Training in progress, step 26

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,141 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mhenrichsen/gemma-7b
+model-index:
+- name: outputs/out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: qlora
+base_model: mhenrichsen/gemma-7b
+bf16: auto
+datasets:
+- path: data.jsonl
+  type: alpaca
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_sample_packing: false
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: true
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 3
+gradient_checkpointing: true
+group_by_length: false
+learning_rate: 0.0002
+load_in_4bit: true
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.05
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: cosine
+micro_batch_size: 2
+model_type: AutoModelForCausalLM
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+output_dir: ./outputs/out
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+sample_packing: true
+saves_per_epoch: 1
+sequence_len: 4096
+special_tokens: null
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+val_set_size: 0.1
+wandb_entity: null
+wandb_log_model: null
+wandb_name: test-task
+wandb_project: null
+wandb_runid: test-task
+wandb_watch: null
+warmup_ratio: 0.1
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# outputs/out
+
+This model is a fine-tuned version of [mhenrichsen/gemma-7b](https://huggingface.co/mhenrichsen/gemma-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0412
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 12
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0695        | 0.1579 | 1    | 1.1912          |
+| 1.1142        | 0.3158 | 2    | 1.1076          |
+| 1.0936        | 0.6316 | 4    | 1.0834          |
+| 1.058         | 0.9474 | 6    | 1.0378          |
+| 0.9794        | 1.1579 | 8    | 1.0479          |
+| 0.9632        | 1.4737 | 10   | 1.0377          |
+| 0.951         | 1.7895 | 12   | 1.0467          |
+| 1.0219        | 2.1053 | 14   | 1.0463          |
+| 0.9345        | 2.3158 | 16   | 1.0417          |
+| 0.9314        | 2.6316 | 18   | 1.0434          |
+| 0.9108        | 2.9474 | 20   | 1.0363          |
+| 0.894         | 3.1579 | 22   | 1.0348          |
+| 0.8835        | 3.4737 | 24   | 1.0412          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mhenrichsen/gemma-7b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab93f1af6b30528b09ddf4f5826c4a502dd62cb47134a77f138d4a97e8d27c9b
+size 200157610

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f177799c9abff78193af4d5cfdef9f02d52e37d9dcddc292eb2029e6b42fad
+size 200068904

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "mhenrichsen/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 256000
+}

merged/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "mhenrichsen/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 256000
+}

merged/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.3"
+}

merged/pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b348b0860343b2b2c23d6fbe3e4adfcf34e71eb6e4e3c6ecf48a7b256d8e2cb
+size 4995510260

merged/pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1e55cb7373ac87cd963fe8602786e148547c16efb0967d1a0f1437f2146e69
+size 4982971572

merged/pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3213d826d0f61ea12aeda226ef2e3636ef75ee9417ab1237d3e99c8cc0ec90bc
+size 4982971572

merged/pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2a8d8766c4ad05efbd8107ec8698cc273a0604107f5c163bbf3f1e66b4e27d
+size 2113995964

merged/pytorch_model.bin.index.json

@@ -0,0 +1,262 @@
+{
+  "metadata": {
+    "total_size": 17075361792
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00004.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.norm.weight": "pytorch_model-00004-of-00004.bin"
+  }
+}

merged/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

merged/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db21bfaffa1fd75fd741df2d95dc51e539d5cc38b07934bae0d7d129db90662
+size 17477581

merged/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef
+size 4241111

merged/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db21bfaffa1fd75fd741df2d95dc51e539d5cc38b07934bae0d7d129db90662
+size 17477581

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef
+size 4241111

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6234a097c180d4a51d9d97718a0f5005d375531436c6de8986f7ad1229263f91
+size 6008