From 3dc05ec3760af9f88c6e5525f0fba33122ad7725 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 6 Jun 2026 14:34:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: Gryphe/MythoMax-L2-13b Source: Original Platform --- .gitattributes | 47 ++++++++++++++++++++++++++++++++ README.md | 37 +++++++++++++++++++++++++ added_tokens.json | 3 ++ config.json | 26 ++++++++++++++++++ configuration.json | 1 + generation_config.json | 10 +++++++ pytorch_model-00001-of-00013.bin | 3 ++ pytorch_model-00002-of-00013.bin | 3 ++ pytorch_model-00003-of-00013.bin | 3 ++ pytorch_model-00004-of-00013.bin | 3 ++ pytorch_model-00005-of-00013.bin | 3 ++ pytorch_model-00006-of-00013.bin | 3 ++ pytorch_model-00007-of-00013.bin | 3 ++ pytorch_model-00008-of-00013.bin | 3 ++ pytorch_model-00009-of-00013.bin | 3 ++ pytorch_model-00010-of-00013.bin | 3 ++ pytorch_model-00011-of-00013.bin | 3 ++ pytorch_model-00012-of-00013.bin | 3 ++ pytorch_model-00013-of-00013.bin | 3 ++ pytorch_model.bin.index.json | 3 ++ special_tokens_map.json | 24 ++++++++++++++++ tokenizer.model | 3 ++ tokenizer_config.json | 35 ++++++++++++++++++++++++ 23 files changed, 228 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 pytorch_model-00001-of-00013.bin create mode 100644 pytorch_model-00002-of-00013.bin create mode 100644 pytorch_model-00003-of-00013.bin create mode 100644 pytorch_model-00004-of-00013.bin create mode 100644 pytorch_model-00005-of-00013.bin create mode 100644 pytorch_model-00006-of-00013.bin create mode 100644 pytorch_model-00007-of-00013.bin create mode 100644 pytorch_model-00008-of-00013.bin create mode 100644 pytorch_model-00009-of-00013.bin create mode 100644 pytorch_model-00010-of-00013.bin create mode 100644 pytorch_model-00011-of-00013.bin create mode 100644 pytorch_model-00012-of-00013.bin create mode 100644 pytorch_model-00013-of-00013.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json 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..073114a --- /dev/null +++ b/README.md @@ -0,0 +1,37 @@ +--- +license: other +language: +- en +--- +With Llama 3 released, it's time for MythoMax to slowly fade away... [Let's do it in style!](https://suno.com/song/3d69cd72-e893-4193-866f-385f47778ce0) + +An improved, potentially even perfected variant of MythoMix, my [MythoLogic-L2](https://huggingface.co/Gryphe/MythoLogic-L2-13b) and [Huginn](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16) merge using a highly experimental tensor type merge technique. The main difference with MythoMix is that I allowed more of Huginn to intermingle with the single tensors located at the front and end of a model, resulting in increased coherency across the entire structure. + +The script and the acccompanying templates I used to produce both can [be found here](https://github.com/Gryphe/BlockMerge_Gradient/tree/main/YAML). + +This model is proficient at both roleplaying and storywriting due to its unique nature. + +Quantized models are available from TheBloke: [GGUF](https://huggingface.co/TheBloke/MythoMax-L2-13B-GGUF) - [GPTQ](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ) - [AWQ](https://huggingface.co/TheBloke/MythoMax-L2-13B-AWQ) (You're the best!) + +## Model details + +The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time) + +This type of merge is incapable of being illustrated, as each of its 363 tensors had an unique ratio applied to it. As with my prior merges, gradients were part of these ratios to further finetune its behaviour. + +## Prompt Format + +This model primarily uses 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..45d0a76 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "mythomax-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": true, + "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..a32a197 --- /dev/null +++ b/pytorch_model-00001-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4603db4e956f1161e6c1ff8a68ee83df19f9221d9239e3fd667465b41859f3d3 +size 2089337041 diff --git a/pytorch_model-00002-of-00013.bin b/pytorch_model-00002-of-00013.bin new file mode 100644 index 0000000..9240292 --- /dev/null +++ b/pytorch_model-00002-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf2b99bf2574f97139d9b8345b46d6cf85934eab2df8aa983e6f617873bd7d1 +size 2044815083 diff --git a/pytorch_model-00003-of-00013.bin b/pytorch_model-00003-of-00013.bin new file mode 100644 index 0000000..c46f526 --- /dev/null +++ b/pytorch_model-00003-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffe674094c5280990fbd71c11bc3284af2e953d27ad727952f9fae009da9db2 +size 2060523307 diff --git a/pytorch_model-00004-of-00013.bin b/pytorch_model-00004-of-00013.bin new file mode 100644 index 0000000..c963fdc --- /dev/null +++ b/pytorch_model-00004-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f9bace05de619c2f5c7b067c4bd009f11b728ccae11fa3571ae1d9b5b83d26 +size 1955665095 diff --git a/pytorch_model-00005-of-00013.bin b/pytorch_model-00005-of-00013.bin new file mode 100644 index 0000000..e2a0363 --- /dev/null +++ b/pytorch_model-00005-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eadeb942cd2e2d94b9fe21bc87c1fb7c39fe944cd9e34d880563a1cc5cb47230 +size 2044794055 diff --git a/pytorch_model-00006-of-00013.bin b/pytorch_model-00006-of-00013.bin new file mode 100644 index 0000000..3dbc609 --- /dev/null +++ b/pytorch_model-00006-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c2d5c0a5402b8c5e3525881aca83d6ef337b0c973fdb8ee3e098adeabeee11 +size 2044794055 diff --git a/pytorch_model-00007-of-00013.bin b/pytorch_model-00007-of-00013.bin new file mode 100644 index 0000000..d1a509a --- /dev/null +++ b/pytorch_model-00007-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7860f3089942dd1f0ced967b7cae4026acbe2f04d4597f3b2a32245dddcbfaf +size 2044815147 diff --git a/pytorch_model-00008-of-00013.bin b/pytorch_model-00008-of-00013.bin new file mode 100644 index 0000000..d449830 --- /dev/null +++ b/pytorch_model-00008-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0b56198c5e269de1919506b01c237f277f24af3957090d6ffd055273f1557d3 +size 2060523307 diff --git a/pytorch_model-00009-of-00013.bin b/pytorch_model-00009-of-00013.bin new file mode 100644 index 0000000..a08749b --- /dev/null +++ b/pytorch_model-00009-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b7c7f3149b6de532effb229c606173a24918a255b79da09d44b76d91c434444 +size 1955665095 diff --git a/pytorch_model-00010-of-00013.bin b/pytorch_model-00010-of-00013.bin new file mode 100644 index 0000000..39cc0d2 --- /dev/null +++ b/pytorch_model-00010-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50843a3b307da2a9a98fb43a69346dedf89c8fcbcf031e4eb248adc0c8e3b209 +size 2044794055 diff --git a/pytorch_model-00011-of-00013.bin b/pytorch_model-00011-of-00013.bin new file mode 100644 index 0000000..c83cd6c --- /dev/null +++ b/pytorch_model-00011-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7fb6340194d82f0d8cb6620f4a412352c0d18601e7accb0081bdc6709b492e +size 2044794055 diff --git a/pytorch_model-00012-of-00013.bin b/pytorch_model-00012-of-00013.bin new file mode 100644 index 0000000..09a14cb --- /dev/null +++ b/pytorch_model-00012-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcee89d5395ed64c1c200bc488fda7be94b406c850ea90c6bf07a141030add7b +size 2044815147 diff --git a/pytorch_model-00013-of-00013.bin b/pytorch_model-00013-of-00013.bin new file mode 100644 index 0000000..ce719c4 --- /dev/null +++ b/pytorch_model-00013-of-00013.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e1dac08e595d295a249bdf22f674663ceacc3d20553fa79475ba1d0cfd4ae8 +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 + } +}