Upload folder using huggingface_hub

pt-m-llada-gpt2-355M_fineweb20b_24h/checkpoint-64800/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|mdm_mask|>": 50257
+}

pt-m-llada-gpt2-355M_fineweb20b_24h/checkpoint-64800/chat_template.jinja

@@ -0,0 +1,11 @@
+{% set loop_messages = messages %}
+{% for message in loop_messages %}
+{% if loop.index0 == 0 %}{{ bos_token }}{% endif %}
+<|start_header_id|>{{ message['role'] }}<|end_header_id|>
+
+{{ message['content'] | trim }}<|eot_id|>
+{%- endfor %}
+{% if add_generation_prompt and (loop_messages | length == 0 or loop_messages[-1]['role'] != 'assistant') %}
+<|start_header_id|>assistant<|end_header_id|>
+
+{% endif %}

pt-m-llada-gpt2-355M_fineweb20b_24h/checkpoint-64800/config.json

@@ -0,0 +1,57 @@
+{
+  "activation_type": "silu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "architectures": [
+    "LLaDAModelLM"
+  ],
+  "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",
+  "bos_token_id": 50256,
+  "d_model": 1024,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "embedding_size": 50304,
+  "eos_token_id": 50256,
+  "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": 50257,
+  "max_sequence_length": 4096,
+  "mlp_hidden_size": 4096,
+  "mlp_ratio": 4,
+  "model_type": "llada",
+  "multi_query_attention": null,
+  "n_experts": null,
+  "n_heads": 16,
+  "n_kv_heads": 16,
+  "n_layers": 15,
+  "pad_token_id": 50256,
+  "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,
+  "transformers_version": "4.57.0",
+  "use_cache": false,
+  "vocab_size": 50304,
+  "weight_tying": false
+}

pt-m-llada-gpt2-355M_fineweb20b_24h/checkpoint-64800/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.57.0",
+  "use_cache": false
+}

pt-m-llada-gpt2-355M_fineweb20b_24h/checkpoint-64800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17aacfa9bca8484e7138fda4c66ccf284c30ee9f16106b49b45bc2046eaa1f15
+size 709441248

pt-m-llada-gpt2-355M_fineweb20b_24h/checkpoint-64800/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<|mdm_mask|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

pt-m-llada-gpt2-355M_fineweb20b_24h/checkpoint-64800/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|mdm_mask|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "mask_token": "<|mdm_mask|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

pt-m-llada-gpt2-355M_fineweb20b_24h/checkpoint-64800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c909bcb4a0c7b508698507a09e4b0a61471fdfd695ebc4b047b423496c01119e
+size 6161