初始化项目，由ModelHub XC社区提供模型

Model: MBZUAI/bactrian-x-llama-13b-merged
Source: Original Platform

.gitattributes

@@ -0,0 +1,47 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+---
+
+#### Current Training Steps: 108,000
+
+
+This repo contains a merged model using low-rank adaptation (LoRA) for LLaMA-13b 
+fit on the [Stanford-Alpaca-52k](https://github.com/tatsu-lab/stanford_alpaca)
+and [databricks-dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data) data in 52 languages.
+
+### Dataset Creation
+
+1. English Instructions: The English instuctions are obtained from [alpaca-52k](https://github.com/tatsu-lab/stanford_alpaca), and [dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data).
+2. Instruction Translation: The instructions (and inputs) are translated into the target languages using Google Translation API (conducted on April 2023).
+3. Output Generation: We generate output from `gpt-3.5-turbo` for each language (conducted on April 2023).
+
+<h3 align="center">
+<img src="https://raw.githubusercontent.com/fajri91/eval_picts/master/BactrianX_dataset.jpg" width="950" align="center">
+</h3>
+
+### Training Parameters
+
+The code for training the model is provided in our [github](https://github.com/mbzuai-nlp/Bactrian-X), which is adapted from [Alpaca-LoRA](https://github.com/tloen/alpaca-lora).
+This version of the weights was trained with the following hyperparameters:
+
+
+- Epochs: 10
+- Batch size: 128
+- Cutoff length: 512
+- Learning rate: 3e-4
+- Lora _r_: 64
+- Lora target modules: q_proj, k_proj, v_proj, o_proj
+
+
+That is:
+
+```
+python finetune.py \
+    --base_model='decapoda-research/llama-13b-hf' \
+    --num_epochs=5 \
+    --batch_size=128 \
+    --cutoff_len=512 \
+    --group_by_length \
+    --output_dir='./bactrian-x-llama-13b-lora' \
+    --lora_target_modules='q_proj,k_proj,v_proj,o_proj' \
+    --lora_r=64 \
+    --micro_batch_size=32
+```
+
+Instructions for running it can be found at https://github.com/MBZUAI-nlp/Bactrian-X.
+
+### Discussion of Biases
+
+(1) Translation bias; (2) Potential English-culture bias in the translated dataset.
+
+
+### Citation Information
+
+```
+@misc{li2023bactrianx,
+      title={Bactrian-X : A Multilingual Replicable Instruction-Following Model with Low-Rank Adaptation}, 
+      author={Haonan Li and Fajri Koto and Minghao Wu and Alham Fikri Aji and Timothy Baldwin},
+      year={2023},
+      eprint={2305.15011},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "decapoda-research/llama-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af0a0639a6ff6e9acc404afecc6e3c790220c3b0a55215218359306b2e1f2f40
+size 2582179025

pytorch_model-00002-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18000bb812e36c3392bc023c809e2140624ff53bf5faae22c536e52cfa301282
+size 2996377799

pytorch_model-00003-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b87d073aeeaa25ad17443a63b6a220edb947864bc3d56bfa86ea96c6d747689
+size 3313592985

pytorch_model-00004-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55f2a1be007e0acca126f0241cab50a9f4e87c98cba08765b314b281ee68a15
+size 2959678041

pytorch_model-00005-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f44ee5d124834239892942a2581b4035634466f0c0f463759a9546041aa507
+size 2959678635

pytorch_model-00006-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364a7e5ff8c746152f4b957bc14abcbe30fb30fdc0e62a5d987f32caa6cc609c
+size 2996377863

pytorch_model-00007-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d354da4d7d88bb788813adb72e1bd4318b323cf03bf630b22fa23dcc7df5d5
+size 2996377863

pytorch_model-00008-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e072df4b28cb9b76be25c6c22b7df77ecf29640f5452d81522d155cba18beae6
+size 3313593049

pytorch_model-00009-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064e9fb387648a0fe7ccd6f921c857090a1d3cb6d70a048d416d04864e30a452
+size 2959678041

pytorch_model-00010-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bdd5b774d738bfa8dcadff68298d32b4b403869866d32bccc35dbd571bf3a0
+size 2959678635

pytorch_model-00011-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500badeb35772b1d9139b6e63e3a8c409fbe9cadcd41fbf50d13d9d36e246720
+size 2996377863

pytorch_model-00012-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf293bd051d337d5e23f037dfcf4652ea5056dd9ee7d209c255ea3215fd9d2e9
+size 2996377863

pytorch_model-00013-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015e760366136cda7384f2e088f5b4bd9f71b9ab5f63c49f2df3823dd5d874a9
+size 3017367643

pytorch_model.bin.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d45e8cc0f5dc0663bd4987a19631fcc783d868511d5b9c0b668cc3b5437aee3
+size 33444

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}