End of training

README.md

@@ -1,3 +1,50 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+base_model: output/llama2-ddm
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: diffullama
+  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. -->
+
+# diffullama
+
+This model is a fine-tuned version of [output/llama2-ddm](https://huggingface.co/output/llama2-ddm) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "output/llama2-ddm",
+  "architectures": [
+    "DiscreteDiffusionModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1b1456ee0114f2d578f9f345f20c6913309923b357915fdcbb40d510c76e29
+size 4938986152

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb1677f5e09762c5cd9d7b2d2c28f2652b03cf4c4a3145b85b5e9e3c806ce68
+size 4947391752

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c0887fed90548d21054d3a3824c3a1e9bb62fa7849d224f14fe4cd3a5494a3
+size 3328345304

model.safetensors.index.json

@@ -0,0 +1,297 @@
+{
+  "metadata": {
+    "total_size": 13214687232
+  },
+  "weight_map": {
+    "denoise_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "denoise_model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "denoise_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "denoise_model.norm.weight": "model-00003-of-00003.safetensors",
+    "embed_tokens.weight": "model-00001-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "ти",
+  "pad_token": "¨",
+  "sep_token": "========",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "mask_token": "ти",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "¨",
+  "padding_side": "right",
+  "sep_token": "========",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7103635ce5c20a6f6d01c93cefbc398a78e2de5a61db27adcfac95d8f56714ba
+size 5368