koichi12 commited on Feb 12, 2025

Commit

8943a07

verified ·

1 Parent(s): dd958be

Add files using upload-large-folder tool

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

.gitattributes +9 -0
llm_tutorial/eval/results/yans-baseline-qwen2-1.5B-3.5e-5-averaged/last_10.json +0 -0
llm_tutorial/llm_recipes/models/hf-model-eval/.gitattributes +35 -0
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja_3M-pairs_3.5e-5/iter_0000698/config.json +29 -0
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja_3M-pairs_3.5e-5/iter_0000698/tokenizer_config.json +83 -0
llm_tutorial/merged_models/en-ja-base_0.33+instruct/mergekit_config.yml +12 -0
llm_tutorial/merged_models/en-ja-base_0.33+instruct/tokenizer.json +0 -0
llm_tutorial/merged_models/en-ja-base_0.33/config.json +30 -0
llm_tutorial/merged_models/en-ja-base_0.33/mergekit_config.yml +12 -0
llm_tutorial/merged_models/en-ja-base_0.33/tokenizer.json +0 -0
llm_tutorial/merged_models/en-ja-base_dare-linear/config.json +30 -0
llm_tutorial/merged_models/en-ja-base_dare-linear/special_tokens_map.json +10 -0
llm_tutorial/merged_models/en-ja-base_dare-linear/tokenizer.json +0 -0
llm_tutorial/merged_models/en-ja-base_dare-linear/tokenizer_config.json +18 -0
llm_tutorial/merged_models/en-ja-base_dare/config.json +30 -0
llm_tutorial/merged_models/en-ja-base_dare/model.safetensors.index.json +1 -0
llm_tutorial/merged_models/en-ja-base_dare/tokenizer.json +0 -0
llm_tutorial/merged_models/en-ja-base_dare/tokenizer_config.json +18 -0
llm_tutorial/merged_models/en-ja_ja-en_base_linear+instruct/README.md +43 -0
llm_tutorial/merged_models/en-ja_ja-en_base_linear+instruct/mergekit_config.yml +12 -0
llm_tutorial/merged_models/en-ja_ja-en_base_linear/config.json +30 -0
llm_tutorial/merged_models/en-ja_ja-en_base_linear/mergekit_config.yml +12 -0
llm_tutorial/merged_models/en-ja_ja-en_base_linear/special_tokens_map.json +51 -0
llm_tutorial/merged_models/en-ja_ja-en_base_linear/tokenizer_config.json +83 -0
llm_tutorial/merged_models/en-ja_ja-en_instruct_dare-linear/config.json +30 -0
llm_tutorial/merged_models/en-ja_ja-en_instruct_dare-linear/mergekit_config.yml +12 -0
llm_tutorial/merged_models/en-ja_ja-en_instruct_dare-linear/special_tokens_map.json +51 -0
llm_tutorial/merged_models/en-ja_ja-en_instruct_dare-linear/tokenizer_config.json +84 -0
llm_tutorial/merged_models/en-ja_ja-en_instruct_linear_0.33/tokenizer_config.json +83 -0
llm_tutorial/merged_models/en-ja_ja-en_instruct_linear_0.5/tokenizer_config.json +84 -0
llm_tutorial/merged_models/en-ja_merged/model.safetensors.index.json +1 -0
llm_tutorial/merged_models/en-ja_merged/special_tokens_map.json +51 -0
llm_tutorial/merged_models/en-ja_merged/tokenizer.json +0 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/README.md +42 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/config.json +30 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/model.safetensors.index.json +1 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/special_tokens_map.json +51 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/tokenizer.json +0 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/tokenizer_config.json +84 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/README.md +42 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/model.safetensors.index.json +1 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/special_tokens_map.json +51 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/tokenizer.json +0 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/tokenizer_config.json +84 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties04-instruct/README.md +42 -0
llm_tutorial/merged_models4/ja-en_en-ja_ties04/tokenizer_config.json +18 -0
tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_adv_infer.so.8 +3 -0
tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_adv_train.so.8 +3 -0
tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_ops_train.so.8 +3 -0
tuning-competition-baseline/.venv/lib/python3.11/site-packages/sympy/concrete/tests/__pycache__/test_sums_products.cpython-311.pyc +3 -0

.gitattributes CHANGED Viewed

@@ -268,3 +268,12 @@ tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/curand/lib
 tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_ops_infer.so.8 filter=lfs diff=lfs merge=lfs -text
 tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cublas/lib/libcublas.so.11 filter=lfs diff=lfs merge=lfs -text
 tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_cnn_train.so.8 filter=lfs diff=lfs merge=lfs -text

 tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_ops_infer.so.8 filter=lfs diff=lfs merge=lfs -text
 tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cublas/lib/libcublas.so.11 filter=lfs diff=lfs merge=lfs -text
 tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_cnn_train.so.8 filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/triton/third_party/cuda/bin/cuobjdump filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/triton/third_party/cuda/bin/ptxas filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_ops_train.so.8 filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/triton/third_party/cuda/lib/libdevice.10.bc filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/lib/libtorch_cuda_linalg.so filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_adv_infer.so.8 filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/sympy/plotting/tests/__pycache__/test_series.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_adv_train.so.8 filter=lfs diff=lfs merge=lfs -text
+tuning-competition-baseline/.venv/lib/python3.11/site-packages/sympy/concrete/tests/__pycache__/test_sums_products.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text

llm_tutorial/eval/results/yans-baseline-qwen2-1.5B-3.5e-5-averaged/last_10.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llm_tutorial/llm_recipes/models/hf-model-eval/.gitattributes ADDED Viewed

	@@ -0,0 +1,35 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja_3M-pairs_3.5e-5/iter_0000698/config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_name_or_path": "/share/pretrained_lm/llm-jp/llm-jp-v3-3.7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 24,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "vocab_size": 99584
+}

llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja_3M-pairs_3.5e-5/iter_0000698/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,83 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

llm_tutorial/merged_models/en-ja-base_0.33+instruct/mergekit_config.yml ADDED Viewed

	@@ -0,0 +1,12 @@

+models:
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b
+    parameters:
+      weight: -1.0
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct
+    parameters:
+      weight: 1.0
+  - model: /home/koiwa/work/llm_tutorial/merged_models/en-ja-base_0.33
+    parameters:
+      weight: 1.0
+merge_method: linear
+dtype: float16

llm_tutorial/merged_models/en-ja-base_0.33+instruct/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llm_tutorial/merged_models/en-ja-base_0.33/config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "_name_or_path": "/home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model/llm-jp-v3-3.7b_ja-en_actual_3M-pairs/iter_0000698",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 24,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 99584
+}

llm_tutorial/merged_models/en-ja-base_0.33/mergekit_config.yml ADDED Viewed

	@@ -0,0 +1,12 @@

+models:
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model/llm-jp-v3-3.7b_ja-en_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.33
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model/llm-jp-v3-3.7b_ja-en_actual_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.33
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b
+    parameters:
+      weight: 0.33
+merge_method: linear
+dtype: float16

llm_tutorial/merged_models/en-ja-base_0.33/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llm_tutorial/merged_models/en-ja-base_dare-linear/config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "_name_or_path": "/work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 24,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 99584
+}

llm_tutorial/merged_models/en-ja-base_dare-linear/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+    "bos_token": "<s>",
+    "cls_token": "<CLS|LLM-jp>",
+    "eod_token": "</s>",
+    "eos_token": "</s>",
+    "mask_token": "<MASK|LLM-jp>",
+    "pad_token": "<PAD|LLM-jp>",
+    "sep_token": "<SEP|LLM-jp>",
+    "unk_token": "<unk>"
+}

llm_tutorial/merged_models/en-ja-base_dare-linear/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llm_tutorial/merged_models/en-ja-base_dare-linear/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "unk_token": "<unk>",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<PAD|LLM-jp>",
+  "cls_token": "<CLS|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "eod_token": "</s>",
+  "mask_token": "<MASK|LLM-jp>",
+  "extra_ids": 0,
+  "sp_model_kwargs": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "clean_up_tokenization_spaces": false,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

llm_tutorial/merged_models/en-ja-base_dare/config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "_name_or_path": "/work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 24,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 99584
+}

llm_tutorial/merged_models/en-ja-base_dare/model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"metadata": {"mergekit_version": "0.0.5.1", "total_size": 7565826048}, "weight_map": {"lm_head.weight": "model-00001-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors"}}

llm_tutorial/merged_models/en-ja-base_dare/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llm_tutorial/merged_models/en-ja-base_dare/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "unk_token": "<unk>",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<PAD|LLM-jp>",
+  "cls_token": "<CLS|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "eod_token": "</s>",
+  "mask_token": "<MASK|LLM-jp>",
+  "extra_ids": 0,
+  "sp_model_kwargs": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "clean_up_tokenization_spaces": false,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

llm_tutorial/merged_models/en-ja_ja-en_base_linear+instruct/README.md ADDED Viewed

	@@ -0,0 +1,43 @@

+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+# en-ja_ja-en_base_linear+instruct
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+## Merge Details
+### Merge Method
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
+### Models Merged
+The following models were included in the merge:
+* /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct
+* /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b
+* /home/koiwa/work/llm_tutorial/merged_models/en-ja_ja-en_base_linear
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+models:
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b
+    parameters:
+      weight: -1.0
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct
+    parameters:
+      weight: 1.0
+  - model: /home/koiwa/work/llm_tutorial/merged_models/en-ja_ja-en_base_linear
+    parameters:
+      weight: 1.0
+merge_method: linear
+dtype: float16
+```

llm_tutorial/merged_models/en-ja_ja-en_base_linear+instruct/mergekit_config.yml ADDED Viewed

	@@ -0,0 +1,12 @@

+models:
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b
+    parameters:
+      weight: -1.0
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct
+    parameters:
+      weight: 1.0
+  - model: /home/koiwa/work/llm_tutorial/merged_models/en-ja_ja-en_base_linear
+    parameters:
+      weight: 1.0
+merge_method: linear
+dtype: float16

llm_tutorial/merged_models/en-ja_ja-en_base_linear/config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "_name_or_path": "/home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model/llm-jp-v3-3.7b_ja-en_actual_3M-pairs/iter_0000698",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 24,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 99584
+}

llm_tutorial/merged_models/en-ja_ja-en_base_linear/mergekit_config.yml ADDED Viewed

	@@ -0,0 +1,12 @@

+models:
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model/llm-jp-v3-3.7b_ja-en_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model/llm-jp-v3-3.7b_ja-en_actual_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16

llm_tutorial/merged_models/en-ja_ja-en_base_linear/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llm_tutorial/merged_models/en-ja_ja-en_base_linear/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,83 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

llm_tutorial/merged_models/en-ja_ja-en_instruct_dare-linear/config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "_name_or_path": "/work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 24,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 99584
+}

llm_tutorial/merged_models/en-ja_ja-en_instruct_dare-linear/mergekit_config.yml ADDED Viewed

	@@ -0,0 +1,12 @@

+models:
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model/llm-jp-v3-3.7b_ja-en_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model/llm-jp-v3-3.7b_ja-en_actual_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+  - model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16

llm_tutorial/merged_models/en-ja_ja-en_instruct_dare-linear/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llm_tutorial/merged_models/en-ja_ja-en_instruct_dare-linear/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,84 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\\n\\n### 指示:\\n' + message['content'] }}{% elif message['role'] == 'system' %}{{ '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}{% elif message['role'] == 'assistant' %}{{ '\\n\\n### 応答:\\n' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\\n\\n### 応答:\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

llm_tutorial/merged_models/en-ja_ja-en_instruct_linear_0.33/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,83 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

llm_tutorial/merged_models/en-ja_ja-en_instruct_linear_0.5/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,84 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\\n\\n### 指示:\\n' + message['content'] }}{% elif message['role'] == 'system' %}{{ '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}{% elif message['role'] == 'assistant' %}{{ '\\n\\n### 応答:\\n' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\\n\\n### 応答:\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

llm_tutorial/merged_models/en-ja_merged/model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1 @@

llm_tutorial/merged_models/en-ja_merged/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llm_tutorial/merged_models/en-ja_merged/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/README.md ADDED Viewed

	@@ -0,0 +1,42 @@

+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+# ja-en_en-ja_ties01-instruct
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+## Merge Details
+### Merge Method
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct as a base.
+### Models Merged
+The following models were included in the merge:
+* /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698
+* /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+models:
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+      density: 0.1
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+      density: 0.1
+base_model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct
+merge_method: ties
+dtype: float16
+```

llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "_name_or_path": "/work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 24,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 99584
+}

llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1 @@

llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llm_tutorial/merged_models4/ja-en_en-ja_ties01-instruct/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,84 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\\n\\n### 指示:\\n' + message['content'] }}{% elif message['role'] == 'system' %}{{ '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}{% elif message['role'] == 'assistant' %}{{ '\\n\\n### 応答:\\n' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\\n\\n### 応答:\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/README.md ADDED Viewed

	@@ -0,0 +1,42 @@

+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+# ja-en_en-ja_ties02-instruct
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+## Merge Details
+### Merge Method
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct as a base.
+### Models Merged
+The following models were included in the merge:
+* /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698
+* /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+models:
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+      density: 0.2
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+      density: 0.2
+base_model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct
+merge_method: ties
+dtype: float16
+```

llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1 @@

llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llm_tutorial/merged_models4/ja-en_en-ja_ties02-instruct/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,84 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\\n\\n### 指示:\\n' + message['content'] }}{% elif message['role'] == 'system' %}{{ '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}{% elif message['role'] == 'assistant' %}{{ '\\n\\n### 応答:\\n' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\\n\\n### 応答:\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

llm_tutorial/merged_models4/ja-en_en-ja_ties04-instruct/README.md ADDED Viewed

	@@ -0,0 +1,42 @@

+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+# ja-en_en-ja_ties04-instruct
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+## Merge Details
+### Merge Method
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct as a base.
+### Models Merged
+The following models were included in the merge:
+* /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698
+* /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+models:
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+      density: 0.4
+  - model: /home/koiwa/work/llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698
+    parameters:
+      weight: 0.5
+      density: 0.4
+base_model: /work01/llm_tutorial/pretrained_lm/llm-jp/llm-jp-v3-3.7b-instruct
+merge_method: ties
+dtype: float16
+```

llm_tutorial/merged_models4/ja-en_en-ja_ties04/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "unk_token": "<unk>",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<PAD|LLM-jp>",
+  "cls_token": "<CLS|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "eod_token": "</s>",
+  "mask_token": "<MASK|LLM-jp>",
+  "extra_ids": 0,
+  "sp_model_kwargs": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "clean_up_tokenization_spaces": false,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_adv_infer.so.8 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b862c716d29e90b519fd9e6cf50662d2e43c6e8cc4fed39d4f1d0f60d59cc62
+size 130420936

tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_adv_train.so.8 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8b8107b64d4ab6a73ce184d301b71e14c2b1bb469ef5734a1baa3a100847d4
+size 121126456

tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cudnn/lib/libcudnn_ops_train.so.8 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:55f5be9ff52def2ff9ba1438b85fb7ecfbfa37d0a0989b746788b39aef81bfe7
+size 74719784

tuning-competition-baseline/.venv/lib/python3.11/site-packages/sympy/concrete/tests/__pycache__/test_sums_products.cpython-311.pyc ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d59dd60d39096f49fbc4b1be2e960983f79fa2ef4c288e2e227a76fefa445d45
+size 187646