Upload folder using huggingface_hub

README.md

@@ -1,35 +1,21 @@
 ---
-license: mit
-language:
-- ja
+library_name: peft
 ---
-Mistral-7B LAPT + CLP+ Japanese
-===
+## Training procedure
 
-## How to use
-```python
-from peft import AutoPeftModelForCausalLM
-from transformers import AutoTokenizer
 
-model = AutoPeftModelForCausalLM.from_pretrained(
-  "atsuki-yamaguchi/Mistral-7B-v0.1-clpp-ja"
-)
-tokenizer = AutoTokenizer.from_pretrained(
-  "atsuki-yamaguchi/Mistral-7B-v0.1-clpp-ja"
-)
-```
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
 
-## Citation
-```
-@article{yamaguchi2024empirical,
-  title={An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative {LLM} Inference}, 
-  author={Atsuki Yamaguchi and Aline Villavicencio and Nikolaos Aletras},
-  journal={ArXiv},
-  year={2024},
-  volume={abs/2402.10712},
-  url={https://arxiv.org/abs/2402.10712}
-}
-```
 
-## Link
-For more details, please visit https://github.com/gucci-j/llm-cva
+- PEFT 0.5.0

adapter_config.json

@@ -1,29 +1 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "atsuki-yamaguchi/Mistral-7B-v0.1-clpp-ja",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
-  "modules_to_save": [
-    "lm_head",
-    "embed_tokens"
-  ],
-  "peft_type": "LORA",
-  "r": 8,
-  "revision": null,
-  "target_modules": [
-    "q_proj",
-    "v_proj",
-    "k_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}
+{"auto_mapping": null, "base_model_name_or_path": "atsuki-yamaguchi/Mistral-7B-v0.1-clpp-ja", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layers_pattern": null, "layers_to_transform": null, "lora_alpha": 32, "lora_dropout": 0.05, "modules_to_save": ["lm_head", "embed_tokens"], "peft_type": "LORA", "r": 8, "revision": null, "target_modules": ["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "task_type": "CAUSAL_LM"}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Mistral-7B-v0.1-ja-clp-plus",
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -18,7 +18,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float64",
   "transformers_version": "4.35.0.dev0",
   "use_cache": true,
   "vocab_size": 32000

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e436861c8cf471e17cc9bb08daf046a00f98d710f91ce68c74fd70e28cb94747
-size 4987196936
+oid sha256:d6deef5ea687d29e730b7861e369102168c3929aa1174631bc4c9ec8ad5095fd
+size 4941026032

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:539496de5ecdf05ff99768d9dfbfde25838361eb4a3214c9ca70138ca46d92da
-size 4899116440
+oid sha256:9d32f4e850f6bda3b1aa1fd85a372377274b9a8a166dab9047fd4cd958199746
+size 4999813072

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686283795d1b7ec495bdfdff1029d1c240da2213c6cce65d32d2f76de8ce54b3
-size 4999813120
+oid sha256:8f3b1794261ba1e27810d553cd2b5f949fcc3a6fe37ba9b09f5033bc7e5de472
+size 4832007496

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c71ef152c6b70d2114c3e6348df73d7f70fa5a020267f9ddb9163fb0dad519
-size 4999813128
+oid sha256:f72da02290a5f95304a8cff4c7216f30405a3f0072ac1b2b1a906e9748ff10a7
+size 4999813120

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4feb6b67528bcad53df28e1771317e0796f663767c8f1b1fc56b270c238d464
-size 4832007496
+oid sha256:f289adb9a536fe1aed9ba102e26c6b07185a467cb77def237d8715d378831662
+size 4999813128

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94286ed0b0dcf9c76517e52fea70500a901795b4ed0667b2e0060431c1aa76f6
-size 4249014896
+oid sha256:be962dec7dca8150b39d0a05b00e8181a30446d8510bbdd1fb5b96b8d4017cd4
+size 4718777176

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 28966928384
+    "total_size": 29491216384
   },
   "weight_map": {
     "lm_head.weight": "model-00006-of-00006.safetensors",
@@ -25,8 +25,8 @@
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
@@ -68,24 +68,24 @@
     "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
@@ -131,11 +131,11 @@
     "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
@@ -145,10 +145,10 @@
     "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
@@ -187,8 +187,8 @@
     "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
@@ -239,11 +239,11 @@
     "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
@@ -253,10 +253,10 @@
     "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf9cc3eb296729d77de6918b554460f2e0b5386fda248f222c235e779193b55
+size 567855324

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21655ba8bdde9d44ecb6be12e1fe5543c4cdb67e0e5a746b9dcacce9091f703
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394f63e155c1870e1adf89d6e808adbedc007a65149566630f394b538ee37fe7
+size 1064

special_tokens_map.json

@@ -1,18 +1,6 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
@@ -20,13 +8,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "[MASK]",
   "pad_token": {
     "content": "[PAD]",
     "lstrip": false,
@@ -34,13 +16,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "sep_token": "[SEP]",
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ca55416176e6a638fb88f1e1e385f0b51da4a42d9ff8b55573866968fc2805
+size 4664