Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,123 @@
+---
+library_name: transformers
+base_model: AlexHung29629/FormoMouse123
+tags:
+- generated_from_trainer
+model-index:
+- name: out_1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.9.2`
+```yaml
+base_model: AlexHung29629/FormoMouse123
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: false
+liger_rms_norm: true
+liger_glu_activation: true
+liger_fused_linear_cross_entropy: true
+
+unfrozen_parameters:
+  - model.lm_head.weight
+  - model.embed_tokens.weight
+
+pretraining_dataset:
+  - path: AlexHung29629/para_pat_text
+    split: train
+    text_column: text
+    type: pretrain
+  - path: AlexHung29629/urban_dictionary
+    split: train
+    text_column: text
+    type: pretrain
+
+dataset_prepared_path: data_prep_1
+val_set_size: 0.0
+output_dir: ./out_1
+
+shuffle_merged_datasets: true
+
+sequence_len: 2048
+pretraining_sample_concatenation: true
+#sample_packing: true
+#eval_sample_packing: false
+pad_to_sequence_len: true
+
+use_tensorboard: true
+
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 2
+max_steps: 10000
+save_steps: 1000
+save_total_limit: 1
+save_only_model: true
+optimizer: ao_adamw_fp8
+lr_scheduler: cosine
+learning_rate: 2e-4
+max_grad_norm: 1.0
+
+bfloat16: true
+
+gradient_checkpointing: true
+
+logging_steps: 1
+torch_compile: false
+sdp_attention: true
+
+
+warmup_ratio: 0.1
+weight_decay: 0.1
+
+```
+
+</details><br>
+
+# out_1
+
+This model is a fine-tuned version of [AlexHung29629/FormoMouse123](https://huggingface.co/AlexHung29629/FormoMouse123) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 10000
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu128
+- Datasets 3.5.1
+- Tokenizers 0.21.1

checkpoint-10000/config.json

@@ -0,0 +1,72 @@
+{
+  "architectures": [
+    "Llama4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "floor_scale": 8192,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 1,
+  "intermediate_size": 3072,
+  "intermediate_size_mlp": 3072,
+  "max_position_embeddings": 32768,
+  "model_type": "llama4_text",
+  "moe_layers": [],
+  "no_rope_layers": [
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1
+  ],
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "num_local_experts": 16,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_qk_norm": true,
+  "vocab_size": 262145
+}

checkpoint-10000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e596259313bd096b646fbcd39bf3d5d3b469cf156774597407acc89698e185
+size 1954813416

checkpoint-10000/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
+  }
+}

checkpoint-10000/tokenizer.json

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

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67708f7ac73e25d8ee37c892a7580fd6c94c52b2236c3b88555be41bcb4d2b3
+size 6993

config.json

@@ -0,0 +1,72 @@
+{
+  "architectures": [
+    "Llama4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "floor_scale": 8192,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 1,
+  "intermediate_size": 3072,
+  "intermediate_size_mlp": 3072,
+  "max_position_embeddings": 32768,
+  "model_type": "llama4_text",
+  "moe_layers": [],
+  "no_rope_layers": [
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1
+  ],
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "num_local_experts": 16,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_qk_norm": true,
+  "vocab_size": 262145
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e596259313bd096b646fbcd39bf3d5d3b469cf156774597407acc89698e185
+size 1954813416

runs/Jun07_10-54-35_miniitx/events.out.tfevents.1749264876.miniitx.107512.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d6ae49d58959b221129ee49d80d7ab24dcee8670c69ed139a27806b44cfb68
+size 2116806

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