformer.blocks.0.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.10.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.2.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.20.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.3.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.30.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_proj.weight": "model-00004-of-00004.safetensors",
+    "model.transformer.blocks.31.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.transformer.blocks.31.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.4.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.8.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.9.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.ff_out.weight": "model-00004-of-00004.safetensors",
+    "model.transformer.ln_f.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.wte.weight": "model-00001-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    "<|mdm_mask|>",
+    "<role>",
+    "</role>",
+    "<|arithmetic_start|>",
+    "<|arithmetic_end|>",
+    "<|number_start|>",
+    "<|number_end|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "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:d1e30dd1588d25682e78c74a57bc775173cc34f85f991385602812a2d498fc7d
+size 11287999