commit c86ad429e95a3d7666aad9ef9dae4bf8ab9e8289 Author: ModelHub XC Date: Sat Jun 6 14:40:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Gryphe/MythoLogic-L2-13b 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/MythoLogic-L2.png b/MythoLogic-L2.png new file mode 100644 index 0000000..e69541b Binary files /dev/null and b/MythoLogic-L2.png differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..a5dbad1 --- /dev/null +++ b/README.md @@ -0,0 +1,33 @@ +--- +license: other +language: +- en +--- +The Llama 2 sequel to my [original experiment](https://huggingface.co/Gryphe/MythoLogic-13b) with gradient merges using [the following script](https://github.com/Gryphe/BlockMerge_Gradient). Its three models ([Hermes](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b), [Chronos](https://huggingface.co/elinas/chronos-13b-v2) and [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-13b-gpt4-2.0)) are almost evenly divided over the layer structure this time. Airoboros was the "wildcard model" due to its superior ability to understand complex instructions. + +Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ) (You're the best!) + +## Model details + +As before, the main objective was to create an all-round model with improved roleplaying capabilities. MythoLogic-L2 differs from its predecessor in that it focuses primarily on the understanding of instructions and personalities of complex character cards. + +Illustrated below are the gradients used for this specific L2 recipe, with the top of the image representing layer 0 and the bottom layer 40. + +![](MythoLogic-L2.png) + +## Prompt Format + +This model primarily uses (and was heavily tested with) Alpaca formatting, so for optimal model performance, use: +``` + + +### Instruction: +Your instruction or question here. +For roleplay purposes, I suggest the following - Write 's next reply in a chat between and . Write a single reply only. + +### Response: +``` + +--- +license: other +--- \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..9c16aa4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "": 32000 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..7637217 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "MythoLogic-L2-13b", + "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": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.32.0.dev0", + "use_cache": false, + "vocab_size": 32000 +} 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..c8a0a69 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "max_length": 4096, + "pad_token_id": 0, + "temperature": 0.9, + "top_p": 0.6, + "transformers_version": "4.32.0.dev0" +} diff --git a/pytorch_model-00001-of-00013.bin b/pytorch_model-00001-of-00013.bin new file mode 100644 index 0000000..ebdfd91 --- /dev/null +++ b/pytorch_model-00001-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d530c5e26f041cbea152563b2a1307f8c795f79471aad55caea01d288303c046 +size 2089337041 diff --git a/pytorch_model-00002-of-00013.bin b/pytorch_model-00002-of-00013.bin new file mode 100644 index 0000000..2e6e206 --- /dev/null +++ b/pytorch_model-00002-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af76e3397e3d53e986b52cf315049247caf16b0ec8b9cd75f62d6540401c696b +size 2044815083 diff --git a/pytorch_model-00003-of-00013.bin b/pytorch_model-00003-of-00013.bin new file mode 100644 index 0000000..46e9d98 --- /dev/null +++ b/pytorch_model-00003-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636f175c4bdbb22e112eddba5ba83fb5c51b3cd26d3e42d6d387a1078a1880fd +size 2060523307 diff --git a/pytorch_model-00004-of-00013.bin b/pytorch_model-00004-of-00013.bin new file mode 100644 index 0000000..6048a7f --- /dev/null +++ b/pytorch_model-00004-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1822e06ef0c7a49bcd0e1acf8057f38a399b3e2cbc325ab499d8508ecf6d03 +size 1955665095 diff --git a/pytorch_model-00005-of-00013.bin b/pytorch_model-00005-of-00013.bin new file mode 100644 index 0000000..d7bd01b --- /dev/null +++ b/pytorch_model-00005-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de13cc9dfd699e3f18abae8a8606cb6731121bb162932676800b1324c48502d +size 2044794055 diff --git a/pytorch_model-00006-of-00013.bin b/pytorch_model-00006-of-00013.bin new file mode 100644 index 0000000..588b5db --- /dev/null +++ b/pytorch_model-00006-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:470ac0b71c7785225fdd3bb734cf2acf28ddc364267faf7ea999436d169e2f98 +size 2044794055 diff --git a/pytorch_model-00007-of-00013.bin b/pytorch_model-00007-of-00013.bin new file mode 100644 index 0000000..4793b51 --- /dev/null +++ b/pytorch_model-00007-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9813becb89c54a2c511303083a964792b2af44c75e279792dc7465541ad9060 +size 2044815147 diff --git a/pytorch_model-00008-of-00013.bin b/pytorch_model-00008-of-00013.bin new file mode 100644 index 0000000..c217dba --- /dev/null +++ b/pytorch_model-00008-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2bbbf2a11ceac9b508ab4b41355d9d52d6e4e824166d1ac06bcd8d609a547e +size 2060523307 diff --git a/pytorch_model-00009-of-00013.bin b/pytorch_model-00009-of-00013.bin new file mode 100644 index 0000000..b0f9a38 --- /dev/null +++ b/pytorch_model-00009-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5591e915c435ecac97d3e36aef2233ed2c67f595ab90bc73c61a6fda639d3dbc +size 1955665095 diff --git a/pytorch_model-00010-of-00013.bin b/pytorch_model-00010-of-00013.bin new file mode 100644 index 0000000..3fddef0 --- /dev/null +++ b/pytorch_model-00010-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd295ae55290bd38e02db8422f5f53cea1d85376fbf0e16e8c0f6e94d629e85 +size 2044794055 diff --git a/pytorch_model-00011-of-00013.bin b/pytorch_model-00011-of-00013.bin new file mode 100644 index 0000000..327776d --- /dev/null +++ b/pytorch_model-00011-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea29e98334aeab3749f0cbad2a86100e15e5208299e6b8776c06392945e8d2e3 +size 2044794055 diff --git a/pytorch_model-00012-of-00013.bin b/pytorch_model-00012-of-00013.bin new file mode 100644 index 0000000..1f16b2a --- /dev/null +++ b/pytorch_model-00012-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a4c2a75d88a224f88db7039fb892e58e54f5c0c9fafe702c47f77c838b6fc4b +size 2044815147 diff --git a/pytorch_model-00013-of-00013.bin b/pytorch_model-00013-of-00013.bin new file mode 100644 index 0000000..fc8199e --- /dev/null +++ b/pytorch_model-00013-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6563cf73e5444b22e7a0b82a7cc98db48a2cd84b4a8f99b80a82b40227188c22 +size 1596514999 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..324bde8 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110bed6b5024f0e81614529f3517f10937e67abfb56ba4b1ba0f377c8a0f32db +size 29894 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..14761dc --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} 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..508754b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,35 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "legacy": false, + "model_max_length": 4096, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +}