Upload model

README.md

@@ -1,82 +1,6 @@
 ---
 library_name: peft
-license: llama2
-datasets:
-- izumi-lab/llm-japanese-dataset
-language:
-- ja
-pipeline_tag: text-generation
 ---
-## AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese
-
-This model is Llama-2-Chat 70B fine-tuned with a part of the following Japanese dataset.
-
-[https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset](https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset)
-
-```
-from datasets import load_dataset
-dataset = load_dataset("izumi-lab/llm-japanese-dataset", revision="main")
-```
-
-- 1000 steps
-- batch_size = 4
-
-
-## Copyright Notice
-
-This model is built on the copyright of Meta's LLaMA series.
-
-Users of this model must also agree to Meta's license.
-
-[https://ai.meta.com/llama/](https://ai.meta.com/llama/)
-
-
-## How to use
-
-```
-import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "0,1,2,3"
-import torch
-torch.cuda.empty_cache()
-from peft import PeftModel
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoConfig
-
-#Load model
-model_id = "meta-llama/Llama-2-70b-chat-hf"
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
-config = AutoConfig.from_pretrained(model_id)
-config.pretraining_tp = 1
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, 
-                                             device_map="auto")
-
-#Load weights
-peft_name = "AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese"
-model_peft  = PeftModel.from_pretrained(
-    model, 
-    peft_name, 
-    device_map="auto"
-)
-model_peft.eval()
-
-
-device = "cuda:0"
-
-text = "### Human: 東京大学の住所は？ ### Assistant: "
-inputs = tokenizer(text, return_tensors="pt").to(device)
-with torch.no_grad():
-  outputs = model.generate(**inputs, max_new_tokens=100)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-
-### Human: 東京大学の住所は？ ### Assistant: 東京大学の住所は、東京都文京区本郷7丁目3番1号です。
-```
-
-
 ## Training procedure
 
 
@@ -93,4 +17,4 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
-- PEFT 0.4.0
+- PEFT 0.4.0

adapter_config.json

@@ -14,13 +14,13 @@
   "r": 64,
   "revision": null,
   "target_modules": [
+    "q_proj",
     "o_proj",
-    "up_proj",
     "v_proj",
-    "q_proj",
     "gate_proj",
+    "k_proj",
     "down_proj",
-    "k_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388ba0e692c5f4d4a23348378c4a37a760e8fd62ef845b25f405137565a70a61
+oid sha256:bec19307c7b9c4fab1b1a24910f91845ab3f837f2d0d59de53b346da1edd056f
 size 3313905157