commit c2e6f1153a8204757eb69d186c5796ab493e989f Author: ModelHub XC Date: Fri May 29 20:07:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MBZUAI/bactrian-x-llama-7b-merged Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..087eecf --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +license: mit +--- + +#### Current Training Steps: 100,000 + + +This repo contains a merged model using low-rank adaptation (LoRA) for LLaMA-7b +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). + +

+ +

+ +### 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-7b-hf' \ + --num_epochs=10 \ + --batch_size=128 \ + --cutoff_len=512 \ + --group_by_length \ + --output_dir='./bactrian-x-llama-7b-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} +} +``` diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e41416d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "[PAD]": 32000 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..9ff0927 --- /dev/null +++ b/config.json @@ -0,0 +1,24 @@ +{ + "_name_or_path": "decapoda-research/llama-7b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 0, + "eos_token_id": 1, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 2048, + "max_sequence_length": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "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 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..96af869 --- /dev/null +++ b/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" +} diff --git a/pytorch_model-00001-of-00007.bin b/pytorch_model-00001-of-00007.bin new file mode 100644 index 0000000..07ffb09 --- /dev/null +++ b/pytorch_model-00001-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f648c66885b2bdc545cec3b33184e9056626016a8023cf4af12edaa20957c5c4 +size 2015453451 diff --git a/pytorch_model-00002-of-00007.bin b/pytorch_model-00002-of-00007.bin new file mode 100644 index 0000000..fc4ab5e --- /dev/null +++ b/pytorch_model-00002-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2e98b46b054ba7143af9bbe9284c8b2668762ffe0318070dc38b4e893bdec0d +size 2023851603 diff --git a/pytorch_model-00003-of-00007.bin b/pytorch_model-00003-of-00007.bin new file mode 100644 index 0000000..52fe2f0 --- /dev/null +++ b/pytorch_model-00003-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd15c014ec31c9355c6a97e4ad9090d5b209c072e13ab6663bb4c2298b1c4a9 +size 2023851667 diff --git a/pytorch_model-00004-of-00007.bin b/pytorch_model-00004-of-00007.bin new file mode 100644 index 0000000..9c7bfdd --- /dev/null +++ b/pytorch_model-00004-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074507a121281d820df7a64157babfc695f105b650330fe32acbc209588fe81b +size 2023851667 diff --git a/pytorch_model-00005-of-00007.bin b/pytorch_model-00005-of-00007.bin new file mode 100644 index 0000000..9f0de8a --- /dev/null +++ b/pytorch_model-00005-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d24d5da5a92bc36101ee0eb1f32ebb63e42fd1b509c9a58690b44da32ab06ea3 +size 2023851667 diff --git a/pytorch_model-00006-of-00007.bin b/pytorch_model-00006-of-00007.bin new file mode 100644 index 0000000..f2817fc --- /dev/null +++ b/pytorch_model-00006-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c407f028fa71f5ca0d89390680a302a329a19e64cc86a88e9c6772e374a08e2 +size 2023851667 diff --git a/pytorch_model-00007-of-00007.bin b/pytorch_model-00007-of-00007.bin new file mode 100644 index 0000000..1d42be1 --- /dev/null +++ b/pytorch_model-00007-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1ceba81cd11ab9b4dcb461be37039eeb6f51689f5adab8dd1af3d4e931d79b9 +size 1342252341 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..7160f6f --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a46e38f983f8f313b91ef8f9e39456478bb9f43314c4bb23b0ee93e98452fa0 +size 26788 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..3f58a5e --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "[PAD]", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9a53a9d --- /dev/null +++ b/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 + } +}