Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +6 -0
- README.md +58 -0
- adapter_config.json +461 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- all_results.json +9 -0
- chat_template.json +3 -0
- checkpoint-100/README.md +202 -0
- checkpoint-100/adapter_config.json +461 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/added_tokens.json +3 -0
- checkpoint-100/chat_template.json +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/preprocessor_config.json +29 -0
- checkpoint-100/processor_config.json +4 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +42 -0
- checkpoint-100/tokenizer.json +3 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +0 -0
- checkpoint-100/trainer_state.json +194 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/README.md +202 -0
- checkpoint-200/adapter_config.json +461 -0
- checkpoint-200/adapter_model.safetensors +3 -0
- checkpoint-200/added_tokens.json +3 -0
- checkpoint-200/chat_template.json +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/preprocessor_config.json +29 -0
- checkpoint-200/processor_config.json +4 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +42 -0
- checkpoint-200/tokenizer.json +3 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +0 -0
- checkpoint-200/trainer_state.json +354 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/README.md +202 -0
- checkpoint-300/adapter_config.json +461 -0
- checkpoint-300/adapter_model.safetensors +3 -0
- checkpoint-300/added_tokens.json +3 -0
- checkpoint-300/chat_template.json +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/preprocessor_config.json +29 -0
- checkpoint-300/processor_config.json +4 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +42 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
checkpoint-480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: google/gemma-3-27b-it
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: gemma4
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# gemma4
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it) on the ets480 dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- num_epochs: 8.0
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
### Framework versions
|
| 53 |
+
|
| 54 |
+
- PEFT 0.12.0
|
| 55 |
+
- Transformers 4.50.0
|
| 56 |
+
- Pytorch 2.6.0+cu124
|
| 57 |
+
- Datasets 3.3.2
|
| 58 |
+
- Tokenizers 0.21.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-27b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"language_model.model.layers.42.self_attn.q_proj",
|
| 24 |
+
"language_model.model.layers.51.mlp.up_proj",
|
| 25 |
+
"language_model.model.layers.51.mlp.down_proj",
|
| 26 |
+
"language_model.model.layers.30.mlp.up_proj",
|
| 27 |
+
"language_model.model.layers.47.self_attn.q_proj",
|
| 28 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
| 29 |
+
"language_model.model.layers.25.self_attn.q_proj",
|
| 30 |
+
"language_model.model.layers.26.self_attn.q_proj",
|
| 31 |
+
"language_model.model.layers.27.mlp.down_proj",
|
| 32 |
+
"language_model.model.layers.9.self_attn.q_proj",
|
| 33 |
+
"language_model.model.layers.45.self_attn.q_proj",
|
| 34 |
+
"language_model.model.layers.51.self_attn.o_proj",
|
| 35 |
+
"language_model.model.layers.0.self_attn.q_proj",
|
| 36 |
+
"language_model.model.layers.21.mlp.up_proj",
|
| 37 |
+
"language_model.model.layers.61.self_attn.q_proj",
|
| 38 |
+
"language_model.model.layers.52.self_attn.k_proj",
|
| 39 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 40 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
| 41 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
| 42 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
| 43 |
+
"language_model.model.layers.38.self_attn.q_proj",
|
| 44 |
+
"language_model.model.layers.30.self_attn.q_proj",
|
| 45 |
+
"language_model.model.layers.22.mlp.down_proj",
|
| 46 |
+
"language_model.model.layers.46.self_attn.q_proj",
|
| 47 |
+
"language_model.model.layers.54.mlp.gate_proj",
|
| 48 |
+
"language_model.model.layers.49.mlp.up_proj",
|
| 49 |
+
"language_model.model.layers.35.self_attn.q_proj",
|
| 50 |
+
"language_model.model.layers.18.self_attn.o_proj",
|
| 51 |
+
"language_model.model.layers.33.self_attn.v_proj",
|
| 52 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
| 53 |
+
"language_model.model.layers.7.self_attn.q_proj",
|
| 54 |
+
"language_model.model.layers.50.self_attn.o_proj",
|
| 55 |
+
"language_model.model.layers.36.self_attn.o_proj",
|
| 56 |
+
"language_model.model.layers.20.self_attn.k_proj",
|
| 57 |
+
"language_model.model.layers.47.self_attn.k_proj",
|
| 58 |
+
"language_model.model.layers.32.mlp.gate_proj",
|
| 59 |
+
"language_model.model.layers.1.self_attn.q_proj",
|
| 60 |
+
"language_model.model.layers.7.mlp.up_proj",
|
| 61 |
+
"language_model.model.layers.36.mlp.gate_proj",
|
| 62 |
+
"language_model.model.layers.45.self_attn.k_proj",
|
| 63 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
| 64 |
+
"language_model.model.layers.58.self_attn.o_proj",
|
| 65 |
+
"language_model.model.layers.43.self_attn.q_proj",
|
| 66 |
+
"language_model.model.layers.60.self_attn.v_proj",
|
| 67 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
| 68 |
+
"language_model.model.layers.60.self_attn.o_proj",
|
| 69 |
+
"language_model.model.layers.29.self_attn.o_proj",
|
| 70 |
+
"language_model.model.layers.31.mlp.gate_proj",
|
| 71 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
| 72 |
+
"language_model.model.layers.6.self_attn.k_proj",
|
| 73 |
+
"language_model.model.layers.56.self_attn.k_proj",
|
| 74 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
| 75 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 76 |
+
"language_model.model.layers.12.self_attn.v_proj",
|
| 77 |
+
"language_model.model.layers.22.self_attn.o_proj",
|
| 78 |
+
"language_model.model.layers.2.self_attn.o_proj",
|
| 79 |
+
"language_model.model.layers.8.mlp.up_proj",
|
| 80 |
+
"language_model.model.layers.57.mlp.down_proj",
|
| 81 |
+
"language_model.model.layers.57.mlp.up_proj",
|
| 82 |
+
"language_model.model.layers.19.mlp.down_proj",
|
| 83 |
+
"language_model.model.layers.16.self_attn.k_proj",
|
| 84 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
| 85 |
+
"language_model.model.layers.17.mlp.down_proj",
|
| 86 |
+
"language_model.model.layers.35.mlp.down_proj",
|
| 87 |
+
"language_model.model.layers.39.self_attn.k_proj",
|
| 88 |
+
"language_model.model.layers.46.mlp.up_proj",
|
| 89 |
+
"language_model.model.layers.52.self_attn.q_proj",
|
| 90 |
+
"language_model.model.layers.8.self_attn.v_proj",
|
| 91 |
+
"language_model.model.layers.8.mlp.down_proj",
|
| 92 |
+
"language_model.model.layers.8.self_attn.o_proj",
|
| 93 |
+
"language_model.model.layers.7.mlp.down_proj",
|
| 94 |
+
"language_model.model.layers.24.self_attn.o_proj",
|
| 95 |
+
"language_model.model.layers.52.mlp.gate_proj",
|
| 96 |
+
"language_model.model.layers.38.self_attn.o_proj",
|
| 97 |
+
"language_model.model.layers.9.self_attn.v_proj",
|
| 98 |
+
"language_model.model.layers.56.self_attn.v_proj",
|
| 99 |
+
"language_model.model.layers.42.mlp.gate_proj",
|
| 100 |
+
"language_model.model.layers.57.self_attn.o_proj",
|
| 101 |
+
"language_model.model.layers.18.self_attn.v_proj",
|
| 102 |
+
"language_model.model.layers.47.mlp.gate_proj",
|
| 103 |
+
"language_model.model.layers.59.self_attn.v_proj",
|
| 104 |
+
"language_model.model.layers.27.mlp.up_proj",
|
| 105 |
+
"language_model.model.layers.36.self_attn.k_proj",
|
| 106 |
+
"language_model.model.layers.43.mlp.gate_proj",
|
| 107 |
+
"language_model.model.layers.54.self_attn.k_proj",
|
| 108 |
+
"language_model.model.layers.28.self_attn.q_proj",
|
| 109 |
+
"language_model.model.layers.9.mlp.down_proj",
|
| 110 |
+
"language_model.model.layers.36.self_attn.v_proj",
|
| 111 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
| 112 |
+
"language_model.model.layers.26.self_attn.o_proj",
|
| 113 |
+
"language_model.model.layers.17.mlp.up_proj",
|
| 114 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
| 115 |
+
"language_model.model.layers.57.self_attn.k_proj",
|
| 116 |
+
"language_model.model.layers.10.mlp.down_proj",
|
| 117 |
+
"language_model.model.layers.25.self_attn.o_proj",
|
| 118 |
+
"language_model.model.layers.55.self_attn.o_proj",
|
| 119 |
+
"language_model.model.layers.6.self_attn.o_proj",
|
| 120 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 121 |
+
"language_model.model.layers.14.self_attn.q_proj",
|
| 122 |
+
"language_model.model.layers.52.mlp.up_proj",
|
| 123 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
| 124 |
+
"language_model.model.layers.52.self_attn.v_proj",
|
| 125 |
+
"language_model.model.layers.17.self_attn.q_proj",
|
| 126 |
+
"language_model.model.layers.47.self_attn.v_proj",
|
| 127 |
+
"language_model.model.layers.29.mlp.up_proj",
|
| 128 |
+
"language_model.model.layers.13.self_attn.k_proj",
|
| 129 |
+
"language_model.model.layers.41.self_attn.v_proj",
|
| 130 |
+
"language_model.model.layers.4.mlp.up_proj",
|
| 131 |
+
"language_model.model.layers.46.self_attn.v_proj",
|
| 132 |
+
"language_model.model.layers.21.self_attn.q_proj",
|
| 133 |
+
"language_model.model.layers.57.mlp.gate_proj",
|
| 134 |
+
"language_model.model.layers.16.self_attn.o_proj",
|
| 135 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
| 136 |
+
"language_model.model.layers.41.self_attn.o_proj",
|
| 137 |
+
"language_model.model.layers.54.self_attn.v_proj",
|
| 138 |
+
"language_model.model.layers.42.self_attn.o_proj",
|
| 139 |
+
"language_model.model.layers.5.self_attn.q_proj",
|
| 140 |
+
"language_model.model.layers.45.self_attn.o_proj",
|
| 141 |
+
"language_model.model.layers.56.self_attn.q_proj",
|
| 142 |
+
"language_model.model.layers.22.self_attn.v_proj",
|
| 143 |
+
"language_model.model.layers.12.mlp.down_proj",
|
| 144 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
| 145 |
+
"language_model.model.layers.61.self_attn.o_proj",
|
| 146 |
+
"language_model.model.layers.32.self_attn.q_proj",
|
| 147 |
+
"language_model.model.layers.33.self_attn.k_proj",
|
| 148 |
+
"language_model.model.layers.34.mlp.up_proj",
|
| 149 |
+
"language_model.model.layers.25.mlp.down_proj",
|
| 150 |
+
"language_model.model.layers.61.self_attn.k_proj",
|
| 151 |
+
"language_model.model.layers.30.mlp.down_proj",
|
| 152 |
+
"language_model.model.layers.21.self_attn.o_proj",
|
| 153 |
+
"language_model.model.layers.30.self_attn.v_proj",
|
| 154 |
+
"language_model.model.layers.46.self_attn.k_proj",
|
| 155 |
+
"language_model.model.layers.4.self_attn.v_proj",
|
| 156 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 157 |
+
"language_model.model.layers.52.self_attn.o_proj",
|
| 158 |
+
"language_model.model.layers.61.mlp.down_proj",
|
| 159 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
| 160 |
+
"language_model.model.layers.37.mlp.down_proj",
|
| 161 |
+
"language_model.model.layers.18.mlp.up_proj",
|
| 162 |
+
"language_model.model.layers.5.mlp.up_proj",
|
| 163 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
| 164 |
+
"language_model.model.layers.44.mlp.down_proj",
|
| 165 |
+
"language_model.model.layers.58.self_attn.v_proj",
|
| 166 |
+
"language_model.model.layers.58.self_attn.q_proj",
|
| 167 |
+
"language_model.model.layers.60.mlp.down_proj",
|
| 168 |
+
"language_model.model.layers.48.mlp.gate_proj",
|
| 169 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
| 170 |
+
"language_model.model.layers.41.self_attn.k_proj",
|
| 171 |
+
"language_model.model.layers.40.self_attn.k_proj",
|
| 172 |
+
"language_model.model.layers.34.self_attn.q_proj",
|
| 173 |
+
"language_model.model.layers.43.mlp.down_proj",
|
| 174 |
+
"language_model.model.layers.17.self_attn.k_proj",
|
| 175 |
+
"language_model.model.layers.37.mlp.up_proj",
|
| 176 |
+
"language_model.model.layers.12.mlp.up_proj",
|
| 177 |
+
"language_model.model.layers.17.self_attn.v_proj",
|
| 178 |
+
"language_model.model.layers.31.mlp.down_proj",
|
| 179 |
+
"language_model.model.layers.48.self_attn.o_proj",
|
| 180 |
+
"language_model.model.layers.3.mlp.down_proj",
|
| 181 |
+
"language_model.model.layers.46.mlp.gate_proj",
|
| 182 |
+
"language_model.model.layers.32.self_attn.o_proj",
|
| 183 |
+
"language_model.model.layers.24.self_attn.q_proj",
|
| 184 |
+
"language_model.model.layers.58.mlp.up_proj",
|
| 185 |
+
"language_model.model.layers.5.self_attn.v_proj",
|
| 186 |
+
"language_model.model.layers.44.self_attn.v_proj",
|
| 187 |
+
"language_model.model.layers.48.self_attn.v_proj",
|
| 188 |
+
"language_model.model.layers.10.self_attn.q_proj",
|
| 189 |
+
"language_model.model.layers.10.mlp.up_proj",
|
| 190 |
+
"language_model.model.layers.48.mlp.up_proj",
|
| 191 |
+
"language_model.model.layers.5.mlp.down_proj",
|
| 192 |
+
"language_model.model.layers.28.mlp.up_proj",
|
| 193 |
+
"language_model.model.layers.47.self_attn.o_proj",
|
| 194 |
+
"language_model.model.layers.8.self_attn.q_proj",
|
| 195 |
+
"language_model.model.layers.53.mlp.gate_proj",
|
| 196 |
+
"language_model.model.layers.57.self_attn.v_proj",
|
| 197 |
+
"language_model.model.layers.9.mlp.gate_proj",
|
| 198 |
+
"language_model.model.layers.2.self_attn.k_proj",
|
| 199 |
+
"language_model.model.layers.5.self_attn.k_proj",
|
| 200 |
+
"language_model.model.layers.34.self_attn.k_proj",
|
| 201 |
+
"language_model.model.layers.17.self_attn.o_proj",
|
| 202 |
+
"language_model.model.layers.21.self_attn.k_proj",
|
| 203 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
| 204 |
+
"language_model.model.layers.48.mlp.down_proj",
|
| 205 |
+
"language_model.model.layers.25.self_attn.v_proj",
|
| 206 |
+
"language_model.model.layers.44.mlp.gate_proj",
|
| 207 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 208 |
+
"language_model.model.layers.4.mlp.down_proj",
|
| 209 |
+
"language_model.model.layers.13.self_attn.v_proj",
|
| 210 |
+
"language_model.model.layers.55.mlp.up_proj",
|
| 211 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
| 212 |
+
"language_model.model.layers.26.mlp.up_proj",
|
| 213 |
+
"language_model.model.layers.50.mlp.gate_proj",
|
| 214 |
+
"language_model.model.layers.56.mlp.down_proj",
|
| 215 |
+
"language_model.model.layers.21.self_attn.v_proj",
|
| 216 |
+
"language_model.model.layers.18.mlp.gate_proj",
|
| 217 |
+
"language_model.model.layers.22.self_attn.q_proj",
|
| 218 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
| 219 |
+
"language_model.model.layers.53.mlp.down_proj",
|
| 220 |
+
"language_model.model.layers.22.mlp.up_proj",
|
| 221 |
+
"language_model.model.layers.56.self_attn.o_proj",
|
| 222 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
| 223 |
+
"language_model.model.layers.14.self_attn.v_proj",
|
| 224 |
+
"language_model.model.layers.29.self_attn.v_proj",
|
| 225 |
+
"language_model.model.layers.50.mlp.up_proj",
|
| 226 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
| 227 |
+
"language_model.model.layers.23.mlp.down_proj",
|
| 228 |
+
"language_model.model.layers.53.self_attn.k_proj",
|
| 229 |
+
"language_model.model.layers.24.mlp.up_proj",
|
| 230 |
+
"language_model.model.layers.55.mlp.gate_proj",
|
| 231 |
+
"language_model.model.layers.39.mlp.up_proj",
|
| 232 |
+
"language_model.model.layers.59.self_attn.o_proj",
|
| 233 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
| 234 |
+
"language_model.model.layers.41.mlp.down_proj",
|
| 235 |
+
"language_model.model.layers.8.self_attn.k_proj",
|
| 236 |
+
"language_model.model.layers.54.self_attn.q_proj",
|
| 237 |
+
"language_model.model.layers.32.self_attn.v_proj",
|
| 238 |
+
"language_model.model.layers.35.self_attn.o_proj",
|
| 239 |
+
"language_model.model.layers.33.self_attn.o_proj",
|
| 240 |
+
"language_model.model.layers.28.self_attn.v_proj",
|
| 241 |
+
"language_model.model.layers.6.mlp.up_proj",
|
| 242 |
+
"language_model.model.layers.40.self_attn.q_proj",
|
| 243 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
| 244 |
+
"language_model.model.layers.10.self_attn.k_proj",
|
| 245 |
+
"language_model.model.layers.37.self_attn.q_proj",
|
| 246 |
+
"language_model.model.layers.49.mlp.down_proj",
|
| 247 |
+
"language_model.model.layers.6.self_attn.q_proj",
|
| 248 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
| 249 |
+
"language_model.model.layers.45.mlp.down_proj",
|
| 250 |
+
"language_model.model.layers.51.self_attn.v_proj",
|
| 251 |
+
"language_model.model.layers.28.self_attn.k_proj",
|
| 252 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
| 253 |
+
"language_model.model.layers.30.self_attn.o_proj",
|
| 254 |
+
"language_model.model.layers.59.mlp.up_proj",
|
| 255 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
| 256 |
+
"language_model.model.layers.6.mlp.down_proj",
|
| 257 |
+
"language_model.model.layers.9.mlp.up_proj",
|
| 258 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
| 259 |
+
"language_model.model.layers.37.mlp.gate_proj",
|
| 260 |
+
"language_model.model.layers.43.self_attn.k_proj",
|
| 261 |
+
"language_model.model.layers.46.self_attn.o_proj",
|
| 262 |
+
"language_model.model.layers.12.self_attn.k_proj",
|
| 263 |
+
"language_model.model.layers.13.mlp.down_proj",
|
| 264 |
+
"language_model.model.layers.4.self_attn.k_proj",
|
| 265 |
+
"language_model.model.layers.49.self_attn.k_proj",
|
| 266 |
+
"language_model.model.layers.51.self_attn.q_proj",
|
| 267 |
+
"language_model.model.layers.52.mlp.down_proj",
|
| 268 |
+
"language_model.model.layers.24.self_attn.v_proj",
|
| 269 |
+
"language_model.model.layers.42.self_attn.v_proj",
|
| 270 |
+
"language_model.model.layers.53.self_attn.o_proj",
|
| 271 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
| 272 |
+
"language_model.model.layers.40.self_attn.v_proj",
|
| 273 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
| 274 |
+
"language_model.model.layers.40.mlp.up_proj",
|
| 275 |
+
"language_model.model.layers.49.self_attn.o_proj",
|
| 276 |
+
"language_model.model.layers.42.mlp.down_proj",
|
| 277 |
+
"language_model.model.layers.41.self_attn.q_proj",
|
| 278 |
+
"language_model.model.layers.42.mlp.up_proj",
|
| 279 |
+
"language_model.model.layers.28.mlp.down_proj",
|
| 280 |
+
"language_model.model.layers.2.self_attn.v_proj",
|
| 281 |
+
"language_model.model.layers.23.mlp.up_proj",
|
| 282 |
+
"language_model.model.layers.36.mlp.down_proj",
|
| 283 |
+
"language_model.model.layers.16.mlp.down_proj",
|
| 284 |
+
"language_model.model.layers.43.self_attn.o_proj",
|
| 285 |
+
"language_model.model.layers.20.self_attn.q_proj",
|
| 286 |
+
"language_model.model.layers.51.mlp.gate_proj",
|
| 287 |
+
"language_model.model.layers.15.mlp.down_proj",
|
| 288 |
+
"language_model.model.layers.10.self_attn.v_proj",
|
| 289 |
+
"language_model.model.layers.35.self_attn.v_proj",
|
| 290 |
+
"language_model.model.layers.59.self_attn.k_proj",
|
| 291 |
+
"language_model.model.layers.47.mlp.up_proj",
|
| 292 |
+
"language_model.model.layers.38.self_attn.v_proj",
|
| 293 |
+
"language_model.model.layers.18.self_attn.q_proj",
|
| 294 |
+
"language_model.model.layers.25.self_attn.k_proj",
|
| 295 |
+
"language_model.model.layers.36.self_attn.q_proj",
|
| 296 |
+
"language_model.model.layers.40.mlp.down_proj",
|
| 297 |
+
"language_model.model.layers.39.mlp.down_proj",
|
| 298 |
+
"language_model.model.layers.41.mlp.gate_proj",
|
| 299 |
+
"language_model.model.layers.29.self_attn.q_proj",
|
| 300 |
+
"language_model.model.layers.56.mlp.up_proj",
|
| 301 |
+
"language_model.model.layers.14.mlp.up_proj",
|
| 302 |
+
"language_model.model.layers.29.mlp.down_proj",
|
| 303 |
+
"language_model.model.layers.13.mlp.up_proj",
|
| 304 |
+
"language_model.model.layers.28.mlp.gate_proj",
|
| 305 |
+
"language_model.model.layers.45.mlp.up_proj",
|
| 306 |
+
"language_model.model.layers.13.self_attn.o_proj",
|
| 307 |
+
"language_model.model.layers.20.self_attn.v_proj",
|
| 308 |
+
"language_model.model.layers.54.self_attn.o_proj",
|
| 309 |
+
"language_model.model.layers.39.mlp.gate_proj",
|
| 310 |
+
"language_model.model.layers.25.mlp.up_proj",
|
| 311 |
+
"language_model.model.layers.53.mlp.up_proj",
|
| 312 |
+
"language_model.model.layers.50.mlp.down_proj",
|
| 313 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
| 314 |
+
"language_model.model.layers.59.mlp.gate_proj",
|
| 315 |
+
"language_model.model.layers.60.mlp.up_proj",
|
| 316 |
+
"language_model.model.layers.24.mlp.down_proj",
|
| 317 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
| 318 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
| 319 |
+
"language_model.model.layers.60.mlp.gate_proj",
|
| 320 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
| 321 |
+
"language_model.model.layers.24.self_attn.k_proj",
|
| 322 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
| 323 |
+
"language_model.model.layers.13.self_attn.q_proj",
|
| 324 |
+
"language_model.model.layers.44.self_attn.o_proj",
|
| 325 |
+
"language_model.model.layers.32.mlp.down_proj",
|
| 326 |
+
"language_model.model.layers.20.mlp.up_proj",
|
| 327 |
+
"language_model.model.layers.10.self_attn.o_proj",
|
| 328 |
+
"language_model.model.layers.41.mlp.up_proj",
|
| 329 |
+
"language_model.model.layers.49.mlp.gate_proj",
|
| 330 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 331 |
+
"language_model.model.layers.39.self_attn.o_proj",
|
| 332 |
+
"language_model.model.layers.14.self_attn.k_proj",
|
| 333 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
| 334 |
+
"language_model.model.layers.7.self_attn.o_proj",
|
| 335 |
+
"language_model.model.layers.21.mlp.down_proj",
|
| 336 |
+
"language_model.model.layers.35.mlp.up_proj",
|
| 337 |
+
"language_model.model.layers.20.mlp.down_proj",
|
| 338 |
+
"language_model.model.layers.15.mlp.up_proj",
|
| 339 |
+
"language_model.model.layers.53.self_attn.v_proj",
|
| 340 |
+
"language_model.model.layers.9.self_attn.o_proj",
|
| 341 |
+
"language_model.model.layers.60.self_attn.k_proj",
|
| 342 |
+
"language_model.model.layers.5.self_attn.o_proj",
|
| 343 |
+
"language_model.model.layers.58.mlp.down_proj",
|
| 344 |
+
"language_model.model.layers.6.self_attn.v_proj",
|
| 345 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.34.mlp.gate_proj",
|
| 347 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
| 348 |
+
"language_model.model.layers.36.mlp.up_proj",
|
| 349 |
+
"language_model.model.layers.57.self_attn.q_proj",
|
| 350 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
| 351 |
+
"language_model.model.layers.28.self_attn.o_proj",
|
| 352 |
+
"language_model.model.layers.55.self_attn.q_proj",
|
| 353 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
| 354 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
| 355 |
+
"language_model.model.layers.32.self_attn.k_proj",
|
| 356 |
+
"language_model.model.layers.12.self_attn.q_proj",
|
| 357 |
+
"language_model.model.layers.35.self_attn.k_proj",
|
| 358 |
+
"language_model.model.layers.37.self_attn.o_proj",
|
| 359 |
+
"language_model.model.layers.55.self_attn.v_proj",
|
| 360 |
+
"language_model.model.layers.50.self_attn.q_proj",
|
| 361 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
| 362 |
+
"language_model.model.layers.26.self_attn.k_proj",
|
| 363 |
+
"language_model.model.layers.1.self_attn.k_proj",
|
| 364 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 365 |
+
"language_model.model.layers.9.self_attn.k_proj",
|
| 366 |
+
"language_model.model.layers.18.mlp.down_proj",
|
| 367 |
+
"language_model.model.layers.33.mlp.down_proj",
|
| 368 |
+
"language_model.model.layers.59.self_attn.q_proj",
|
| 369 |
+
"language_model.model.layers.11.mlp.down_proj",
|
| 370 |
+
"language_model.model.layers.61.mlp.up_proj",
|
| 371 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
| 372 |
+
"language_model.model.layers.30.self_attn.k_proj",
|
| 373 |
+
"language_model.model.layers.14.self_attn.o_proj",
|
| 374 |
+
"language_model.model.layers.47.mlp.down_proj",
|
| 375 |
+
"language_model.model.layers.16.self_attn.v_proj",
|
| 376 |
+
"language_model.model.layers.40.self_attn.o_proj",
|
| 377 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
| 378 |
+
"language_model.model.layers.54.mlp.down_proj",
|
| 379 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
| 380 |
+
"language_model.model.layers.61.self_attn.v_proj",
|
| 381 |
+
"language_model.model.layers.42.self_attn.k_proj",
|
| 382 |
+
"language_model.model.layers.44.self_attn.q_proj",
|
| 383 |
+
"language_model.model.layers.3.mlp.up_proj",
|
| 384 |
+
"language_model.model.layers.58.self_attn.k_proj",
|
| 385 |
+
"language_model.model.layers.54.mlp.up_proj",
|
| 386 |
+
"language_model.model.layers.59.mlp.down_proj",
|
| 387 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 388 |
+
"language_model.model.layers.33.self_attn.q_proj",
|
| 389 |
+
"language_model.model.layers.43.mlp.up_proj",
|
| 390 |
+
"language_model.model.layers.48.self_attn.q_proj",
|
| 391 |
+
"language_model.model.layers.0.self_attn.k_proj",
|
| 392 |
+
"language_model.model.layers.22.self_attn.k_proj",
|
| 393 |
+
"language_model.model.layers.49.self_attn.q_proj",
|
| 394 |
+
"language_model.model.layers.43.self_attn.v_proj",
|
| 395 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
| 396 |
+
"language_model.model.layers.38.mlp.up_proj",
|
| 397 |
+
"language_model.model.layers.1.self_attn.v_proj",
|
| 398 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
| 399 |
+
"language_model.model.layers.56.mlp.gate_proj",
|
| 400 |
+
"language_model.model.layers.50.self_attn.v_proj",
|
| 401 |
+
"language_model.model.layers.29.self_attn.k_proj",
|
| 402 |
+
"language_model.model.layers.8.mlp.gate_proj",
|
| 403 |
+
"language_model.model.layers.34.self_attn.v_proj",
|
| 404 |
+
"language_model.model.layers.20.self_attn.o_proj",
|
| 405 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
| 406 |
+
"language_model.model.layers.37.self_attn.v_proj",
|
| 407 |
+
"language_model.model.layers.4.self_attn.q_proj",
|
| 408 |
+
"language_model.model.layers.55.mlp.down_proj",
|
| 409 |
+
"language_model.model.layers.45.self_attn.v_proj",
|
| 410 |
+
"language_model.model.layers.61.mlp.gate_proj",
|
| 411 |
+
"language_model.model.layers.0.self_attn.o_proj",
|
| 412 |
+
"language_model.model.layers.37.self_attn.k_proj",
|
| 413 |
+
"language_model.model.layers.51.self_attn.k_proj",
|
| 414 |
+
"language_model.model.layers.38.mlp.gate_proj",
|
| 415 |
+
"language_model.model.layers.26.mlp.down_proj",
|
| 416 |
+
"language_model.model.layers.48.self_attn.k_proj",
|
| 417 |
+
"language_model.model.layers.39.self_attn.q_proj",
|
| 418 |
+
"language_model.model.layers.45.mlp.gate_proj",
|
| 419 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
| 420 |
+
"language_model.model.layers.11.mlp.up_proj",
|
| 421 |
+
"language_model.model.layers.34.mlp.down_proj",
|
| 422 |
+
"language_model.model.layers.0.self_attn.v_proj",
|
| 423 |
+
"language_model.model.layers.44.self_attn.k_proj",
|
| 424 |
+
"language_model.model.layers.16.self_attn.q_proj",
|
| 425 |
+
"language_model.model.layers.14.mlp.down_proj",
|
| 426 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 427 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
| 428 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
| 429 |
+
"language_model.model.layers.31.mlp.up_proj",
|
| 430 |
+
"language_model.model.layers.44.mlp.up_proj",
|
| 431 |
+
"language_model.model.layers.58.mlp.gate_proj",
|
| 432 |
+
"language_model.model.layers.26.self_attn.v_proj",
|
| 433 |
+
"language_model.model.layers.34.self_attn.o_proj",
|
| 434 |
+
"language_model.model.layers.19.mlp.up_proj",
|
| 435 |
+
"language_model.model.layers.2.self_attn.q_proj",
|
| 436 |
+
"language_model.model.layers.40.mlp.gate_proj",
|
| 437 |
+
"language_model.model.layers.32.mlp.up_proj",
|
| 438 |
+
"language_model.model.layers.33.mlp.up_proj",
|
| 439 |
+
"language_model.model.layers.4.self_attn.o_proj",
|
| 440 |
+
"language_model.model.layers.35.mlp.gate_proj",
|
| 441 |
+
"language_model.model.layers.18.self_attn.k_proj",
|
| 442 |
+
"language_model.model.layers.38.self_attn.k_proj",
|
| 443 |
+
"language_model.model.layers.49.self_attn.v_proj",
|
| 444 |
+
"language_model.model.layers.31.self_attn.o_proj",
|
| 445 |
+
"language_model.model.layers.55.self_attn.k_proj",
|
| 446 |
+
"language_model.model.layers.38.mlp.down_proj",
|
| 447 |
+
"language_model.model.layers.46.mlp.down_proj",
|
| 448 |
+
"language_model.model.layers.1.self_attn.o_proj",
|
| 449 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
| 450 |
+
"language_model.model.layers.33.mlp.gate_proj",
|
| 451 |
+
"language_model.model.layers.60.self_attn.q_proj",
|
| 452 |
+
"language_model.model.layers.39.self_attn.v_proj",
|
| 453 |
+
"language_model.model.layers.16.mlp.up_proj",
|
| 454 |
+
"language_model.model.layers.50.self_attn.k_proj",
|
| 455 |
+
"language_model.model.layers.12.self_attn.o_proj",
|
| 456 |
+
"language_model.model.layers.53.self_attn.q_proj"
|
| 457 |
+
],
|
| 458 |
+
"task_type": "CAUSAL_LM",
|
| 459 |
+
"use_dora": false,
|
| 460 |
+
"use_rslora": false
|
| 461 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d51d0b54fa39feffff06d1b159e05c5ef5c452cefc613d58b44149187d958bc
|
| 3 |
+
size 1816396048
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"num_input_tokens_seen": 4519360,
|
| 4 |
+
"total_flos": 7.178223503576986e+17,
|
| 5 |
+
"train_loss": 1.3478541066272858,
|
| 6 |
+
"train_runtime": 3084.094,
|
| 7 |
+
"train_samples_per_second": 1.245,
|
| 8 |
+
"train_steps_per_second": 0.156
|
| 9 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 3 |
+
}
|
checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-3-27b-it
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-27b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"language_model.model.layers.42.self_attn.q_proj",
|
| 24 |
+
"language_model.model.layers.51.mlp.up_proj",
|
| 25 |
+
"language_model.model.layers.51.mlp.down_proj",
|
| 26 |
+
"language_model.model.layers.30.mlp.up_proj",
|
| 27 |
+
"language_model.model.layers.47.self_attn.q_proj",
|
| 28 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
| 29 |
+
"language_model.model.layers.25.self_attn.q_proj",
|
| 30 |
+
"language_model.model.layers.26.self_attn.q_proj",
|
| 31 |
+
"language_model.model.layers.27.mlp.down_proj",
|
| 32 |
+
"language_model.model.layers.9.self_attn.q_proj",
|
| 33 |
+
"language_model.model.layers.45.self_attn.q_proj",
|
| 34 |
+
"language_model.model.layers.51.self_attn.o_proj",
|
| 35 |
+
"language_model.model.layers.0.self_attn.q_proj",
|
| 36 |
+
"language_model.model.layers.21.mlp.up_proj",
|
| 37 |
+
"language_model.model.layers.61.self_attn.q_proj",
|
| 38 |
+
"language_model.model.layers.52.self_attn.k_proj",
|
| 39 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 40 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
| 41 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
| 42 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
| 43 |
+
"language_model.model.layers.38.self_attn.q_proj",
|
| 44 |
+
"language_model.model.layers.30.self_attn.q_proj",
|
| 45 |
+
"language_model.model.layers.22.mlp.down_proj",
|
| 46 |
+
"language_model.model.layers.46.self_attn.q_proj",
|
| 47 |
+
"language_model.model.layers.54.mlp.gate_proj",
|
| 48 |
+
"language_model.model.layers.49.mlp.up_proj",
|
| 49 |
+
"language_model.model.layers.35.self_attn.q_proj",
|
| 50 |
+
"language_model.model.layers.18.self_attn.o_proj",
|
| 51 |
+
"language_model.model.layers.33.self_attn.v_proj",
|
| 52 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
| 53 |
+
"language_model.model.layers.7.self_attn.q_proj",
|
| 54 |
+
"language_model.model.layers.50.self_attn.o_proj",
|
| 55 |
+
"language_model.model.layers.36.self_attn.o_proj",
|
| 56 |
+
"language_model.model.layers.20.self_attn.k_proj",
|
| 57 |
+
"language_model.model.layers.47.self_attn.k_proj",
|
| 58 |
+
"language_model.model.layers.32.mlp.gate_proj",
|
| 59 |
+
"language_model.model.layers.1.self_attn.q_proj",
|
| 60 |
+
"language_model.model.layers.7.mlp.up_proj",
|
| 61 |
+
"language_model.model.layers.36.mlp.gate_proj",
|
| 62 |
+
"language_model.model.layers.45.self_attn.k_proj",
|
| 63 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
| 64 |
+
"language_model.model.layers.58.self_attn.o_proj",
|
| 65 |
+
"language_model.model.layers.43.self_attn.q_proj",
|
| 66 |
+
"language_model.model.layers.60.self_attn.v_proj",
|
| 67 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
| 68 |
+
"language_model.model.layers.60.self_attn.o_proj",
|
| 69 |
+
"language_model.model.layers.29.self_attn.o_proj",
|
| 70 |
+
"language_model.model.layers.31.mlp.gate_proj",
|
| 71 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
| 72 |
+
"language_model.model.layers.6.self_attn.k_proj",
|
| 73 |
+
"language_model.model.layers.56.self_attn.k_proj",
|
| 74 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
| 75 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 76 |
+
"language_model.model.layers.12.self_attn.v_proj",
|
| 77 |
+
"language_model.model.layers.22.self_attn.o_proj",
|
| 78 |
+
"language_model.model.layers.2.self_attn.o_proj",
|
| 79 |
+
"language_model.model.layers.8.mlp.up_proj",
|
| 80 |
+
"language_model.model.layers.57.mlp.down_proj",
|
| 81 |
+
"language_model.model.layers.57.mlp.up_proj",
|
| 82 |
+
"language_model.model.layers.19.mlp.down_proj",
|
| 83 |
+
"language_model.model.layers.16.self_attn.k_proj",
|
| 84 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
| 85 |
+
"language_model.model.layers.17.mlp.down_proj",
|
| 86 |
+
"language_model.model.layers.35.mlp.down_proj",
|
| 87 |
+
"language_model.model.layers.39.self_attn.k_proj",
|
| 88 |
+
"language_model.model.layers.46.mlp.up_proj",
|
| 89 |
+
"language_model.model.layers.52.self_attn.q_proj",
|
| 90 |
+
"language_model.model.layers.8.self_attn.v_proj",
|
| 91 |
+
"language_model.model.layers.8.mlp.down_proj",
|
| 92 |
+
"language_model.model.layers.8.self_attn.o_proj",
|
| 93 |
+
"language_model.model.layers.7.mlp.down_proj",
|
| 94 |
+
"language_model.model.layers.24.self_attn.o_proj",
|
| 95 |
+
"language_model.model.layers.52.mlp.gate_proj",
|
| 96 |
+
"language_model.model.layers.38.self_attn.o_proj",
|
| 97 |
+
"language_model.model.layers.9.self_attn.v_proj",
|
| 98 |
+
"language_model.model.layers.56.self_attn.v_proj",
|
| 99 |
+
"language_model.model.layers.42.mlp.gate_proj",
|
| 100 |
+
"language_model.model.layers.57.self_attn.o_proj",
|
| 101 |
+
"language_model.model.layers.18.self_attn.v_proj",
|
| 102 |
+
"language_model.model.layers.47.mlp.gate_proj",
|
| 103 |
+
"language_model.model.layers.59.self_attn.v_proj",
|
| 104 |
+
"language_model.model.layers.27.mlp.up_proj",
|
| 105 |
+
"language_model.model.layers.36.self_attn.k_proj",
|
| 106 |
+
"language_model.model.layers.43.mlp.gate_proj",
|
| 107 |
+
"language_model.model.layers.54.self_attn.k_proj",
|
| 108 |
+
"language_model.model.layers.28.self_attn.q_proj",
|
| 109 |
+
"language_model.model.layers.9.mlp.down_proj",
|
| 110 |
+
"language_model.model.layers.36.self_attn.v_proj",
|
| 111 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
| 112 |
+
"language_model.model.layers.26.self_attn.o_proj",
|
| 113 |
+
"language_model.model.layers.17.mlp.up_proj",
|
| 114 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
| 115 |
+
"language_model.model.layers.57.self_attn.k_proj",
|
| 116 |
+
"language_model.model.layers.10.mlp.down_proj",
|
| 117 |
+
"language_model.model.layers.25.self_attn.o_proj",
|
| 118 |
+
"language_model.model.layers.55.self_attn.o_proj",
|
| 119 |
+
"language_model.model.layers.6.self_attn.o_proj",
|
| 120 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 121 |
+
"language_model.model.layers.14.self_attn.q_proj",
|
| 122 |
+
"language_model.model.layers.52.mlp.up_proj",
|
| 123 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
| 124 |
+
"language_model.model.layers.52.self_attn.v_proj",
|
| 125 |
+
"language_model.model.layers.17.self_attn.q_proj",
|
| 126 |
+
"language_model.model.layers.47.self_attn.v_proj",
|
| 127 |
+
"language_model.model.layers.29.mlp.up_proj",
|
| 128 |
+
"language_model.model.layers.13.self_attn.k_proj",
|
| 129 |
+
"language_model.model.layers.41.self_attn.v_proj",
|
| 130 |
+
"language_model.model.layers.4.mlp.up_proj",
|
| 131 |
+
"language_model.model.layers.46.self_attn.v_proj",
|
| 132 |
+
"language_model.model.layers.21.self_attn.q_proj",
|
| 133 |
+
"language_model.model.layers.57.mlp.gate_proj",
|
| 134 |
+
"language_model.model.layers.16.self_attn.o_proj",
|
| 135 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
| 136 |
+
"language_model.model.layers.41.self_attn.o_proj",
|
| 137 |
+
"language_model.model.layers.54.self_attn.v_proj",
|
| 138 |
+
"language_model.model.layers.42.self_attn.o_proj",
|
| 139 |
+
"language_model.model.layers.5.self_attn.q_proj",
|
| 140 |
+
"language_model.model.layers.45.self_attn.o_proj",
|
| 141 |
+
"language_model.model.layers.56.self_attn.q_proj",
|
| 142 |
+
"language_model.model.layers.22.self_attn.v_proj",
|
| 143 |
+
"language_model.model.layers.12.mlp.down_proj",
|
| 144 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
| 145 |
+
"language_model.model.layers.61.self_attn.o_proj",
|
| 146 |
+
"language_model.model.layers.32.self_attn.q_proj",
|
| 147 |
+
"language_model.model.layers.33.self_attn.k_proj",
|
| 148 |
+
"language_model.model.layers.34.mlp.up_proj",
|
| 149 |
+
"language_model.model.layers.25.mlp.down_proj",
|
| 150 |
+
"language_model.model.layers.61.self_attn.k_proj",
|
| 151 |
+
"language_model.model.layers.30.mlp.down_proj",
|
| 152 |
+
"language_model.model.layers.21.self_attn.o_proj",
|
| 153 |
+
"language_model.model.layers.30.self_attn.v_proj",
|
| 154 |
+
"language_model.model.layers.46.self_attn.k_proj",
|
| 155 |
+
"language_model.model.layers.4.self_attn.v_proj",
|
| 156 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 157 |
+
"language_model.model.layers.52.self_attn.o_proj",
|
| 158 |
+
"language_model.model.layers.61.mlp.down_proj",
|
| 159 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
| 160 |
+
"language_model.model.layers.37.mlp.down_proj",
|
| 161 |
+
"language_model.model.layers.18.mlp.up_proj",
|
| 162 |
+
"language_model.model.layers.5.mlp.up_proj",
|
| 163 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
| 164 |
+
"language_model.model.layers.44.mlp.down_proj",
|
| 165 |
+
"language_model.model.layers.58.self_attn.v_proj",
|
| 166 |
+
"language_model.model.layers.58.self_attn.q_proj",
|
| 167 |
+
"language_model.model.layers.60.mlp.down_proj",
|
| 168 |
+
"language_model.model.layers.48.mlp.gate_proj",
|
| 169 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
| 170 |
+
"language_model.model.layers.41.self_attn.k_proj",
|
| 171 |
+
"language_model.model.layers.40.self_attn.k_proj",
|
| 172 |
+
"language_model.model.layers.34.self_attn.q_proj",
|
| 173 |
+
"language_model.model.layers.43.mlp.down_proj",
|
| 174 |
+
"language_model.model.layers.17.self_attn.k_proj",
|
| 175 |
+
"language_model.model.layers.37.mlp.up_proj",
|
| 176 |
+
"language_model.model.layers.12.mlp.up_proj",
|
| 177 |
+
"language_model.model.layers.17.self_attn.v_proj",
|
| 178 |
+
"language_model.model.layers.31.mlp.down_proj",
|
| 179 |
+
"language_model.model.layers.48.self_attn.o_proj",
|
| 180 |
+
"language_model.model.layers.3.mlp.down_proj",
|
| 181 |
+
"language_model.model.layers.46.mlp.gate_proj",
|
| 182 |
+
"language_model.model.layers.32.self_attn.o_proj",
|
| 183 |
+
"language_model.model.layers.24.self_attn.q_proj",
|
| 184 |
+
"language_model.model.layers.58.mlp.up_proj",
|
| 185 |
+
"language_model.model.layers.5.self_attn.v_proj",
|
| 186 |
+
"language_model.model.layers.44.self_attn.v_proj",
|
| 187 |
+
"language_model.model.layers.48.self_attn.v_proj",
|
| 188 |
+
"language_model.model.layers.10.self_attn.q_proj",
|
| 189 |
+
"language_model.model.layers.10.mlp.up_proj",
|
| 190 |
+
"language_model.model.layers.48.mlp.up_proj",
|
| 191 |
+
"language_model.model.layers.5.mlp.down_proj",
|
| 192 |
+
"language_model.model.layers.28.mlp.up_proj",
|
| 193 |
+
"language_model.model.layers.47.self_attn.o_proj",
|
| 194 |
+
"language_model.model.layers.8.self_attn.q_proj",
|
| 195 |
+
"language_model.model.layers.53.mlp.gate_proj",
|
| 196 |
+
"language_model.model.layers.57.self_attn.v_proj",
|
| 197 |
+
"language_model.model.layers.9.mlp.gate_proj",
|
| 198 |
+
"language_model.model.layers.2.self_attn.k_proj",
|
| 199 |
+
"language_model.model.layers.5.self_attn.k_proj",
|
| 200 |
+
"language_model.model.layers.34.self_attn.k_proj",
|
| 201 |
+
"language_model.model.layers.17.self_attn.o_proj",
|
| 202 |
+
"language_model.model.layers.21.self_attn.k_proj",
|
| 203 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
| 204 |
+
"language_model.model.layers.48.mlp.down_proj",
|
| 205 |
+
"language_model.model.layers.25.self_attn.v_proj",
|
| 206 |
+
"language_model.model.layers.44.mlp.gate_proj",
|
| 207 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 208 |
+
"language_model.model.layers.4.mlp.down_proj",
|
| 209 |
+
"language_model.model.layers.13.self_attn.v_proj",
|
| 210 |
+
"language_model.model.layers.55.mlp.up_proj",
|
| 211 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
| 212 |
+
"language_model.model.layers.26.mlp.up_proj",
|
| 213 |
+
"language_model.model.layers.50.mlp.gate_proj",
|
| 214 |
+
"language_model.model.layers.56.mlp.down_proj",
|
| 215 |
+
"language_model.model.layers.21.self_attn.v_proj",
|
| 216 |
+
"language_model.model.layers.18.mlp.gate_proj",
|
| 217 |
+
"language_model.model.layers.22.self_attn.q_proj",
|
| 218 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
| 219 |
+
"language_model.model.layers.53.mlp.down_proj",
|
| 220 |
+
"language_model.model.layers.22.mlp.up_proj",
|
| 221 |
+
"language_model.model.layers.56.self_attn.o_proj",
|
| 222 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
| 223 |
+
"language_model.model.layers.14.self_attn.v_proj",
|
| 224 |
+
"language_model.model.layers.29.self_attn.v_proj",
|
| 225 |
+
"language_model.model.layers.50.mlp.up_proj",
|
| 226 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
| 227 |
+
"language_model.model.layers.23.mlp.down_proj",
|
| 228 |
+
"language_model.model.layers.53.self_attn.k_proj",
|
| 229 |
+
"language_model.model.layers.24.mlp.up_proj",
|
| 230 |
+
"language_model.model.layers.55.mlp.gate_proj",
|
| 231 |
+
"language_model.model.layers.39.mlp.up_proj",
|
| 232 |
+
"language_model.model.layers.59.self_attn.o_proj",
|
| 233 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
| 234 |
+
"language_model.model.layers.41.mlp.down_proj",
|
| 235 |
+
"language_model.model.layers.8.self_attn.k_proj",
|
| 236 |
+
"language_model.model.layers.54.self_attn.q_proj",
|
| 237 |
+
"language_model.model.layers.32.self_attn.v_proj",
|
| 238 |
+
"language_model.model.layers.35.self_attn.o_proj",
|
| 239 |
+
"language_model.model.layers.33.self_attn.o_proj",
|
| 240 |
+
"language_model.model.layers.28.self_attn.v_proj",
|
| 241 |
+
"language_model.model.layers.6.mlp.up_proj",
|
| 242 |
+
"language_model.model.layers.40.self_attn.q_proj",
|
| 243 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
| 244 |
+
"language_model.model.layers.10.self_attn.k_proj",
|
| 245 |
+
"language_model.model.layers.37.self_attn.q_proj",
|
| 246 |
+
"language_model.model.layers.49.mlp.down_proj",
|
| 247 |
+
"language_model.model.layers.6.self_attn.q_proj",
|
| 248 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
| 249 |
+
"language_model.model.layers.45.mlp.down_proj",
|
| 250 |
+
"language_model.model.layers.51.self_attn.v_proj",
|
| 251 |
+
"language_model.model.layers.28.self_attn.k_proj",
|
| 252 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
| 253 |
+
"language_model.model.layers.30.self_attn.o_proj",
|
| 254 |
+
"language_model.model.layers.59.mlp.up_proj",
|
| 255 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
| 256 |
+
"language_model.model.layers.6.mlp.down_proj",
|
| 257 |
+
"language_model.model.layers.9.mlp.up_proj",
|
| 258 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
| 259 |
+
"language_model.model.layers.37.mlp.gate_proj",
|
| 260 |
+
"language_model.model.layers.43.self_attn.k_proj",
|
| 261 |
+
"language_model.model.layers.46.self_attn.o_proj",
|
| 262 |
+
"language_model.model.layers.12.self_attn.k_proj",
|
| 263 |
+
"language_model.model.layers.13.mlp.down_proj",
|
| 264 |
+
"language_model.model.layers.4.self_attn.k_proj",
|
| 265 |
+
"language_model.model.layers.49.self_attn.k_proj",
|
| 266 |
+
"language_model.model.layers.51.self_attn.q_proj",
|
| 267 |
+
"language_model.model.layers.52.mlp.down_proj",
|
| 268 |
+
"language_model.model.layers.24.self_attn.v_proj",
|
| 269 |
+
"language_model.model.layers.42.self_attn.v_proj",
|
| 270 |
+
"language_model.model.layers.53.self_attn.o_proj",
|
| 271 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
| 272 |
+
"language_model.model.layers.40.self_attn.v_proj",
|
| 273 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
| 274 |
+
"language_model.model.layers.40.mlp.up_proj",
|
| 275 |
+
"language_model.model.layers.49.self_attn.o_proj",
|
| 276 |
+
"language_model.model.layers.42.mlp.down_proj",
|
| 277 |
+
"language_model.model.layers.41.self_attn.q_proj",
|
| 278 |
+
"language_model.model.layers.42.mlp.up_proj",
|
| 279 |
+
"language_model.model.layers.28.mlp.down_proj",
|
| 280 |
+
"language_model.model.layers.2.self_attn.v_proj",
|
| 281 |
+
"language_model.model.layers.23.mlp.up_proj",
|
| 282 |
+
"language_model.model.layers.36.mlp.down_proj",
|
| 283 |
+
"language_model.model.layers.16.mlp.down_proj",
|
| 284 |
+
"language_model.model.layers.43.self_attn.o_proj",
|
| 285 |
+
"language_model.model.layers.20.self_attn.q_proj",
|
| 286 |
+
"language_model.model.layers.51.mlp.gate_proj",
|
| 287 |
+
"language_model.model.layers.15.mlp.down_proj",
|
| 288 |
+
"language_model.model.layers.10.self_attn.v_proj",
|
| 289 |
+
"language_model.model.layers.35.self_attn.v_proj",
|
| 290 |
+
"language_model.model.layers.59.self_attn.k_proj",
|
| 291 |
+
"language_model.model.layers.47.mlp.up_proj",
|
| 292 |
+
"language_model.model.layers.38.self_attn.v_proj",
|
| 293 |
+
"language_model.model.layers.18.self_attn.q_proj",
|
| 294 |
+
"language_model.model.layers.25.self_attn.k_proj",
|
| 295 |
+
"language_model.model.layers.36.self_attn.q_proj",
|
| 296 |
+
"language_model.model.layers.40.mlp.down_proj",
|
| 297 |
+
"language_model.model.layers.39.mlp.down_proj",
|
| 298 |
+
"language_model.model.layers.41.mlp.gate_proj",
|
| 299 |
+
"language_model.model.layers.29.self_attn.q_proj",
|
| 300 |
+
"language_model.model.layers.56.mlp.up_proj",
|
| 301 |
+
"language_model.model.layers.14.mlp.up_proj",
|
| 302 |
+
"language_model.model.layers.29.mlp.down_proj",
|
| 303 |
+
"language_model.model.layers.13.mlp.up_proj",
|
| 304 |
+
"language_model.model.layers.28.mlp.gate_proj",
|
| 305 |
+
"language_model.model.layers.45.mlp.up_proj",
|
| 306 |
+
"language_model.model.layers.13.self_attn.o_proj",
|
| 307 |
+
"language_model.model.layers.20.self_attn.v_proj",
|
| 308 |
+
"language_model.model.layers.54.self_attn.o_proj",
|
| 309 |
+
"language_model.model.layers.39.mlp.gate_proj",
|
| 310 |
+
"language_model.model.layers.25.mlp.up_proj",
|
| 311 |
+
"language_model.model.layers.53.mlp.up_proj",
|
| 312 |
+
"language_model.model.layers.50.mlp.down_proj",
|
| 313 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
| 314 |
+
"language_model.model.layers.59.mlp.gate_proj",
|
| 315 |
+
"language_model.model.layers.60.mlp.up_proj",
|
| 316 |
+
"language_model.model.layers.24.mlp.down_proj",
|
| 317 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
| 318 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
| 319 |
+
"language_model.model.layers.60.mlp.gate_proj",
|
| 320 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
| 321 |
+
"language_model.model.layers.24.self_attn.k_proj",
|
| 322 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
| 323 |
+
"language_model.model.layers.13.self_attn.q_proj",
|
| 324 |
+
"language_model.model.layers.44.self_attn.o_proj",
|
| 325 |
+
"language_model.model.layers.32.mlp.down_proj",
|
| 326 |
+
"language_model.model.layers.20.mlp.up_proj",
|
| 327 |
+
"language_model.model.layers.10.self_attn.o_proj",
|
| 328 |
+
"language_model.model.layers.41.mlp.up_proj",
|
| 329 |
+
"language_model.model.layers.49.mlp.gate_proj",
|
| 330 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 331 |
+
"language_model.model.layers.39.self_attn.o_proj",
|
| 332 |
+
"language_model.model.layers.14.self_attn.k_proj",
|
| 333 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
| 334 |
+
"language_model.model.layers.7.self_attn.o_proj",
|
| 335 |
+
"language_model.model.layers.21.mlp.down_proj",
|
| 336 |
+
"language_model.model.layers.35.mlp.up_proj",
|
| 337 |
+
"language_model.model.layers.20.mlp.down_proj",
|
| 338 |
+
"language_model.model.layers.15.mlp.up_proj",
|
| 339 |
+
"language_model.model.layers.53.self_attn.v_proj",
|
| 340 |
+
"language_model.model.layers.9.self_attn.o_proj",
|
| 341 |
+
"language_model.model.layers.60.self_attn.k_proj",
|
| 342 |
+
"language_model.model.layers.5.self_attn.o_proj",
|
| 343 |
+
"language_model.model.layers.58.mlp.down_proj",
|
| 344 |
+
"language_model.model.layers.6.self_attn.v_proj",
|
| 345 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.34.mlp.gate_proj",
|
| 347 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
| 348 |
+
"language_model.model.layers.36.mlp.up_proj",
|
| 349 |
+
"language_model.model.layers.57.self_attn.q_proj",
|
| 350 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
| 351 |
+
"language_model.model.layers.28.self_attn.o_proj",
|
| 352 |
+
"language_model.model.layers.55.self_attn.q_proj",
|
| 353 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
| 354 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
| 355 |
+
"language_model.model.layers.32.self_attn.k_proj",
|
| 356 |
+
"language_model.model.layers.12.self_attn.q_proj",
|
| 357 |
+
"language_model.model.layers.35.self_attn.k_proj",
|
| 358 |
+
"language_model.model.layers.37.self_attn.o_proj",
|
| 359 |
+
"language_model.model.layers.55.self_attn.v_proj",
|
| 360 |
+
"language_model.model.layers.50.self_attn.q_proj",
|
| 361 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
| 362 |
+
"language_model.model.layers.26.self_attn.k_proj",
|
| 363 |
+
"language_model.model.layers.1.self_attn.k_proj",
|
| 364 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 365 |
+
"language_model.model.layers.9.self_attn.k_proj",
|
| 366 |
+
"language_model.model.layers.18.mlp.down_proj",
|
| 367 |
+
"language_model.model.layers.33.mlp.down_proj",
|
| 368 |
+
"language_model.model.layers.59.self_attn.q_proj",
|
| 369 |
+
"language_model.model.layers.11.mlp.down_proj",
|
| 370 |
+
"language_model.model.layers.61.mlp.up_proj",
|
| 371 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
| 372 |
+
"language_model.model.layers.30.self_attn.k_proj",
|
| 373 |
+
"language_model.model.layers.14.self_attn.o_proj",
|
| 374 |
+
"language_model.model.layers.47.mlp.down_proj",
|
| 375 |
+
"language_model.model.layers.16.self_attn.v_proj",
|
| 376 |
+
"language_model.model.layers.40.self_attn.o_proj",
|
| 377 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
| 378 |
+
"language_model.model.layers.54.mlp.down_proj",
|
| 379 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
| 380 |
+
"language_model.model.layers.61.self_attn.v_proj",
|
| 381 |
+
"language_model.model.layers.42.self_attn.k_proj",
|
| 382 |
+
"language_model.model.layers.44.self_attn.q_proj",
|
| 383 |
+
"language_model.model.layers.3.mlp.up_proj",
|
| 384 |
+
"language_model.model.layers.58.self_attn.k_proj",
|
| 385 |
+
"language_model.model.layers.54.mlp.up_proj",
|
| 386 |
+
"language_model.model.layers.59.mlp.down_proj",
|
| 387 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 388 |
+
"language_model.model.layers.33.self_attn.q_proj",
|
| 389 |
+
"language_model.model.layers.43.mlp.up_proj",
|
| 390 |
+
"language_model.model.layers.48.self_attn.q_proj",
|
| 391 |
+
"language_model.model.layers.0.self_attn.k_proj",
|
| 392 |
+
"language_model.model.layers.22.self_attn.k_proj",
|
| 393 |
+
"language_model.model.layers.49.self_attn.q_proj",
|
| 394 |
+
"language_model.model.layers.43.self_attn.v_proj",
|
| 395 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
| 396 |
+
"language_model.model.layers.38.mlp.up_proj",
|
| 397 |
+
"language_model.model.layers.1.self_attn.v_proj",
|
| 398 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
| 399 |
+
"language_model.model.layers.56.mlp.gate_proj",
|
| 400 |
+
"language_model.model.layers.50.self_attn.v_proj",
|
| 401 |
+
"language_model.model.layers.29.self_attn.k_proj",
|
| 402 |
+
"language_model.model.layers.8.mlp.gate_proj",
|
| 403 |
+
"language_model.model.layers.34.self_attn.v_proj",
|
| 404 |
+
"language_model.model.layers.20.self_attn.o_proj",
|
| 405 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
| 406 |
+
"language_model.model.layers.37.self_attn.v_proj",
|
| 407 |
+
"language_model.model.layers.4.self_attn.q_proj",
|
| 408 |
+
"language_model.model.layers.55.mlp.down_proj",
|
| 409 |
+
"language_model.model.layers.45.self_attn.v_proj",
|
| 410 |
+
"language_model.model.layers.61.mlp.gate_proj",
|
| 411 |
+
"language_model.model.layers.0.self_attn.o_proj",
|
| 412 |
+
"language_model.model.layers.37.self_attn.k_proj",
|
| 413 |
+
"language_model.model.layers.51.self_attn.k_proj",
|
| 414 |
+
"language_model.model.layers.38.mlp.gate_proj",
|
| 415 |
+
"language_model.model.layers.26.mlp.down_proj",
|
| 416 |
+
"language_model.model.layers.48.self_attn.k_proj",
|
| 417 |
+
"language_model.model.layers.39.self_attn.q_proj",
|
| 418 |
+
"language_model.model.layers.45.mlp.gate_proj",
|
| 419 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
| 420 |
+
"language_model.model.layers.11.mlp.up_proj",
|
| 421 |
+
"language_model.model.layers.34.mlp.down_proj",
|
| 422 |
+
"language_model.model.layers.0.self_attn.v_proj",
|
| 423 |
+
"language_model.model.layers.44.self_attn.k_proj",
|
| 424 |
+
"language_model.model.layers.16.self_attn.q_proj",
|
| 425 |
+
"language_model.model.layers.14.mlp.down_proj",
|
| 426 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 427 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
| 428 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
| 429 |
+
"language_model.model.layers.31.mlp.up_proj",
|
| 430 |
+
"language_model.model.layers.44.mlp.up_proj",
|
| 431 |
+
"language_model.model.layers.58.mlp.gate_proj",
|
| 432 |
+
"language_model.model.layers.26.self_attn.v_proj",
|
| 433 |
+
"language_model.model.layers.34.self_attn.o_proj",
|
| 434 |
+
"language_model.model.layers.19.mlp.up_proj",
|
| 435 |
+
"language_model.model.layers.2.self_attn.q_proj",
|
| 436 |
+
"language_model.model.layers.40.mlp.gate_proj",
|
| 437 |
+
"language_model.model.layers.32.mlp.up_proj",
|
| 438 |
+
"language_model.model.layers.33.mlp.up_proj",
|
| 439 |
+
"language_model.model.layers.4.self_attn.o_proj",
|
| 440 |
+
"language_model.model.layers.35.mlp.gate_proj",
|
| 441 |
+
"language_model.model.layers.18.self_attn.k_proj",
|
| 442 |
+
"language_model.model.layers.38.self_attn.k_proj",
|
| 443 |
+
"language_model.model.layers.49.self_attn.v_proj",
|
| 444 |
+
"language_model.model.layers.31.self_attn.o_proj",
|
| 445 |
+
"language_model.model.layers.55.self_attn.k_proj",
|
| 446 |
+
"language_model.model.layers.38.mlp.down_proj",
|
| 447 |
+
"language_model.model.layers.46.mlp.down_proj",
|
| 448 |
+
"language_model.model.layers.1.self_attn.o_proj",
|
| 449 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
| 450 |
+
"language_model.model.layers.33.mlp.gate_proj",
|
| 451 |
+
"language_model.model.layers.60.self_attn.q_proj",
|
| 452 |
+
"language_model.model.layers.39.self_attn.v_proj",
|
| 453 |
+
"language_model.model.layers.16.mlp.up_proj",
|
| 454 |
+
"language_model.model.layers.50.self_attn.k_proj",
|
| 455 |
+
"language_model.model.layers.12.self_attn.o_proj",
|
| 456 |
+
"language_model.model.layers.53.self_attn.q_proj"
|
| 457 |
+
],
|
| 458 |
+
"task_type": "CAUSAL_LM",
|
| 459 |
+
"use_dora": false,
|
| 460 |
+
"use_rslora": false
|
| 461 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28d3bb9ec26846a38315ef55c91527ebfcd4ad2feee687610369bb71ab7e710f
|
| 3 |
+
size 1816396048
|
checkpoint-100/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
checkpoint-100/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 3 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33d3e6dd0c9ea086a07267eb6551641761a77013e2c577deb5d65e54babad4f6
|
| 3 |
+
size 3633264318
|
checkpoint-100/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pan_and_scan": null,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
+
"image_seq_length": 256,
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"pan_and_scan_max_num_crops": null,
|
| 20 |
+
"pan_and_scan_min_crop_size": null,
|
| 21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
+
"processor_class": "Gemma3Processor",
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 896,
|
| 27 |
+
"width": 896
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-100/processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "Gemma3Processor"
|
| 4 |
+
}
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
| 3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d81ab8a94dd339ba2c70164a98109aa12d23e5aaba97bde0e815da1c698cbb56
|
| 3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<end_of_turn>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"boi_token": "<start_of_image>",
|
| 12 |
+
"bos_token": {
|
| 13 |
+
"content": "<bos>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eoi_token": "<end_of_image>",
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<eos>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"image_token": "<image_soft_token>",
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<pad>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"unk_token": {
|
| 36 |
+
"content": "<unk>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
}
|
| 42 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
checkpoint-100/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
checkpoint-100/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.6666666666666665,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.08333333333333333,
|
| 14 |
+
"grad_norm": 41.758705139160156,
|
| 15 |
+
"learning_rate": 4.9986614686909146e-05,
|
| 16 |
+
"loss": 39.5171,
|
| 17 |
+
"num_input_tokens_seen": 47056,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.16666666666666666,
|
| 22 |
+
"grad_norm": 35.72260665893555,
|
| 23 |
+
"learning_rate": 4.994647308096509e-05,
|
| 24 |
+
"loss": 3.2466,
|
| 25 |
+
"num_input_tokens_seen": 93544,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.25,
|
| 30 |
+
"grad_norm": 40.3800163269043,
|
| 31 |
+
"learning_rate": 4.987961816680492e-05,
|
| 32 |
+
"loss": 3.3122,
|
| 33 |
+
"num_input_tokens_seen": 141120,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.3333333333333333,
|
| 38 |
+
"grad_norm": 22.71551513671875,
|
| 39 |
+
"learning_rate": 4.9786121534345265e-05,
|
| 40 |
+
"loss": 3.0265,
|
| 41 |
+
"num_input_tokens_seen": 188544,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.4166666666666667,
|
| 46 |
+
"grad_norm": 16.711044311523438,
|
| 47 |
+
"learning_rate": 4.966608330212198e-05,
|
| 48 |
+
"loss": 2.6989,
|
| 49 |
+
"num_input_tokens_seen": 235128,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.5,
|
| 54 |
+
"grad_norm": 10.093056678771973,
|
| 55 |
+
"learning_rate": 4.951963201008076e-05,
|
| 56 |
+
"loss": 2.2284,
|
| 57 |
+
"num_input_tokens_seen": 281904,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5833333333333334,
|
| 62 |
+
"grad_norm": 12.554229736328125,
|
| 63 |
+
"learning_rate": 4.934692448193334e-05,
|
| 64 |
+
"loss": 2.2164,
|
| 65 |
+
"num_input_tokens_seen": 330096,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6666666666666666,
|
| 70 |
+
"grad_norm": 20.774412155151367,
|
| 71 |
+
"learning_rate": 4.914814565722671e-05,
|
| 72 |
+
"loss": 2.6854,
|
| 73 |
+
"num_input_tokens_seen": 376824,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.75,
|
| 78 |
+
"grad_norm": 12.924601554870605,
|
| 79 |
+
"learning_rate": 4.892350839330522e-05,
|
| 80 |
+
"loss": 2.4108,
|
| 81 |
+
"num_input_tokens_seen": 424048,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.8333333333333334,
|
| 86 |
+
"grad_norm": 23.568218231201172,
|
| 87 |
+
"learning_rate": 4.867325323737765e-05,
|
| 88 |
+
"loss": 2.419,
|
| 89 |
+
"num_input_tokens_seen": 470432,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.9166666666666666,
|
| 94 |
+
"grad_norm": 29.64082908630371,
|
| 95 |
+
"learning_rate": 4.839764816893315e-05,
|
| 96 |
+
"loss": 2.3183,
|
| 97 |
+
"num_input_tokens_seen": 517624,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.0,
|
| 102 |
+
"grad_norm": 17.5496883392334,
|
| 103 |
+
"learning_rate": 4.8096988312782174e-05,
|
| 104 |
+
"loss": 1.9734,
|
| 105 |
+
"num_input_tokens_seen": 564920,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.0833333333333333,
|
| 110 |
+
"grad_norm": 14.56460189819336,
|
| 111 |
+
"learning_rate": 4.7771595623029394e-05,
|
| 112 |
+
"loss": 1.8086,
|
| 113 |
+
"num_input_tokens_seen": 611240,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.1666666666666667,
|
| 118 |
+
"grad_norm": 11.394974708557129,
|
| 119 |
+
"learning_rate": 4.742181853831721e-05,
|
| 120 |
+
"loss": 2.4591,
|
| 121 |
+
"num_input_tokens_seen": 658904,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.25,
|
| 126 |
+
"grad_norm": 5.737662315368652,
|
| 127 |
+
"learning_rate": 4.7048031608708876e-05,
|
| 128 |
+
"loss": 1.7169,
|
| 129 |
+
"num_input_tokens_seen": 706480,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.3333333333333333,
|
| 134 |
+
"grad_norm": 18.580102920532227,
|
| 135 |
+
"learning_rate": 4.665063509461097e-05,
|
| 136 |
+
"loss": 1.809,
|
| 137 |
+
"num_input_tokens_seen": 752904,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.4166666666666667,
|
| 142 |
+
"grad_norm": 18.77831268310547,
|
| 143 |
+
"learning_rate": 4.6230054538164474e-05,
|
| 144 |
+
"loss": 2.3907,
|
| 145 |
+
"num_input_tokens_seen": 800304,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.5,
|
| 150 |
+
"grad_norm": 7.019700527191162,
|
| 151 |
+
"learning_rate": 4.5786740307563636e-05,
|
| 152 |
+
"loss": 2.0662,
|
| 153 |
+
"num_input_tokens_seen": 846792,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.5833333333333335,
|
| 158 |
+
"grad_norm": 12.335309028625488,
|
| 159 |
+
"learning_rate": 4.5321167114790385e-05,
|
| 160 |
+
"loss": 2.0185,
|
| 161 |
+
"num_input_tokens_seen": 894552,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.6666666666666665,
|
| 166 |
+
"grad_norm": 8.229971885681152,
|
| 167 |
+
"learning_rate": 4.4833833507280884e-05,
|
| 168 |
+
"loss": 1.9831,
|
| 169 |
+
"num_input_tokens_seen": 941040,
|
| 170 |
+
"step": 100
|
| 171 |
+
}
|
| 172 |
+
],
|
| 173 |
+
"logging_steps": 5,
|
| 174 |
+
"max_steps": 480,
|
| 175 |
+
"num_input_tokens_seen": 941040,
|
| 176 |
+
"num_train_epochs": 8,
|
| 177 |
+
"save_steps": 100,
|
| 178 |
+
"stateful_callbacks": {
|
| 179 |
+
"TrainerControl": {
|
| 180 |
+
"args": {
|
| 181 |
+
"should_epoch_stop": false,
|
| 182 |
+
"should_evaluate": false,
|
| 183 |
+
"should_log": false,
|
| 184 |
+
"should_save": true,
|
| 185 |
+
"should_training_stop": false
|
| 186 |
+
},
|
| 187 |
+
"attributes": {}
|
| 188 |
+
}
|
| 189 |
+
},
|
| 190 |
+
"total_flos": 1.4946796550409984e+17,
|
| 191 |
+
"train_batch_size": 1,
|
| 192 |
+
"trial_name": null,
|
| 193 |
+
"trial_params": null
|
| 194 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01cf6a1b3597e72bc7b90c88ce73fa75eed9ace24c5f542bd93a792085dd5c9c
|
| 3 |
+
size 5688
|
checkpoint-200/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-3-27b-it
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-27b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"language_model.model.layers.42.self_attn.q_proj",
|
| 24 |
+
"language_model.model.layers.51.mlp.up_proj",
|
| 25 |
+
"language_model.model.layers.51.mlp.down_proj",
|
| 26 |
+
"language_model.model.layers.30.mlp.up_proj",
|
| 27 |
+
"language_model.model.layers.47.self_attn.q_proj",
|
| 28 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
| 29 |
+
"language_model.model.layers.25.self_attn.q_proj",
|
| 30 |
+
"language_model.model.layers.26.self_attn.q_proj",
|
| 31 |
+
"language_model.model.layers.27.mlp.down_proj",
|
| 32 |
+
"language_model.model.layers.9.self_attn.q_proj",
|
| 33 |
+
"language_model.model.layers.45.self_attn.q_proj",
|
| 34 |
+
"language_model.model.layers.51.self_attn.o_proj",
|
| 35 |
+
"language_model.model.layers.0.self_attn.q_proj",
|
| 36 |
+
"language_model.model.layers.21.mlp.up_proj",
|
| 37 |
+
"language_model.model.layers.61.self_attn.q_proj",
|
| 38 |
+
"language_model.model.layers.52.self_attn.k_proj",
|
| 39 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 40 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
| 41 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
| 42 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
| 43 |
+
"language_model.model.layers.38.self_attn.q_proj",
|
| 44 |
+
"language_model.model.layers.30.self_attn.q_proj",
|
| 45 |
+
"language_model.model.layers.22.mlp.down_proj",
|
| 46 |
+
"language_model.model.layers.46.self_attn.q_proj",
|
| 47 |
+
"language_model.model.layers.54.mlp.gate_proj",
|
| 48 |
+
"language_model.model.layers.49.mlp.up_proj",
|
| 49 |
+
"language_model.model.layers.35.self_attn.q_proj",
|
| 50 |
+
"language_model.model.layers.18.self_attn.o_proj",
|
| 51 |
+
"language_model.model.layers.33.self_attn.v_proj",
|
| 52 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
| 53 |
+
"language_model.model.layers.7.self_attn.q_proj",
|
| 54 |
+
"language_model.model.layers.50.self_attn.o_proj",
|
| 55 |
+
"language_model.model.layers.36.self_attn.o_proj",
|
| 56 |
+
"language_model.model.layers.20.self_attn.k_proj",
|
| 57 |
+
"language_model.model.layers.47.self_attn.k_proj",
|
| 58 |
+
"language_model.model.layers.32.mlp.gate_proj",
|
| 59 |
+
"language_model.model.layers.1.self_attn.q_proj",
|
| 60 |
+
"language_model.model.layers.7.mlp.up_proj",
|
| 61 |
+
"language_model.model.layers.36.mlp.gate_proj",
|
| 62 |
+
"language_model.model.layers.45.self_attn.k_proj",
|
| 63 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
| 64 |
+
"language_model.model.layers.58.self_attn.o_proj",
|
| 65 |
+
"language_model.model.layers.43.self_attn.q_proj",
|
| 66 |
+
"language_model.model.layers.60.self_attn.v_proj",
|
| 67 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
| 68 |
+
"language_model.model.layers.60.self_attn.o_proj",
|
| 69 |
+
"language_model.model.layers.29.self_attn.o_proj",
|
| 70 |
+
"language_model.model.layers.31.mlp.gate_proj",
|
| 71 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
| 72 |
+
"language_model.model.layers.6.self_attn.k_proj",
|
| 73 |
+
"language_model.model.layers.56.self_attn.k_proj",
|
| 74 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
| 75 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 76 |
+
"language_model.model.layers.12.self_attn.v_proj",
|
| 77 |
+
"language_model.model.layers.22.self_attn.o_proj",
|
| 78 |
+
"language_model.model.layers.2.self_attn.o_proj",
|
| 79 |
+
"language_model.model.layers.8.mlp.up_proj",
|
| 80 |
+
"language_model.model.layers.57.mlp.down_proj",
|
| 81 |
+
"language_model.model.layers.57.mlp.up_proj",
|
| 82 |
+
"language_model.model.layers.19.mlp.down_proj",
|
| 83 |
+
"language_model.model.layers.16.self_attn.k_proj",
|
| 84 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
| 85 |
+
"language_model.model.layers.17.mlp.down_proj",
|
| 86 |
+
"language_model.model.layers.35.mlp.down_proj",
|
| 87 |
+
"language_model.model.layers.39.self_attn.k_proj",
|
| 88 |
+
"language_model.model.layers.46.mlp.up_proj",
|
| 89 |
+
"language_model.model.layers.52.self_attn.q_proj",
|
| 90 |
+
"language_model.model.layers.8.self_attn.v_proj",
|
| 91 |
+
"language_model.model.layers.8.mlp.down_proj",
|
| 92 |
+
"language_model.model.layers.8.self_attn.o_proj",
|
| 93 |
+
"language_model.model.layers.7.mlp.down_proj",
|
| 94 |
+
"language_model.model.layers.24.self_attn.o_proj",
|
| 95 |
+
"language_model.model.layers.52.mlp.gate_proj",
|
| 96 |
+
"language_model.model.layers.38.self_attn.o_proj",
|
| 97 |
+
"language_model.model.layers.9.self_attn.v_proj",
|
| 98 |
+
"language_model.model.layers.56.self_attn.v_proj",
|
| 99 |
+
"language_model.model.layers.42.mlp.gate_proj",
|
| 100 |
+
"language_model.model.layers.57.self_attn.o_proj",
|
| 101 |
+
"language_model.model.layers.18.self_attn.v_proj",
|
| 102 |
+
"language_model.model.layers.47.mlp.gate_proj",
|
| 103 |
+
"language_model.model.layers.59.self_attn.v_proj",
|
| 104 |
+
"language_model.model.layers.27.mlp.up_proj",
|
| 105 |
+
"language_model.model.layers.36.self_attn.k_proj",
|
| 106 |
+
"language_model.model.layers.43.mlp.gate_proj",
|
| 107 |
+
"language_model.model.layers.54.self_attn.k_proj",
|
| 108 |
+
"language_model.model.layers.28.self_attn.q_proj",
|
| 109 |
+
"language_model.model.layers.9.mlp.down_proj",
|
| 110 |
+
"language_model.model.layers.36.self_attn.v_proj",
|
| 111 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
| 112 |
+
"language_model.model.layers.26.self_attn.o_proj",
|
| 113 |
+
"language_model.model.layers.17.mlp.up_proj",
|
| 114 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
| 115 |
+
"language_model.model.layers.57.self_attn.k_proj",
|
| 116 |
+
"language_model.model.layers.10.mlp.down_proj",
|
| 117 |
+
"language_model.model.layers.25.self_attn.o_proj",
|
| 118 |
+
"language_model.model.layers.55.self_attn.o_proj",
|
| 119 |
+
"language_model.model.layers.6.self_attn.o_proj",
|
| 120 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 121 |
+
"language_model.model.layers.14.self_attn.q_proj",
|
| 122 |
+
"language_model.model.layers.52.mlp.up_proj",
|
| 123 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
| 124 |
+
"language_model.model.layers.52.self_attn.v_proj",
|
| 125 |
+
"language_model.model.layers.17.self_attn.q_proj",
|
| 126 |
+
"language_model.model.layers.47.self_attn.v_proj",
|
| 127 |
+
"language_model.model.layers.29.mlp.up_proj",
|
| 128 |
+
"language_model.model.layers.13.self_attn.k_proj",
|
| 129 |
+
"language_model.model.layers.41.self_attn.v_proj",
|
| 130 |
+
"language_model.model.layers.4.mlp.up_proj",
|
| 131 |
+
"language_model.model.layers.46.self_attn.v_proj",
|
| 132 |
+
"language_model.model.layers.21.self_attn.q_proj",
|
| 133 |
+
"language_model.model.layers.57.mlp.gate_proj",
|
| 134 |
+
"language_model.model.layers.16.self_attn.o_proj",
|
| 135 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
| 136 |
+
"language_model.model.layers.41.self_attn.o_proj",
|
| 137 |
+
"language_model.model.layers.54.self_attn.v_proj",
|
| 138 |
+
"language_model.model.layers.42.self_attn.o_proj",
|
| 139 |
+
"language_model.model.layers.5.self_attn.q_proj",
|
| 140 |
+
"language_model.model.layers.45.self_attn.o_proj",
|
| 141 |
+
"language_model.model.layers.56.self_attn.q_proj",
|
| 142 |
+
"language_model.model.layers.22.self_attn.v_proj",
|
| 143 |
+
"language_model.model.layers.12.mlp.down_proj",
|
| 144 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
| 145 |
+
"language_model.model.layers.61.self_attn.o_proj",
|
| 146 |
+
"language_model.model.layers.32.self_attn.q_proj",
|
| 147 |
+
"language_model.model.layers.33.self_attn.k_proj",
|
| 148 |
+
"language_model.model.layers.34.mlp.up_proj",
|
| 149 |
+
"language_model.model.layers.25.mlp.down_proj",
|
| 150 |
+
"language_model.model.layers.61.self_attn.k_proj",
|
| 151 |
+
"language_model.model.layers.30.mlp.down_proj",
|
| 152 |
+
"language_model.model.layers.21.self_attn.o_proj",
|
| 153 |
+
"language_model.model.layers.30.self_attn.v_proj",
|
| 154 |
+
"language_model.model.layers.46.self_attn.k_proj",
|
| 155 |
+
"language_model.model.layers.4.self_attn.v_proj",
|
| 156 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 157 |
+
"language_model.model.layers.52.self_attn.o_proj",
|
| 158 |
+
"language_model.model.layers.61.mlp.down_proj",
|
| 159 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
| 160 |
+
"language_model.model.layers.37.mlp.down_proj",
|
| 161 |
+
"language_model.model.layers.18.mlp.up_proj",
|
| 162 |
+
"language_model.model.layers.5.mlp.up_proj",
|
| 163 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
| 164 |
+
"language_model.model.layers.44.mlp.down_proj",
|
| 165 |
+
"language_model.model.layers.58.self_attn.v_proj",
|
| 166 |
+
"language_model.model.layers.58.self_attn.q_proj",
|
| 167 |
+
"language_model.model.layers.60.mlp.down_proj",
|
| 168 |
+
"language_model.model.layers.48.mlp.gate_proj",
|
| 169 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
| 170 |
+
"language_model.model.layers.41.self_attn.k_proj",
|
| 171 |
+
"language_model.model.layers.40.self_attn.k_proj",
|
| 172 |
+
"language_model.model.layers.34.self_attn.q_proj",
|
| 173 |
+
"language_model.model.layers.43.mlp.down_proj",
|
| 174 |
+
"language_model.model.layers.17.self_attn.k_proj",
|
| 175 |
+
"language_model.model.layers.37.mlp.up_proj",
|
| 176 |
+
"language_model.model.layers.12.mlp.up_proj",
|
| 177 |
+
"language_model.model.layers.17.self_attn.v_proj",
|
| 178 |
+
"language_model.model.layers.31.mlp.down_proj",
|
| 179 |
+
"language_model.model.layers.48.self_attn.o_proj",
|
| 180 |
+
"language_model.model.layers.3.mlp.down_proj",
|
| 181 |
+
"language_model.model.layers.46.mlp.gate_proj",
|
| 182 |
+
"language_model.model.layers.32.self_attn.o_proj",
|
| 183 |
+
"language_model.model.layers.24.self_attn.q_proj",
|
| 184 |
+
"language_model.model.layers.58.mlp.up_proj",
|
| 185 |
+
"language_model.model.layers.5.self_attn.v_proj",
|
| 186 |
+
"language_model.model.layers.44.self_attn.v_proj",
|
| 187 |
+
"language_model.model.layers.48.self_attn.v_proj",
|
| 188 |
+
"language_model.model.layers.10.self_attn.q_proj",
|
| 189 |
+
"language_model.model.layers.10.mlp.up_proj",
|
| 190 |
+
"language_model.model.layers.48.mlp.up_proj",
|
| 191 |
+
"language_model.model.layers.5.mlp.down_proj",
|
| 192 |
+
"language_model.model.layers.28.mlp.up_proj",
|
| 193 |
+
"language_model.model.layers.47.self_attn.o_proj",
|
| 194 |
+
"language_model.model.layers.8.self_attn.q_proj",
|
| 195 |
+
"language_model.model.layers.53.mlp.gate_proj",
|
| 196 |
+
"language_model.model.layers.57.self_attn.v_proj",
|
| 197 |
+
"language_model.model.layers.9.mlp.gate_proj",
|
| 198 |
+
"language_model.model.layers.2.self_attn.k_proj",
|
| 199 |
+
"language_model.model.layers.5.self_attn.k_proj",
|
| 200 |
+
"language_model.model.layers.34.self_attn.k_proj",
|
| 201 |
+
"language_model.model.layers.17.self_attn.o_proj",
|
| 202 |
+
"language_model.model.layers.21.self_attn.k_proj",
|
| 203 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
| 204 |
+
"language_model.model.layers.48.mlp.down_proj",
|
| 205 |
+
"language_model.model.layers.25.self_attn.v_proj",
|
| 206 |
+
"language_model.model.layers.44.mlp.gate_proj",
|
| 207 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 208 |
+
"language_model.model.layers.4.mlp.down_proj",
|
| 209 |
+
"language_model.model.layers.13.self_attn.v_proj",
|
| 210 |
+
"language_model.model.layers.55.mlp.up_proj",
|
| 211 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
| 212 |
+
"language_model.model.layers.26.mlp.up_proj",
|
| 213 |
+
"language_model.model.layers.50.mlp.gate_proj",
|
| 214 |
+
"language_model.model.layers.56.mlp.down_proj",
|
| 215 |
+
"language_model.model.layers.21.self_attn.v_proj",
|
| 216 |
+
"language_model.model.layers.18.mlp.gate_proj",
|
| 217 |
+
"language_model.model.layers.22.self_attn.q_proj",
|
| 218 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
| 219 |
+
"language_model.model.layers.53.mlp.down_proj",
|
| 220 |
+
"language_model.model.layers.22.mlp.up_proj",
|
| 221 |
+
"language_model.model.layers.56.self_attn.o_proj",
|
| 222 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
| 223 |
+
"language_model.model.layers.14.self_attn.v_proj",
|
| 224 |
+
"language_model.model.layers.29.self_attn.v_proj",
|
| 225 |
+
"language_model.model.layers.50.mlp.up_proj",
|
| 226 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
| 227 |
+
"language_model.model.layers.23.mlp.down_proj",
|
| 228 |
+
"language_model.model.layers.53.self_attn.k_proj",
|
| 229 |
+
"language_model.model.layers.24.mlp.up_proj",
|
| 230 |
+
"language_model.model.layers.55.mlp.gate_proj",
|
| 231 |
+
"language_model.model.layers.39.mlp.up_proj",
|
| 232 |
+
"language_model.model.layers.59.self_attn.o_proj",
|
| 233 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
| 234 |
+
"language_model.model.layers.41.mlp.down_proj",
|
| 235 |
+
"language_model.model.layers.8.self_attn.k_proj",
|
| 236 |
+
"language_model.model.layers.54.self_attn.q_proj",
|
| 237 |
+
"language_model.model.layers.32.self_attn.v_proj",
|
| 238 |
+
"language_model.model.layers.35.self_attn.o_proj",
|
| 239 |
+
"language_model.model.layers.33.self_attn.o_proj",
|
| 240 |
+
"language_model.model.layers.28.self_attn.v_proj",
|
| 241 |
+
"language_model.model.layers.6.mlp.up_proj",
|
| 242 |
+
"language_model.model.layers.40.self_attn.q_proj",
|
| 243 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
| 244 |
+
"language_model.model.layers.10.self_attn.k_proj",
|
| 245 |
+
"language_model.model.layers.37.self_attn.q_proj",
|
| 246 |
+
"language_model.model.layers.49.mlp.down_proj",
|
| 247 |
+
"language_model.model.layers.6.self_attn.q_proj",
|
| 248 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
| 249 |
+
"language_model.model.layers.45.mlp.down_proj",
|
| 250 |
+
"language_model.model.layers.51.self_attn.v_proj",
|
| 251 |
+
"language_model.model.layers.28.self_attn.k_proj",
|
| 252 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
| 253 |
+
"language_model.model.layers.30.self_attn.o_proj",
|
| 254 |
+
"language_model.model.layers.59.mlp.up_proj",
|
| 255 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
| 256 |
+
"language_model.model.layers.6.mlp.down_proj",
|
| 257 |
+
"language_model.model.layers.9.mlp.up_proj",
|
| 258 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
| 259 |
+
"language_model.model.layers.37.mlp.gate_proj",
|
| 260 |
+
"language_model.model.layers.43.self_attn.k_proj",
|
| 261 |
+
"language_model.model.layers.46.self_attn.o_proj",
|
| 262 |
+
"language_model.model.layers.12.self_attn.k_proj",
|
| 263 |
+
"language_model.model.layers.13.mlp.down_proj",
|
| 264 |
+
"language_model.model.layers.4.self_attn.k_proj",
|
| 265 |
+
"language_model.model.layers.49.self_attn.k_proj",
|
| 266 |
+
"language_model.model.layers.51.self_attn.q_proj",
|
| 267 |
+
"language_model.model.layers.52.mlp.down_proj",
|
| 268 |
+
"language_model.model.layers.24.self_attn.v_proj",
|
| 269 |
+
"language_model.model.layers.42.self_attn.v_proj",
|
| 270 |
+
"language_model.model.layers.53.self_attn.o_proj",
|
| 271 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
| 272 |
+
"language_model.model.layers.40.self_attn.v_proj",
|
| 273 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
| 274 |
+
"language_model.model.layers.40.mlp.up_proj",
|
| 275 |
+
"language_model.model.layers.49.self_attn.o_proj",
|
| 276 |
+
"language_model.model.layers.42.mlp.down_proj",
|
| 277 |
+
"language_model.model.layers.41.self_attn.q_proj",
|
| 278 |
+
"language_model.model.layers.42.mlp.up_proj",
|
| 279 |
+
"language_model.model.layers.28.mlp.down_proj",
|
| 280 |
+
"language_model.model.layers.2.self_attn.v_proj",
|
| 281 |
+
"language_model.model.layers.23.mlp.up_proj",
|
| 282 |
+
"language_model.model.layers.36.mlp.down_proj",
|
| 283 |
+
"language_model.model.layers.16.mlp.down_proj",
|
| 284 |
+
"language_model.model.layers.43.self_attn.o_proj",
|
| 285 |
+
"language_model.model.layers.20.self_attn.q_proj",
|
| 286 |
+
"language_model.model.layers.51.mlp.gate_proj",
|
| 287 |
+
"language_model.model.layers.15.mlp.down_proj",
|
| 288 |
+
"language_model.model.layers.10.self_attn.v_proj",
|
| 289 |
+
"language_model.model.layers.35.self_attn.v_proj",
|
| 290 |
+
"language_model.model.layers.59.self_attn.k_proj",
|
| 291 |
+
"language_model.model.layers.47.mlp.up_proj",
|
| 292 |
+
"language_model.model.layers.38.self_attn.v_proj",
|
| 293 |
+
"language_model.model.layers.18.self_attn.q_proj",
|
| 294 |
+
"language_model.model.layers.25.self_attn.k_proj",
|
| 295 |
+
"language_model.model.layers.36.self_attn.q_proj",
|
| 296 |
+
"language_model.model.layers.40.mlp.down_proj",
|
| 297 |
+
"language_model.model.layers.39.mlp.down_proj",
|
| 298 |
+
"language_model.model.layers.41.mlp.gate_proj",
|
| 299 |
+
"language_model.model.layers.29.self_attn.q_proj",
|
| 300 |
+
"language_model.model.layers.56.mlp.up_proj",
|
| 301 |
+
"language_model.model.layers.14.mlp.up_proj",
|
| 302 |
+
"language_model.model.layers.29.mlp.down_proj",
|
| 303 |
+
"language_model.model.layers.13.mlp.up_proj",
|
| 304 |
+
"language_model.model.layers.28.mlp.gate_proj",
|
| 305 |
+
"language_model.model.layers.45.mlp.up_proj",
|
| 306 |
+
"language_model.model.layers.13.self_attn.o_proj",
|
| 307 |
+
"language_model.model.layers.20.self_attn.v_proj",
|
| 308 |
+
"language_model.model.layers.54.self_attn.o_proj",
|
| 309 |
+
"language_model.model.layers.39.mlp.gate_proj",
|
| 310 |
+
"language_model.model.layers.25.mlp.up_proj",
|
| 311 |
+
"language_model.model.layers.53.mlp.up_proj",
|
| 312 |
+
"language_model.model.layers.50.mlp.down_proj",
|
| 313 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
| 314 |
+
"language_model.model.layers.59.mlp.gate_proj",
|
| 315 |
+
"language_model.model.layers.60.mlp.up_proj",
|
| 316 |
+
"language_model.model.layers.24.mlp.down_proj",
|
| 317 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
| 318 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
| 319 |
+
"language_model.model.layers.60.mlp.gate_proj",
|
| 320 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
| 321 |
+
"language_model.model.layers.24.self_attn.k_proj",
|
| 322 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
| 323 |
+
"language_model.model.layers.13.self_attn.q_proj",
|
| 324 |
+
"language_model.model.layers.44.self_attn.o_proj",
|
| 325 |
+
"language_model.model.layers.32.mlp.down_proj",
|
| 326 |
+
"language_model.model.layers.20.mlp.up_proj",
|
| 327 |
+
"language_model.model.layers.10.self_attn.o_proj",
|
| 328 |
+
"language_model.model.layers.41.mlp.up_proj",
|
| 329 |
+
"language_model.model.layers.49.mlp.gate_proj",
|
| 330 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 331 |
+
"language_model.model.layers.39.self_attn.o_proj",
|
| 332 |
+
"language_model.model.layers.14.self_attn.k_proj",
|
| 333 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
| 334 |
+
"language_model.model.layers.7.self_attn.o_proj",
|
| 335 |
+
"language_model.model.layers.21.mlp.down_proj",
|
| 336 |
+
"language_model.model.layers.35.mlp.up_proj",
|
| 337 |
+
"language_model.model.layers.20.mlp.down_proj",
|
| 338 |
+
"language_model.model.layers.15.mlp.up_proj",
|
| 339 |
+
"language_model.model.layers.53.self_attn.v_proj",
|
| 340 |
+
"language_model.model.layers.9.self_attn.o_proj",
|
| 341 |
+
"language_model.model.layers.60.self_attn.k_proj",
|
| 342 |
+
"language_model.model.layers.5.self_attn.o_proj",
|
| 343 |
+
"language_model.model.layers.58.mlp.down_proj",
|
| 344 |
+
"language_model.model.layers.6.self_attn.v_proj",
|
| 345 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.34.mlp.gate_proj",
|
| 347 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
| 348 |
+
"language_model.model.layers.36.mlp.up_proj",
|
| 349 |
+
"language_model.model.layers.57.self_attn.q_proj",
|
| 350 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
| 351 |
+
"language_model.model.layers.28.self_attn.o_proj",
|
| 352 |
+
"language_model.model.layers.55.self_attn.q_proj",
|
| 353 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
| 354 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
| 355 |
+
"language_model.model.layers.32.self_attn.k_proj",
|
| 356 |
+
"language_model.model.layers.12.self_attn.q_proj",
|
| 357 |
+
"language_model.model.layers.35.self_attn.k_proj",
|
| 358 |
+
"language_model.model.layers.37.self_attn.o_proj",
|
| 359 |
+
"language_model.model.layers.55.self_attn.v_proj",
|
| 360 |
+
"language_model.model.layers.50.self_attn.q_proj",
|
| 361 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
| 362 |
+
"language_model.model.layers.26.self_attn.k_proj",
|
| 363 |
+
"language_model.model.layers.1.self_attn.k_proj",
|
| 364 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 365 |
+
"language_model.model.layers.9.self_attn.k_proj",
|
| 366 |
+
"language_model.model.layers.18.mlp.down_proj",
|
| 367 |
+
"language_model.model.layers.33.mlp.down_proj",
|
| 368 |
+
"language_model.model.layers.59.self_attn.q_proj",
|
| 369 |
+
"language_model.model.layers.11.mlp.down_proj",
|
| 370 |
+
"language_model.model.layers.61.mlp.up_proj",
|
| 371 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
| 372 |
+
"language_model.model.layers.30.self_attn.k_proj",
|
| 373 |
+
"language_model.model.layers.14.self_attn.o_proj",
|
| 374 |
+
"language_model.model.layers.47.mlp.down_proj",
|
| 375 |
+
"language_model.model.layers.16.self_attn.v_proj",
|
| 376 |
+
"language_model.model.layers.40.self_attn.o_proj",
|
| 377 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
| 378 |
+
"language_model.model.layers.54.mlp.down_proj",
|
| 379 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
| 380 |
+
"language_model.model.layers.61.self_attn.v_proj",
|
| 381 |
+
"language_model.model.layers.42.self_attn.k_proj",
|
| 382 |
+
"language_model.model.layers.44.self_attn.q_proj",
|
| 383 |
+
"language_model.model.layers.3.mlp.up_proj",
|
| 384 |
+
"language_model.model.layers.58.self_attn.k_proj",
|
| 385 |
+
"language_model.model.layers.54.mlp.up_proj",
|
| 386 |
+
"language_model.model.layers.59.mlp.down_proj",
|
| 387 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 388 |
+
"language_model.model.layers.33.self_attn.q_proj",
|
| 389 |
+
"language_model.model.layers.43.mlp.up_proj",
|
| 390 |
+
"language_model.model.layers.48.self_attn.q_proj",
|
| 391 |
+
"language_model.model.layers.0.self_attn.k_proj",
|
| 392 |
+
"language_model.model.layers.22.self_attn.k_proj",
|
| 393 |
+
"language_model.model.layers.49.self_attn.q_proj",
|
| 394 |
+
"language_model.model.layers.43.self_attn.v_proj",
|
| 395 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
| 396 |
+
"language_model.model.layers.38.mlp.up_proj",
|
| 397 |
+
"language_model.model.layers.1.self_attn.v_proj",
|
| 398 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
| 399 |
+
"language_model.model.layers.56.mlp.gate_proj",
|
| 400 |
+
"language_model.model.layers.50.self_attn.v_proj",
|
| 401 |
+
"language_model.model.layers.29.self_attn.k_proj",
|
| 402 |
+
"language_model.model.layers.8.mlp.gate_proj",
|
| 403 |
+
"language_model.model.layers.34.self_attn.v_proj",
|
| 404 |
+
"language_model.model.layers.20.self_attn.o_proj",
|
| 405 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
| 406 |
+
"language_model.model.layers.37.self_attn.v_proj",
|
| 407 |
+
"language_model.model.layers.4.self_attn.q_proj",
|
| 408 |
+
"language_model.model.layers.55.mlp.down_proj",
|
| 409 |
+
"language_model.model.layers.45.self_attn.v_proj",
|
| 410 |
+
"language_model.model.layers.61.mlp.gate_proj",
|
| 411 |
+
"language_model.model.layers.0.self_attn.o_proj",
|
| 412 |
+
"language_model.model.layers.37.self_attn.k_proj",
|
| 413 |
+
"language_model.model.layers.51.self_attn.k_proj",
|
| 414 |
+
"language_model.model.layers.38.mlp.gate_proj",
|
| 415 |
+
"language_model.model.layers.26.mlp.down_proj",
|
| 416 |
+
"language_model.model.layers.48.self_attn.k_proj",
|
| 417 |
+
"language_model.model.layers.39.self_attn.q_proj",
|
| 418 |
+
"language_model.model.layers.45.mlp.gate_proj",
|
| 419 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
| 420 |
+
"language_model.model.layers.11.mlp.up_proj",
|
| 421 |
+
"language_model.model.layers.34.mlp.down_proj",
|
| 422 |
+
"language_model.model.layers.0.self_attn.v_proj",
|
| 423 |
+
"language_model.model.layers.44.self_attn.k_proj",
|
| 424 |
+
"language_model.model.layers.16.self_attn.q_proj",
|
| 425 |
+
"language_model.model.layers.14.mlp.down_proj",
|
| 426 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 427 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
| 428 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
| 429 |
+
"language_model.model.layers.31.mlp.up_proj",
|
| 430 |
+
"language_model.model.layers.44.mlp.up_proj",
|
| 431 |
+
"language_model.model.layers.58.mlp.gate_proj",
|
| 432 |
+
"language_model.model.layers.26.self_attn.v_proj",
|
| 433 |
+
"language_model.model.layers.34.self_attn.o_proj",
|
| 434 |
+
"language_model.model.layers.19.mlp.up_proj",
|
| 435 |
+
"language_model.model.layers.2.self_attn.q_proj",
|
| 436 |
+
"language_model.model.layers.40.mlp.gate_proj",
|
| 437 |
+
"language_model.model.layers.32.mlp.up_proj",
|
| 438 |
+
"language_model.model.layers.33.mlp.up_proj",
|
| 439 |
+
"language_model.model.layers.4.self_attn.o_proj",
|
| 440 |
+
"language_model.model.layers.35.mlp.gate_proj",
|
| 441 |
+
"language_model.model.layers.18.self_attn.k_proj",
|
| 442 |
+
"language_model.model.layers.38.self_attn.k_proj",
|
| 443 |
+
"language_model.model.layers.49.self_attn.v_proj",
|
| 444 |
+
"language_model.model.layers.31.self_attn.o_proj",
|
| 445 |
+
"language_model.model.layers.55.self_attn.k_proj",
|
| 446 |
+
"language_model.model.layers.38.mlp.down_proj",
|
| 447 |
+
"language_model.model.layers.46.mlp.down_proj",
|
| 448 |
+
"language_model.model.layers.1.self_attn.o_proj",
|
| 449 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
| 450 |
+
"language_model.model.layers.33.mlp.gate_proj",
|
| 451 |
+
"language_model.model.layers.60.self_attn.q_proj",
|
| 452 |
+
"language_model.model.layers.39.self_attn.v_proj",
|
| 453 |
+
"language_model.model.layers.16.mlp.up_proj",
|
| 454 |
+
"language_model.model.layers.50.self_attn.k_proj",
|
| 455 |
+
"language_model.model.layers.12.self_attn.o_proj",
|
| 456 |
+
"language_model.model.layers.53.self_attn.q_proj"
|
| 457 |
+
],
|
| 458 |
+
"task_type": "CAUSAL_LM",
|
| 459 |
+
"use_dora": false,
|
| 460 |
+
"use_rslora": false
|
| 461 |
+
}
|
checkpoint-200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:009b159f26fd9d9e8c4c7ed6d01d26749efd9295d27b880e1aadc825d5462ce6
|
| 3 |
+
size 1816396048
|
checkpoint-200/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
checkpoint-200/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 3 |
+
}
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c914241914d379ce858d82dc1a8626f3b1d194e7bd0f4f9b844addae3ecc1fdd
|
| 3 |
+
size 3633264318
|
checkpoint-200/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pan_and_scan": null,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
+
"image_seq_length": 256,
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"pan_and_scan_max_num_crops": null,
|
| 20 |
+
"pan_and_scan_min_crop_size": null,
|
| 21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
+
"processor_class": "Gemma3Processor",
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 896,
|
| 27 |
+
"width": 896
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-200/processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "Gemma3Processor"
|
| 4 |
+
}
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
|
| 3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a24a2c55bac51e60edc32b47e808693c5846d18a8adef6c0e9b1eb88e079f0f
|
| 3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<end_of_turn>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"boi_token": "<start_of_image>",
|
| 12 |
+
"bos_token": {
|
| 13 |
+
"content": "<bos>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eoi_token": "<end_of_image>",
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<eos>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"image_token": "<image_soft_token>",
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<pad>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"unk_token": {
|
| 36 |
+
"content": "<unk>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
}
|
| 42 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
checkpoint-200/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
checkpoint-200/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,354 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.3333333333333335,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.08333333333333333,
|
| 14 |
+
"grad_norm": 41.758705139160156,
|
| 15 |
+
"learning_rate": 4.9986614686909146e-05,
|
| 16 |
+
"loss": 39.5171,
|
| 17 |
+
"num_input_tokens_seen": 47056,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.16666666666666666,
|
| 22 |
+
"grad_norm": 35.72260665893555,
|
| 23 |
+
"learning_rate": 4.994647308096509e-05,
|
| 24 |
+
"loss": 3.2466,
|
| 25 |
+
"num_input_tokens_seen": 93544,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.25,
|
| 30 |
+
"grad_norm": 40.3800163269043,
|
| 31 |
+
"learning_rate": 4.987961816680492e-05,
|
| 32 |
+
"loss": 3.3122,
|
| 33 |
+
"num_input_tokens_seen": 141120,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.3333333333333333,
|
| 38 |
+
"grad_norm": 22.71551513671875,
|
| 39 |
+
"learning_rate": 4.9786121534345265e-05,
|
| 40 |
+
"loss": 3.0265,
|
| 41 |
+
"num_input_tokens_seen": 188544,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.4166666666666667,
|
| 46 |
+
"grad_norm": 16.711044311523438,
|
| 47 |
+
"learning_rate": 4.966608330212198e-05,
|
| 48 |
+
"loss": 2.6989,
|
| 49 |
+
"num_input_tokens_seen": 235128,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.5,
|
| 54 |
+
"grad_norm": 10.093056678771973,
|
| 55 |
+
"learning_rate": 4.951963201008076e-05,
|
| 56 |
+
"loss": 2.2284,
|
| 57 |
+
"num_input_tokens_seen": 281904,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5833333333333334,
|
| 62 |
+
"grad_norm": 12.554229736328125,
|
| 63 |
+
"learning_rate": 4.934692448193334e-05,
|
| 64 |
+
"loss": 2.2164,
|
| 65 |
+
"num_input_tokens_seen": 330096,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6666666666666666,
|
| 70 |
+
"grad_norm": 20.774412155151367,
|
| 71 |
+
"learning_rate": 4.914814565722671e-05,
|
| 72 |
+
"loss": 2.6854,
|
| 73 |
+
"num_input_tokens_seen": 376824,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.75,
|
| 78 |
+
"grad_norm": 12.924601554870605,
|
| 79 |
+
"learning_rate": 4.892350839330522e-05,
|
| 80 |
+
"loss": 2.4108,
|
| 81 |
+
"num_input_tokens_seen": 424048,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.8333333333333334,
|
| 86 |
+
"grad_norm": 23.568218231201172,
|
| 87 |
+
"learning_rate": 4.867325323737765e-05,
|
| 88 |
+
"loss": 2.419,
|
| 89 |
+
"num_input_tokens_seen": 470432,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.9166666666666666,
|
| 94 |
+
"grad_norm": 29.64082908630371,
|
| 95 |
+
"learning_rate": 4.839764816893315e-05,
|
| 96 |
+
"loss": 2.3183,
|
| 97 |
+
"num_input_tokens_seen": 517624,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.0,
|
| 102 |
+
"grad_norm": 17.5496883392334,
|
| 103 |
+
"learning_rate": 4.8096988312782174e-05,
|
| 104 |
+
"loss": 1.9734,
|
| 105 |
+
"num_input_tokens_seen": 564920,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.0833333333333333,
|
| 110 |
+
"grad_norm": 14.56460189819336,
|
| 111 |
+
"learning_rate": 4.7771595623029394e-05,
|
| 112 |
+
"loss": 1.8086,
|
| 113 |
+
"num_input_tokens_seen": 611240,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.1666666666666667,
|
| 118 |
+
"grad_norm": 11.394974708557129,
|
| 119 |
+
"learning_rate": 4.742181853831721e-05,
|
| 120 |
+
"loss": 2.4591,
|
| 121 |
+
"num_input_tokens_seen": 658904,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.25,
|
| 126 |
+
"grad_norm": 5.737662315368652,
|
| 127 |
+
"learning_rate": 4.7048031608708876e-05,
|
| 128 |
+
"loss": 1.7169,
|
| 129 |
+
"num_input_tokens_seen": 706480,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.3333333333333333,
|
| 134 |
+
"grad_norm": 18.580102920532227,
|
| 135 |
+
"learning_rate": 4.665063509461097e-05,
|
| 136 |
+
"loss": 1.809,
|
| 137 |
+
"num_input_tokens_seen": 752904,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.4166666666666667,
|
| 142 |
+
"grad_norm": 18.77831268310547,
|
| 143 |
+
"learning_rate": 4.6230054538164474e-05,
|
| 144 |
+
"loss": 2.3907,
|
| 145 |
+
"num_input_tokens_seen": 800304,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.5,
|
| 150 |
+
"grad_norm": 7.019700527191162,
|
| 151 |
+
"learning_rate": 4.5786740307563636e-05,
|
| 152 |
+
"loss": 2.0662,
|
| 153 |
+
"num_input_tokens_seen": 846792,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.5833333333333335,
|
| 158 |
+
"grad_norm": 12.335309028625488,
|
| 159 |
+
"learning_rate": 4.5321167114790385e-05,
|
| 160 |
+
"loss": 2.0185,
|
| 161 |
+
"num_input_tokens_seen": 894552,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.6666666666666665,
|
| 166 |
+
"grad_norm": 8.229971885681152,
|
| 167 |
+
"learning_rate": 4.4833833507280884e-05,
|
| 168 |
+
"loss": 1.9831,
|
| 169 |
+
"num_input_tokens_seen": 941040,
|
| 170 |
+
"step": 100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.75,
|
| 174 |
+
"grad_norm": 13.02308177947998,
|
| 175 |
+
"learning_rate": 4.4325261334068426e-05,
|
| 176 |
+
"loss": 2.0873,
|
| 177 |
+
"num_input_tokens_seen": 987776,
|
| 178 |
+
"step": 105
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.8333333333333335,
|
| 182 |
+
"grad_norm": 6.7481513023376465,
|
| 183 |
+
"learning_rate": 4.379599518697444e-05,
|
| 184 |
+
"loss": 1.9163,
|
| 185 |
+
"num_input_tokens_seen": 1036072,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.9166666666666665,
|
| 190 |
+
"grad_norm": 8.03829288482666,
|
| 191 |
+
"learning_rate": 4.324660181744589e-05,
|
| 192 |
+
"loss": 1.4848,
|
| 193 |
+
"num_input_tokens_seen": 1083328,
|
| 194 |
+
"step": 115
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.0,
|
| 198 |
+
"grad_norm": 9.837620735168457,
|
| 199 |
+
"learning_rate": 4.267766952966369e-05,
|
| 200 |
+
"loss": 1.7719,
|
| 201 |
+
"num_input_tokens_seen": 1129840,
|
| 202 |
+
"step": 120
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.0833333333333335,
|
| 206 |
+
"grad_norm": 14.701643943786621,
|
| 207 |
+
"learning_rate": 4.208980755057178e-05,
|
| 208 |
+
"loss": 1.4241,
|
| 209 |
+
"num_input_tokens_seen": 1177616,
|
| 210 |
+
"step": 125
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.1666666666666665,
|
| 214 |
+
"grad_norm": 30.390798568725586,
|
| 215 |
+
"learning_rate": 4.148364537750172e-05,
|
| 216 |
+
"loss": 1.6277,
|
| 217 |
+
"num_input_tokens_seen": 1225296,
|
| 218 |
+
"step": 130
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.25,
|
| 222 |
+
"grad_norm": 9.536770820617676,
|
| 223 |
+
"learning_rate": 4.085983210409114e-05,
|
| 224 |
+
"loss": 0.9761,
|
| 225 |
+
"num_input_tokens_seen": 1272160,
|
| 226 |
+
"step": 135
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.3333333333333335,
|
| 230 |
+
"grad_norm": 11.45682430267334,
|
| 231 |
+
"learning_rate": 4.021903572521802e-05,
|
| 232 |
+
"loss": 1.0144,
|
| 233 |
+
"num_input_tokens_seen": 1319432,
|
| 234 |
+
"step": 140
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.4166666666666665,
|
| 238 |
+
"grad_norm": 11.267831802368164,
|
| 239 |
+
"learning_rate": 3.956194242169506e-05,
|
| 240 |
+
"loss": 1.3858,
|
| 241 |
+
"num_input_tokens_seen": 1365992,
|
| 242 |
+
"step": 145
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.5,
|
| 246 |
+
"grad_norm": 11.92896556854248,
|
| 247 |
+
"learning_rate": 3.888925582549006e-05,
|
| 248 |
+
"loss": 0.9969,
|
| 249 |
+
"num_input_tokens_seen": 1412712,
|
| 250 |
+
"step": 150
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.5833333333333335,
|
| 254 |
+
"grad_norm": 15.724352836608887,
|
| 255 |
+
"learning_rate": 3.82016962662592e-05,
|
| 256 |
+
"loss": 1.0721,
|
| 257 |
+
"num_input_tokens_seen": 1459448,
|
| 258 |
+
"step": 155
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.6666666666666665,
|
| 262 |
+
"grad_norm": 12.68454360961914,
|
| 263 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 264 |
+
"loss": 1.6622,
|
| 265 |
+
"num_input_tokens_seen": 1506944,
|
| 266 |
+
"step": 160
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.75,
|
| 270 |
+
"grad_norm": 6.482985496520996,
|
| 271 |
+
"learning_rate": 3.678491842064995e-05,
|
| 272 |
+
"loss": 1.059,
|
| 273 |
+
"num_input_tokens_seen": 1554216,
|
| 274 |
+
"step": 165
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.8333333333333335,
|
| 278 |
+
"grad_norm": 15.581390380859375,
|
| 279 |
+
"learning_rate": 3.6057217255475034e-05,
|
| 280 |
+
"loss": 0.774,
|
| 281 |
+
"num_input_tokens_seen": 1600608,
|
| 282 |
+
"step": 170
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.9166666666666665,
|
| 286 |
+
"grad_norm": 3.8697454929351807,
|
| 287 |
+
"learning_rate": 3.5317675745109866e-05,
|
| 288 |
+
"loss": 1.0403,
|
| 289 |
+
"num_input_tokens_seen": 1647272,
|
| 290 |
+
"step": 175
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.0,
|
| 294 |
+
"grad_norm": 54.316123962402344,
|
| 295 |
+
"learning_rate": 3.456708580912725e-05,
|
| 296 |
+
"loss": 2.173,
|
| 297 |
+
"num_input_tokens_seen": 1694760,
|
| 298 |
+
"step": 180
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.0833333333333335,
|
| 302 |
+
"grad_norm": 57.840152740478516,
|
| 303 |
+
"learning_rate": 3.380625119803084e-05,
|
| 304 |
+
"loss": 1.9583,
|
| 305 |
+
"num_input_tokens_seen": 1741936,
|
| 306 |
+
"step": 185
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.1666666666666665,
|
| 310 |
+
"grad_norm": 26.283540725708008,
|
| 311 |
+
"learning_rate": 3.303598663257904e-05,
|
| 312 |
+
"loss": 1.8407,
|
| 313 |
+
"num_input_tokens_seen": 1788624,
|
| 314 |
+
"step": 190
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.25,
|
| 318 |
+
"grad_norm": 15.37193489074707,
|
| 319 |
+
"learning_rate": 3.225711693136156e-05,
|
| 320 |
+
"loss": 1.1398,
|
| 321 |
+
"num_input_tokens_seen": 1835336,
|
| 322 |
+
"step": 195
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 3.3333333333333335,
|
| 326 |
+
"grad_norm": 53.772212982177734,
|
| 327 |
+
"learning_rate": 3.147047612756302e-05,
|
| 328 |
+
"loss": 0.8378,
|
| 329 |
+
"num_input_tokens_seen": 1882584,
|
| 330 |
+
"step": 200
|
| 331 |
+
}
|
| 332 |
+
],
|
| 333 |
+
"logging_steps": 5,
|
| 334 |
+
"max_steps": 480,
|
| 335 |
+
"num_input_tokens_seen": 1882584,
|
| 336 |
+
"num_train_epochs": 8,
|
| 337 |
+
"save_steps": 100,
|
| 338 |
+
"stateful_callbacks": {
|
| 339 |
+
"TrainerControl": {
|
| 340 |
+
"args": {
|
| 341 |
+
"should_epoch_stop": false,
|
| 342 |
+
"should_evaluate": false,
|
| 343 |
+
"should_log": false,
|
| 344 |
+
"should_save": true,
|
| 345 |
+
"should_training_stop": false
|
| 346 |
+
},
|
| 347 |
+
"attributes": {}
|
| 348 |
+
}
|
| 349 |
+
},
|
| 350 |
+
"total_flos": 2.9901598271122406e+17,
|
| 351 |
+
"train_batch_size": 1,
|
| 352 |
+
"trial_name": null,
|
| 353 |
+
"trial_params": null
|
| 354 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01cf6a1b3597e72bc7b90c88ce73fa75eed9ace24c5f542bd93a792085dd5c9c
|
| 3 |
+
size 5688
|
checkpoint-300/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-3-27b-it
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-27b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"language_model.model.layers.42.self_attn.q_proj",
|
| 24 |
+
"language_model.model.layers.51.mlp.up_proj",
|
| 25 |
+
"language_model.model.layers.51.mlp.down_proj",
|
| 26 |
+
"language_model.model.layers.30.mlp.up_proj",
|
| 27 |
+
"language_model.model.layers.47.self_attn.q_proj",
|
| 28 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
| 29 |
+
"language_model.model.layers.25.self_attn.q_proj",
|
| 30 |
+
"language_model.model.layers.26.self_attn.q_proj",
|
| 31 |
+
"language_model.model.layers.27.mlp.down_proj",
|
| 32 |
+
"language_model.model.layers.9.self_attn.q_proj",
|
| 33 |
+
"language_model.model.layers.45.self_attn.q_proj",
|
| 34 |
+
"language_model.model.layers.51.self_attn.o_proj",
|
| 35 |
+
"language_model.model.layers.0.self_attn.q_proj",
|
| 36 |
+
"language_model.model.layers.21.mlp.up_proj",
|
| 37 |
+
"language_model.model.layers.61.self_attn.q_proj",
|
| 38 |
+
"language_model.model.layers.52.self_attn.k_proj",
|
| 39 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 40 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
| 41 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
| 42 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
| 43 |
+
"language_model.model.layers.38.self_attn.q_proj",
|
| 44 |
+
"language_model.model.layers.30.self_attn.q_proj",
|
| 45 |
+
"language_model.model.layers.22.mlp.down_proj",
|
| 46 |
+
"language_model.model.layers.46.self_attn.q_proj",
|
| 47 |
+
"language_model.model.layers.54.mlp.gate_proj",
|
| 48 |
+
"language_model.model.layers.49.mlp.up_proj",
|
| 49 |
+
"language_model.model.layers.35.self_attn.q_proj",
|
| 50 |
+
"language_model.model.layers.18.self_attn.o_proj",
|
| 51 |
+
"language_model.model.layers.33.self_attn.v_proj",
|
| 52 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
| 53 |
+
"language_model.model.layers.7.self_attn.q_proj",
|
| 54 |
+
"language_model.model.layers.50.self_attn.o_proj",
|
| 55 |
+
"language_model.model.layers.36.self_attn.o_proj",
|
| 56 |
+
"language_model.model.layers.20.self_attn.k_proj",
|
| 57 |
+
"language_model.model.layers.47.self_attn.k_proj",
|
| 58 |
+
"language_model.model.layers.32.mlp.gate_proj",
|
| 59 |
+
"language_model.model.layers.1.self_attn.q_proj",
|
| 60 |
+
"language_model.model.layers.7.mlp.up_proj",
|
| 61 |
+
"language_model.model.layers.36.mlp.gate_proj",
|
| 62 |
+
"language_model.model.layers.45.self_attn.k_proj",
|
| 63 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
| 64 |
+
"language_model.model.layers.58.self_attn.o_proj",
|
| 65 |
+
"language_model.model.layers.43.self_attn.q_proj",
|
| 66 |
+
"language_model.model.layers.60.self_attn.v_proj",
|
| 67 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
| 68 |
+
"language_model.model.layers.60.self_attn.o_proj",
|
| 69 |
+
"language_model.model.layers.29.self_attn.o_proj",
|
| 70 |
+
"language_model.model.layers.31.mlp.gate_proj",
|
| 71 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
| 72 |
+
"language_model.model.layers.6.self_attn.k_proj",
|
| 73 |
+
"language_model.model.layers.56.self_attn.k_proj",
|
| 74 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
| 75 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 76 |
+
"language_model.model.layers.12.self_attn.v_proj",
|
| 77 |
+
"language_model.model.layers.22.self_attn.o_proj",
|
| 78 |
+
"language_model.model.layers.2.self_attn.o_proj",
|
| 79 |
+
"language_model.model.layers.8.mlp.up_proj",
|
| 80 |
+
"language_model.model.layers.57.mlp.down_proj",
|
| 81 |
+
"language_model.model.layers.57.mlp.up_proj",
|
| 82 |
+
"language_model.model.layers.19.mlp.down_proj",
|
| 83 |
+
"language_model.model.layers.16.self_attn.k_proj",
|
| 84 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
| 85 |
+
"language_model.model.layers.17.mlp.down_proj",
|
| 86 |
+
"language_model.model.layers.35.mlp.down_proj",
|
| 87 |
+
"language_model.model.layers.39.self_attn.k_proj",
|
| 88 |
+
"language_model.model.layers.46.mlp.up_proj",
|
| 89 |
+
"language_model.model.layers.52.self_attn.q_proj",
|
| 90 |
+
"language_model.model.layers.8.self_attn.v_proj",
|
| 91 |
+
"language_model.model.layers.8.mlp.down_proj",
|
| 92 |
+
"language_model.model.layers.8.self_attn.o_proj",
|
| 93 |
+
"language_model.model.layers.7.mlp.down_proj",
|
| 94 |
+
"language_model.model.layers.24.self_attn.o_proj",
|
| 95 |
+
"language_model.model.layers.52.mlp.gate_proj",
|
| 96 |
+
"language_model.model.layers.38.self_attn.o_proj",
|
| 97 |
+
"language_model.model.layers.9.self_attn.v_proj",
|
| 98 |
+
"language_model.model.layers.56.self_attn.v_proj",
|
| 99 |
+
"language_model.model.layers.42.mlp.gate_proj",
|
| 100 |
+
"language_model.model.layers.57.self_attn.o_proj",
|
| 101 |
+
"language_model.model.layers.18.self_attn.v_proj",
|
| 102 |
+
"language_model.model.layers.47.mlp.gate_proj",
|
| 103 |
+
"language_model.model.layers.59.self_attn.v_proj",
|
| 104 |
+
"language_model.model.layers.27.mlp.up_proj",
|
| 105 |
+
"language_model.model.layers.36.self_attn.k_proj",
|
| 106 |
+
"language_model.model.layers.43.mlp.gate_proj",
|
| 107 |
+
"language_model.model.layers.54.self_attn.k_proj",
|
| 108 |
+
"language_model.model.layers.28.self_attn.q_proj",
|
| 109 |
+
"language_model.model.layers.9.mlp.down_proj",
|
| 110 |
+
"language_model.model.layers.36.self_attn.v_proj",
|
| 111 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
| 112 |
+
"language_model.model.layers.26.self_attn.o_proj",
|
| 113 |
+
"language_model.model.layers.17.mlp.up_proj",
|
| 114 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
| 115 |
+
"language_model.model.layers.57.self_attn.k_proj",
|
| 116 |
+
"language_model.model.layers.10.mlp.down_proj",
|
| 117 |
+
"language_model.model.layers.25.self_attn.o_proj",
|
| 118 |
+
"language_model.model.layers.55.self_attn.o_proj",
|
| 119 |
+
"language_model.model.layers.6.self_attn.o_proj",
|
| 120 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 121 |
+
"language_model.model.layers.14.self_attn.q_proj",
|
| 122 |
+
"language_model.model.layers.52.mlp.up_proj",
|
| 123 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
| 124 |
+
"language_model.model.layers.52.self_attn.v_proj",
|
| 125 |
+
"language_model.model.layers.17.self_attn.q_proj",
|
| 126 |
+
"language_model.model.layers.47.self_attn.v_proj",
|
| 127 |
+
"language_model.model.layers.29.mlp.up_proj",
|
| 128 |
+
"language_model.model.layers.13.self_attn.k_proj",
|
| 129 |
+
"language_model.model.layers.41.self_attn.v_proj",
|
| 130 |
+
"language_model.model.layers.4.mlp.up_proj",
|
| 131 |
+
"language_model.model.layers.46.self_attn.v_proj",
|
| 132 |
+
"language_model.model.layers.21.self_attn.q_proj",
|
| 133 |
+
"language_model.model.layers.57.mlp.gate_proj",
|
| 134 |
+
"language_model.model.layers.16.self_attn.o_proj",
|
| 135 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
| 136 |
+
"language_model.model.layers.41.self_attn.o_proj",
|
| 137 |
+
"language_model.model.layers.54.self_attn.v_proj",
|
| 138 |
+
"language_model.model.layers.42.self_attn.o_proj",
|
| 139 |
+
"language_model.model.layers.5.self_attn.q_proj",
|
| 140 |
+
"language_model.model.layers.45.self_attn.o_proj",
|
| 141 |
+
"language_model.model.layers.56.self_attn.q_proj",
|
| 142 |
+
"language_model.model.layers.22.self_attn.v_proj",
|
| 143 |
+
"language_model.model.layers.12.mlp.down_proj",
|
| 144 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
| 145 |
+
"language_model.model.layers.61.self_attn.o_proj",
|
| 146 |
+
"language_model.model.layers.32.self_attn.q_proj",
|
| 147 |
+
"language_model.model.layers.33.self_attn.k_proj",
|
| 148 |
+
"language_model.model.layers.34.mlp.up_proj",
|
| 149 |
+
"language_model.model.layers.25.mlp.down_proj",
|
| 150 |
+
"language_model.model.layers.61.self_attn.k_proj",
|
| 151 |
+
"language_model.model.layers.30.mlp.down_proj",
|
| 152 |
+
"language_model.model.layers.21.self_attn.o_proj",
|
| 153 |
+
"language_model.model.layers.30.self_attn.v_proj",
|
| 154 |
+
"language_model.model.layers.46.self_attn.k_proj",
|
| 155 |
+
"language_model.model.layers.4.self_attn.v_proj",
|
| 156 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 157 |
+
"language_model.model.layers.52.self_attn.o_proj",
|
| 158 |
+
"language_model.model.layers.61.mlp.down_proj",
|
| 159 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
| 160 |
+
"language_model.model.layers.37.mlp.down_proj",
|
| 161 |
+
"language_model.model.layers.18.mlp.up_proj",
|
| 162 |
+
"language_model.model.layers.5.mlp.up_proj",
|
| 163 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
| 164 |
+
"language_model.model.layers.44.mlp.down_proj",
|
| 165 |
+
"language_model.model.layers.58.self_attn.v_proj",
|
| 166 |
+
"language_model.model.layers.58.self_attn.q_proj",
|
| 167 |
+
"language_model.model.layers.60.mlp.down_proj",
|
| 168 |
+
"language_model.model.layers.48.mlp.gate_proj",
|
| 169 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
| 170 |
+
"language_model.model.layers.41.self_attn.k_proj",
|
| 171 |
+
"language_model.model.layers.40.self_attn.k_proj",
|
| 172 |
+
"language_model.model.layers.34.self_attn.q_proj",
|
| 173 |
+
"language_model.model.layers.43.mlp.down_proj",
|
| 174 |
+
"language_model.model.layers.17.self_attn.k_proj",
|
| 175 |
+
"language_model.model.layers.37.mlp.up_proj",
|
| 176 |
+
"language_model.model.layers.12.mlp.up_proj",
|
| 177 |
+
"language_model.model.layers.17.self_attn.v_proj",
|
| 178 |
+
"language_model.model.layers.31.mlp.down_proj",
|
| 179 |
+
"language_model.model.layers.48.self_attn.o_proj",
|
| 180 |
+
"language_model.model.layers.3.mlp.down_proj",
|
| 181 |
+
"language_model.model.layers.46.mlp.gate_proj",
|
| 182 |
+
"language_model.model.layers.32.self_attn.o_proj",
|
| 183 |
+
"language_model.model.layers.24.self_attn.q_proj",
|
| 184 |
+
"language_model.model.layers.58.mlp.up_proj",
|
| 185 |
+
"language_model.model.layers.5.self_attn.v_proj",
|
| 186 |
+
"language_model.model.layers.44.self_attn.v_proj",
|
| 187 |
+
"language_model.model.layers.48.self_attn.v_proj",
|
| 188 |
+
"language_model.model.layers.10.self_attn.q_proj",
|
| 189 |
+
"language_model.model.layers.10.mlp.up_proj",
|
| 190 |
+
"language_model.model.layers.48.mlp.up_proj",
|
| 191 |
+
"language_model.model.layers.5.mlp.down_proj",
|
| 192 |
+
"language_model.model.layers.28.mlp.up_proj",
|
| 193 |
+
"language_model.model.layers.47.self_attn.o_proj",
|
| 194 |
+
"language_model.model.layers.8.self_attn.q_proj",
|
| 195 |
+
"language_model.model.layers.53.mlp.gate_proj",
|
| 196 |
+
"language_model.model.layers.57.self_attn.v_proj",
|
| 197 |
+
"language_model.model.layers.9.mlp.gate_proj",
|
| 198 |
+
"language_model.model.layers.2.self_attn.k_proj",
|
| 199 |
+
"language_model.model.layers.5.self_attn.k_proj",
|
| 200 |
+
"language_model.model.layers.34.self_attn.k_proj",
|
| 201 |
+
"language_model.model.layers.17.self_attn.o_proj",
|
| 202 |
+
"language_model.model.layers.21.self_attn.k_proj",
|
| 203 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
| 204 |
+
"language_model.model.layers.48.mlp.down_proj",
|
| 205 |
+
"language_model.model.layers.25.self_attn.v_proj",
|
| 206 |
+
"language_model.model.layers.44.mlp.gate_proj",
|
| 207 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 208 |
+
"language_model.model.layers.4.mlp.down_proj",
|
| 209 |
+
"language_model.model.layers.13.self_attn.v_proj",
|
| 210 |
+
"language_model.model.layers.55.mlp.up_proj",
|
| 211 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
| 212 |
+
"language_model.model.layers.26.mlp.up_proj",
|
| 213 |
+
"language_model.model.layers.50.mlp.gate_proj",
|
| 214 |
+
"language_model.model.layers.56.mlp.down_proj",
|
| 215 |
+
"language_model.model.layers.21.self_attn.v_proj",
|
| 216 |
+
"language_model.model.layers.18.mlp.gate_proj",
|
| 217 |
+
"language_model.model.layers.22.self_attn.q_proj",
|
| 218 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
| 219 |
+
"language_model.model.layers.53.mlp.down_proj",
|
| 220 |
+
"language_model.model.layers.22.mlp.up_proj",
|
| 221 |
+
"language_model.model.layers.56.self_attn.o_proj",
|
| 222 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
| 223 |
+
"language_model.model.layers.14.self_attn.v_proj",
|
| 224 |
+
"language_model.model.layers.29.self_attn.v_proj",
|
| 225 |
+
"language_model.model.layers.50.mlp.up_proj",
|
| 226 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
| 227 |
+
"language_model.model.layers.23.mlp.down_proj",
|
| 228 |
+
"language_model.model.layers.53.self_attn.k_proj",
|
| 229 |
+
"language_model.model.layers.24.mlp.up_proj",
|
| 230 |
+
"language_model.model.layers.55.mlp.gate_proj",
|
| 231 |
+
"language_model.model.layers.39.mlp.up_proj",
|
| 232 |
+
"language_model.model.layers.59.self_attn.o_proj",
|
| 233 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
| 234 |
+
"language_model.model.layers.41.mlp.down_proj",
|
| 235 |
+
"language_model.model.layers.8.self_attn.k_proj",
|
| 236 |
+
"language_model.model.layers.54.self_attn.q_proj",
|
| 237 |
+
"language_model.model.layers.32.self_attn.v_proj",
|
| 238 |
+
"language_model.model.layers.35.self_attn.o_proj",
|
| 239 |
+
"language_model.model.layers.33.self_attn.o_proj",
|
| 240 |
+
"language_model.model.layers.28.self_attn.v_proj",
|
| 241 |
+
"language_model.model.layers.6.mlp.up_proj",
|
| 242 |
+
"language_model.model.layers.40.self_attn.q_proj",
|
| 243 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
| 244 |
+
"language_model.model.layers.10.self_attn.k_proj",
|
| 245 |
+
"language_model.model.layers.37.self_attn.q_proj",
|
| 246 |
+
"language_model.model.layers.49.mlp.down_proj",
|
| 247 |
+
"language_model.model.layers.6.self_attn.q_proj",
|
| 248 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
| 249 |
+
"language_model.model.layers.45.mlp.down_proj",
|
| 250 |
+
"language_model.model.layers.51.self_attn.v_proj",
|
| 251 |
+
"language_model.model.layers.28.self_attn.k_proj",
|
| 252 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
| 253 |
+
"language_model.model.layers.30.self_attn.o_proj",
|
| 254 |
+
"language_model.model.layers.59.mlp.up_proj",
|
| 255 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
| 256 |
+
"language_model.model.layers.6.mlp.down_proj",
|
| 257 |
+
"language_model.model.layers.9.mlp.up_proj",
|
| 258 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
| 259 |
+
"language_model.model.layers.37.mlp.gate_proj",
|
| 260 |
+
"language_model.model.layers.43.self_attn.k_proj",
|
| 261 |
+
"language_model.model.layers.46.self_attn.o_proj",
|
| 262 |
+
"language_model.model.layers.12.self_attn.k_proj",
|
| 263 |
+
"language_model.model.layers.13.mlp.down_proj",
|
| 264 |
+
"language_model.model.layers.4.self_attn.k_proj",
|
| 265 |
+
"language_model.model.layers.49.self_attn.k_proj",
|
| 266 |
+
"language_model.model.layers.51.self_attn.q_proj",
|
| 267 |
+
"language_model.model.layers.52.mlp.down_proj",
|
| 268 |
+
"language_model.model.layers.24.self_attn.v_proj",
|
| 269 |
+
"language_model.model.layers.42.self_attn.v_proj",
|
| 270 |
+
"language_model.model.layers.53.self_attn.o_proj",
|
| 271 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
| 272 |
+
"language_model.model.layers.40.self_attn.v_proj",
|
| 273 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
| 274 |
+
"language_model.model.layers.40.mlp.up_proj",
|
| 275 |
+
"language_model.model.layers.49.self_attn.o_proj",
|
| 276 |
+
"language_model.model.layers.42.mlp.down_proj",
|
| 277 |
+
"language_model.model.layers.41.self_attn.q_proj",
|
| 278 |
+
"language_model.model.layers.42.mlp.up_proj",
|
| 279 |
+
"language_model.model.layers.28.mlp.down_proj",
|
| 280 |
+
"language_model.model.layers.2.self_attn.v_proj",
|
| 281 |
+
"language_model.model.layers.23.mlp.up_proj",
|
| 282 |
+
"language_model.model.layers.36.mlp.down_proj",
|
| 283 |
+
"language_model.model.layers.16.mlp.down_proj",
|
| 284 |
+
"language_model.model.layers.43.self_attn.o_proj",
|
| 285 |
+
"language_model.model.layers.20.self_attn.q_proj",
|
| 286 |
+
"language_model.model.layers.51.mlp.gate_proj",
|
| 287 |
+
"language_model.model.layers.15.mlp.down_proj",
|
| 288 |
+
"language_model.model.layers.10.self_attn.v_proj",
|
| 289 |
+
"language_model.model.layers.35.self_attn.v_proj",
|
| 290 |
+
"language_model.model.layers.59.self_attn.k_proj",
|
| 291 |
+
"language_model.model.layers.47.mlp.up_proj",
|
| 292 |
+
"language_model.model.layers.38.self_attn.v_proj",
|
| 293 |
+
"language_model.model.layers.18.self_attn.q_proj",
|
| 294 |
+
"language_model.model.layers.25.self_attn.k_proj",
|
| 295 |
+
"language_model.model.layers.36.self_attn.q_proj",
|
| 296 |
+
"language_model.model.layers.40.mlp.down_proj",
|
| 297 |
+
"language_model.model.layers.39.mlp.down_proj",
|
| 298 |
+
"language_model.model.layers.41.mlp.gate_proj",
|
| 299 |
+
"language_model.model.layers.29.self_attn.q_proj",
|
| 300 |
+
"language_model.model.layers.56.mlp.up_proj",
|
| 301 |
+
"language_model.model.layers.14.mlp.up_proj",
|
| 302 |
+
"language_model.model.layers.29.mlp.down_proj",
|
| 303 |
+
"language_model.model.layers.13.mlp.up_proj",
|
| 304 |
+
"language_model.model.layers.28.mlp.gate_proj",
|
| 305 |
+
"language_model.model.layers.45.mlp.up_proj",
|
| 306 |
+
"language_model.model.layers.13.self_attn.o_proj",
|
| 307 |
+
"language_model.model.layers.20.self_attn.v_proj",
|
| 308 |
+
"language_model.model.layers.54.self_attn.o_proj",
|
| 309 |
+
"language_model.model.layers.39.mlp.gate_proj",
|
| 310 |
+
"language_model.model.layers.25.mlp.up_proj",
|
| 311 |
+
"language_model.model.layers.53.mlp.up_proj",
|
| 312 |
+
"language_model.model.layers.50.mlp.down_proj",
|
| 313 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
| 314 |
+
"language_model.model.layers.59.mlp.gate_proj",
|
| 315 |
+
"language_model.model.layers.60.mlp.up_proj",
|
| 316 |
+
"language_model.model.layers.24.mlp.down_proj",
|
| 317 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
| 318 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
| 319 |
+
"language_model.model.layers.60.mlp.gate_proj",
|
| 320 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
| 321 |
+
"language_model.model.layers.24.self_attn.k_proj",
|
| 322 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
| 323 |
+
"language_model.model.layers.13.self_attn.q_proj",
|
| 324 |
+
"language_model.model.layers.44.self_attn.o_proj",
|
| 325 |
+
"language_model.model.layers.32.mlp.down_proj",
|
| 326 |
+
"language_model.model.layers.20.mlp.up_proj",
|
| 327 |
+
"language_model.model.layers.10.self_attn.o_proj",
|
| 328 |
+
"language_model.model.layers.41.mlp.up_proj",
|
| 329 |
+
"language_model.model.layers.49.mlp.gate_proj",
|
| 330 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 331 |
+
"language_model.model.layers.39.self_attn.o_proj",
|
| 332 |
+
"language_model.model.layers.14.self_attn.k_proj",
|
| 333 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
| 334 |
+
"language_model.model.layers.7.self_attn.o_proj",
|
| 335 |
+
"language_model.model.layers.21.mlp.down_proj",
|
| 336 |
+
"language_model.model.layers.35.mlp.up_proj",
|
| 337 |
+
"language_model.model.layers.20.mlp.down_proj",
|
| 338 |
+
"language_model.model.layers.15.mlp.up_proj",
|
| 339 |
+
"language_model.model.layers.53.self_attn.v_proj",
|
| 340 |
+
"language_model.model.layers.9.self_attn.o_proj",
|
| 341 |
+
"language_model.model.layers.60.self_attn.k_proj",
|
| 342 |
+
"language_model.model.layers.5.self_attn.o_proj",
|
| 343 |
+
"language_model.model.layers.58.mlp.down_proj",
|
| 344 |
+
"language_model.model.layers.6.self_attn.v_proj",
|
| 345 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.34.mlp.gate_proj",
|
| 347 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
| 348 |
+
"language_model.model.layers.36.mlp.up_proj",
|
| 349 |
+
"language_model.model.layers.57.self_attn.q_proj",
|
| 350 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
| 351 |
+
"language_model.model.layers.28.self_attn.o_proj",
|
| 352 |
+
"language_model.model.layers.55.self_attn.q_proj",
|
| 353 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
| 354 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
| 355 |
+
"language_model.model.layers.32.self_attn.k_proj",
|
| 356 |
+
"language_model.model.layers.12.self_attn.q_proj",
|
| 357 |
+
"language_model.model.layers.35.self_attn.k_proj",
|
| 358 |
+
"language_model.model.layers.37.self_attn.o_proj",
|
| 359 |
+
"language_model.model.layers.55.self_attn.v_proj",
|
| 360 |
+
"language_model.model.layers.50.self_attn.q_proj",
|
| 361 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
| 362 |
+
"language_model.model.layers.26.self_attn.k_proj",
|
| 363 |
+
"language_model.model.layers.1.self_attn.k_proj",
|
| 364 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 365 |
+
"language_model.model.layers.9.self_attn.k_proj",
|
| 366 |
+
"language_model.model.layers.18.mlp.down_proj",
|
| 367 |
+
"language_model.model.layers.33.mlp.down_proj",
|
| 368 |
+
"language_model.model.layers.59.self_attn.q_proj",
|
| 369 |
+
"language_model.model.layers.11.mlp.down_proj",
|
| 370 |
+
"language_model.model.layers.61.mlp.up_proj",
|
| 371 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
| 372 |
+
"language_model.model.layers.30.self_attn.k_proj",
|
| 373 |
+
"language_model.model.layers.14.self_attn.o_proj",
|
| 374 |
+
"language_model.model.layers.47.mlp.down_proj",
|
| 375 |
+
"language_model.model.layers.16.self_attn.v_proj",
|
| 376 |
+
"language_model.model.layers.40.self_attn.o_proj",
|
| 377 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
| 378 |
+
"language_model.model.layers.54.mlp.down_proj",
|
| 379 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
| 380 |
+
"language_model.model.layers.61.self_attn.v_proj",
|
| 381 |
+
"language_model.model.layers.42.self_attn.k_proj",
|
| 382 |
+
"language_model.model.layers.44.self_attn.q_proj",
|
| 383 |
+
"language_model.model.layers.3.mlp.up_proj",
|
| 384 |
+
"language_model.model.layers.58.self_attn.k_proj",
|
| 385 |
+
"language_model.model.layers.54.mlp.up_proj",
|
| 386 |
+
"language_model.model.layers.59.mlp.down_proj",
|
| 387 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 388 |
+
"language_model.model.layers.33.self_attn.q_proj",
|
| 389 |
+
"language_model.model.layers.43.mlp.up_proj",
|
| 390 |
+
"language_model.model.layers.48.self_attn.q_proj",
|
| 391 |
+
"language_model.model.layers.0.self_attn.k_proj",
|
| 392 |
+
"language_model.model.layers.22.self_attn.k_proj",
|
| 393 |
+
"language_model.model.layers.49.self_attn.q_proj",
|
| 394 |
+
"language_model.model.layers.43.self_attn.v_proj",
|
| 395 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
| 396 |
+
"language_model.model.layers.38.mlp.up_proj",
|
| 397 |
+
"language_model.model.layers.1.self_attn.v_proj",
|
| 398 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
| 399 |
+
"language_model.model.layers.56.mlp.gate_proj",
|
| 400 |
+
"language_model.model.layers.50.self_attn.v_proj",
|
| 401 |
+
"language_model.model.layers.29.self_attn.k_proj",
|
| 402 |
+
"language_model.model.layers.8.mlp.gate_proj",
|
| 403 |
+
"language_model.model.layers.34.self_attn.v_proj",
|
| 404 |
+
"language_model.model.layers.20.self_attn.o_proj",
|
| 405 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
| 406 |
+
"language_model.model.layers.37.self_attn.v_proj",
|
| 407 |
+
"language_model.model.layers.4.self_attn.q_proj",
|
| 408 |
+
"language_model.model.layers.55.mlp.down_proj",
|
| 409 |
+
"language_model.model.layers.45.self_attn.v_proj",
|
| 410 |
+
"language_model.model.layers.61.mlp.gate_proj",
|
| 411 |
+
"language_model.model.layers.0.self_attn.o_proj",
|
| 412 |
+
"language_model.model.layers.37.self_attn.k_proj",
|
| 413 |
+
"language_model.model.layers.51.self_attn.k_proj",
|
| 414 |
+
"language_model.model.layers.38.mlp.gate_proj",
|
| 415 |
+
"language_model.model.layers.26.mlp.down_proj",
|
| 416 |
+
"language_model.model.layers.48.self_attn.k_proj",
|
| 417 |
+
"language_model.model.layers.39.self_attn.q_proj",
|
| 418 |
+
"language_model.model.layers.45.mlp.gate_proj",
|
| 419 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
| 420 |
+
"language_model.model.layers.11.mlp.up_proj",
|
| 421 |
+
"language_model.model.layers.34.mlp.down_proj",
|
| 422 |
+
"language_model.model.layers.0.self_attn.v_proj",
|
| 423 |
+
"language_model.model.layers.44.self_attn.k_proj",
|
| 424 |
+
"language_model.model.layers.16.self_attn.q_proj",
|
| 425 |
+
"language_model.model.layers.14.mlp.down_proj",
|
| 426 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 427 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
| 428 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
| 429 |
+
"language_model.model.layers.31.mlp.up_proj",
|
| 430 |
+
"language_model.model.layers.44.mlp.up_proj",
|
| 431 |
+
"language_model.model.layers.58.mlp.gate_proj",
|
| 432 |
+
"language_model.model.layers.26.self_attn.v_proj",
|
| 433 |
+
"language_model.model.layers.34.self_attn.o_proj",
|
| 434 |
+
"language_model.model.layers.19.mlp.up_proj",
|
| 435 |
+
"language_model.model.layers.2.self_attn.q_proj",
|
| 436 |
+
"language_model.model.layers.40.mlp.gate_proj",
|
| 437 |
+
"language_model.model.layers.32.mlp.up_proj",
|
| 438 |
+
"language_model.model.layers.33.mlp.up_proj",
|
| 439 |
+
"language_model.model.layers.4.self_attn.o_proj",
|
| 440 |
+
"language_model.model.layers.35.mlp.gate_proj",
|
| 441 |
+
"language_model.model.layers.18.self_attn.k_proj",
|
| 442 |
+
"language_model.model.layers.38.self_attn.k_proj",
|
| 443 |
+
"language_model.model.layers.49.self_attn.v_proj",
|
| 444 |
+
"language_model.model.layers.31.self_attn.o_proj",
|
| 445 |
+
"language_model.model.layers.55.self_attn.k_proj",
|
| 446 |
+
"language_model.model.layers.38.mlp.down_proj",
|
| 447 |
+
"language_model.model.layers.46.mlp.down_proj",
|
| 448 |
+
"language_model.model.layers.1.self_attn.o_proj",
|
| 449 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
| 450 |
+
"language_model.model.layers.33.mlp.gate_proj",
|
| 451 |
+
"language_model.model.layers.60.self_attn.q_proj",
|
| 452 |
+
"language_model.model.layers.39.self_attn.v_proj",
|
| 453 |
+
"language_model.model.layers.16.mlp.up_proj",
|
| 454 |
+
"language_model.model.layers.50.self_attn.k_proj",
|
| 455 |
+
"language_model.model.layers.12.self_attn.o_proj",
|
| 456 |
+
"language_model.model.layers.53.self_attn.q_proj"
|
| 457 |
+
],
|
| 458 |
+
"task_type": "CAUSAL_LM",
|
| 459 |
+
"use_dora": false,
|
| 460 |
+
"use_rslora": false
|
| 461 |
+
}
|
checkpoint-300/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00ce87bb1573078c8fccc3f37cd13d9891bd76e4bd71b13f7785a0833f9e5199
|
| 3 |
+
size 1816396048
|
checkpoint-300/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
checkpoint-300/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 3 |
+
}
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4e6ec940d4ecdeea4c965d77f8df2fdafcea0d0a61d00bf1f41cdc3815bd04
|
| 3 |
+
size 3633264318
|
checkpoint-300/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pan_and_scan": null,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
+
"image_seq_length": 256,
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"pan_and_scan_max_num_crops": null,
|
| 20 |
+
"pan_and_scan_min_crop_size": null,
|
| 21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
+
"processor_class": "Gemma3Processor",
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 896,
|
| 27 |
+
"width": 896
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-300/processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "Gemma3Processor"
|
| 4 |
+
}
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
|
| 3 |
+
size 14244
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a97313cd95c7993a78511391093119014f9c53386af6123ad477df823bae5781
|
| 3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<end_of_turn>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"boi_token": "<start_of_image>",
|
| 12 |
+
"bos_token": {
|
| 13 |
+
"content": "<bos>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eoi_token": "<end_of_image>",
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<eos>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"image_token": "<image_soft_token>",
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<pad>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"unk_token": {
|
| 36 |
+
"content": "<unk>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
}
|
| 42 |
+
}
|