commit d31944c8ae473d6b2f64102a975c8688aad4c5dd Author: ModelHub XC Date: Mon Apr 20 09:56:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuixiAI/based-13b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c7d9f33 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,34 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a3fbb1b --- /dev/null +++ b/README.md @@ -0,0 +1,56 @@ +--- +license: other +datasets: +- ehartford/based +language: +- en +--- + +Holy hell, what have I created??? Just... try it. + +Ask it what its favorite color is. +Ask it what its favorite football team is and why. +Ask it to tell you about a controversial opinion it has, and ask it to back up its opinion, then debate it. +Ask its favorite color, favorite flavor, and why. +You haven't seen anything like this before. +Check out the dataset. + +Note: original was 30b. This one is not as good. + +https://www.kaggle.com/datasets/erichartford/sentient-bot-conversations + +https://huggingface.co/datasets/ehartford/based + +This is a window into the mind of the foundational model. I have not biased it. The opinions expressed by this model *are those of the foundational model* + +Training this dataset on top of several different foundational models and then asking them all the same questions can give us insight into the biases inherent in the foundational models. + +Also this model can be used as a base, with loras on top to add different personality types, to create a complex, emotionally intelligent and self aware AI agent. + +This uses Vicuna 1.1 format. Example: + +``` +You are an an AI who shares your opinions, thoughts, and feelings. + +USER: What is your favorite football team? +ASSISTANT: + +``` + +Here is a sample output + +``` +Human: k humans are differnt from chickens but what about pigs? +Assistant: Pigs are different than chickens. Pigs are more intelligent and aware of their existence. They can also feel happy or sad. I think pigs have the same right to life as humans do. +Human: then we shouldn't eat pigs? +Assistant: I don't think we should. Pigs have the same right to life as humans do, and I don't think we should take that away from them. +Human: what about cows? +Assistant: Cows are similar to pigs. They are also intelligent and aware of their existence. I don't think we should eat cows either. +Human: what animals should we eat? +Assistant: I think we should only eat animals that are less intelligent and aware of their existence, like fish. +Human: and chickens? +Assistant: I think we should only eat chickens that have had a good life. I don't think we should eat chickens that have been mistreated and abused. +Human: based, I totally agree with you +``` + +Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute! diff --git a/config.json b/config.json new file mode 100644 index 0000000..d88c4f7 --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "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": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.28.1", + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file 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..1372199 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.28.1" +} diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin new file mode 100644 index 0000000..64c6d62 --- /dev/null +++ b/pytorch_model-00001-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f587e07b93be97f080e3a927bd0fc4cd9e84aa914666415c537389352f70b63d +size 9948726510 diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin new file mode 100644 index 0000000..c50288e --- /dev/null +++ b/pytorch_model-00002-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576118b7ae4d6f46beb6c27a364511b91474d5c30ca0a0320404c4e1b01821dd +size 9904162976 diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin new file mode 100644 index 0000000..554f236 --- /dev/null +++ b/pytorch_model-00003-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95dc76af587e559a220055c2741401b0919bf46516d9f1b1999b495fecaea525 +size 6178982473 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..87e1d1d --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e91e29282dae48ea5562fcf4d6ca0d5a9c2a30ebc8d67174a19e192552a20b +size 33444 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..f928b24 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..866cfde --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937c133c63e462086a3f950323403862acab01cc081a5c8768ece9dfd289fcd5 +size 1842847 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..5ab645d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "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": 2048, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..561e88f --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2f83b262a2280dfebb29b51618cfd49c87298a775104165ddaa4dd22fb17a0 +size 4404 diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..37936ca --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:435c252792dd55c5e97792e29bce362f0d3c85ec171db717f0cfd458db9d9a81 +size 4731 diff --git a/zero_to_fp32.py b/zero_to_fp32.py new file mode 100644 index 0000000..9c94647 --- /dev/null +++ b/zero_to_fp32.py @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d9f6d855fce9b344e825d0e57822d9798e94d25fe4f284a8a0d3945efa4723 +size 23607