Upload 5 files

README.md

@@ -0,0 +1,49 @@
+---
+license: apache-2.0
+inference: false
+language: ja
+---
+
+# japanese-large-lm-3.6b-instruction-sft-4bit-128g-actorder_False
+
+This repository provides a 3.6B parameters Japanese language **quantized** model, fine-tuned and trained by [LINE Corporation](https://linecorp.com/ja/).
+
+## For Japanese
+
+詳細な説明や実験に関しては「[【インターンレポート】量子化による大規模言語モデル軽量化の効果測定](https://engineering.linecorp.com/ja/blog/quantization-lightweighting-llms)」をご覧ください。
+
+## How to use
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("line-corporation/japanese-large-lm-3.6b-instruction-sft", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained("line-corporation/japanese-large-lm-3.6b-instruction-sft-4bit-128g-actorder_False")
+ 
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
+ 
+input_text = """四国の県名を全て列挙してください。"""
+text = generator(
+    f"ユーザー: {input_text}\nシステム: ",
+    max_length = 256,
+    do_sample = True,
+    temperature = 0.7,
+    top_p = 0.9,
+    top_k = 0,
+    repetition_penalty = 1.1,
+    num_beams = 1,
+    pad_token_id = tokenizer.pad_token_id,
+    num_return_sequences = 1,
+)
+print(text) # [{'generated_text': 'ユーザー: 四国の県名を全て列挙してください。\nシステム:  高知県、徳島県、香川県、愛媛県'}]
+```
+
+## Tokenization
+
+We use a sentencepiece tokenizer with a unigram language model and byte-fallback.
+We **do not** apply pre-tokenization with Japanese tokenizer.
+Thus, a user may directly feed raw sentences into the tokenizer.
+
+## License
+[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "line-corporation/japanese-large-lm-3.6b-instruction-sft",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_dropout": 0.1,
+  "end_token_id": 2,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "pad_token_id": 2,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.0",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 51200
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a418523e898e651bdc8ab353d9ddef196a7eafbc567a63685467a209e403989
+size 2399277296

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96d0124f7d0ff32b21cabbc6cd414aafab488916a5ec436b6c543b4005e89fb
+size 2084891970

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "quantized/line-corporation/japanese-large-lm-3.6b-instruction-sft/gptq-4bit-128g-actorder_False",
+  "model_file_base_name": "gptq_model-4bit-128g"
+}