End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,57 @@
+---
+license: other
+base_model: google/gemma-2b-it
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: gemma_03-11-16-07
+  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. -->
+
+# gemma_03-11-16-07
+
+This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the generator dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: tpu
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.3.0.dev20240307
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-2b-it",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d643c2d4b6f6814ddb5f83f814b8ef849efed8dfcdc63cf7ce35e5d5624f5cd0
+size 4945246408

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d0704897ef7605fa3e76672e5238e78795f4fa2825603149be249568912500
+size 1115697824

model.safetensors.index.json

@@ -0,0 +1,172 @@
+{
+  "metadata": {
+    "total_size": 6060920832
+  },
+  "weight_map": {
+    "_orig_module.lm_head.weight": "model-00002-of-00002.safetensors",
+    "_orig_module.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.0._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.1._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.10._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.11._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.12._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.13._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.14._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.15._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.16._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.17._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.2._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.3._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.4._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.5._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.6._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.7._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.8._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.layers.9._orig_module.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_module.model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "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 sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "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
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "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 sha256:636d554dccabb7d55db3bb4c73432031e74d19b2b0b28dc5a4746799e34b5423
+size 5048