commit 13c4dd4c5bfc1e0fc21812e3614924ed7990adc3 Author: ModelHub XC Date: Sun Jul 5 22:32:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Undi95/ReMM-SLERP-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/README.md b/README.md new file mode 100644 index 0000000..95e7799 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +license: cc-by-nc-4.0 +base_model: +- TheBloke/Llama-2-13B-fp16 +- jondurbin/airoboros-l2-13b-2.1 +- NousResearch/Nous-Hermes-Llama2-13b +- Undi95/ReML-L2-13B +--- +Re:MythoMax (ReMM) is a recreation trial of the original [MythoMax-L2-B13](https://huggingface.co/Gryphe/MythoMax-L2-13b) with updated models. + +This merge use SLERP [TESTING] to merge ReML and Huginn v1.2. + +Command useds and explaination : +```shell +Due to hardware limitation, some merge was done in 2 part. + +- Recreate ReML : Mythologic (v2) (Chronos/Hermes/Airboros) +=> Replacing Chronos by The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 (0.30) +=> Replacing Airoboros by jondurbin/airoboros-l2-13b-2.1 (last version) (0.40) +=> Keeping NousResearch/Nous-Hermes-Llama2-13b (0.30) + +Part 1: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReML-L2-13B-part1 --merge The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 --density 0.42 --merge jondurbin/airoboros-l2-13b-2.1 --density 0.56 --cuda + +Part 2: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReML-L2-13B --merge NousResearch/Nous-Hermes-Llama2-13b --density 0.30 --merge Undi95/ReML-L2-13B-part1 --density 0.70 --cuda + +With that : +- Recreate ReMM : MythoMax (v2) (Mythologic/Huginn v1) +=> Replacing Mythologic by the one above (0.5) +=> Replacing Huginn by The-Face-Of-Goonery/Huginn-13b-v1.2 (hottest) (0.5) + +Part 3: python slerpmergelm.py "The-Face-Of-Goonery_Huginn-13b-v1.2" "Undi95_ReML-L2-13B" "result" +``` + +Version of SLERP used is different to accept usage on notebook : https://github.com/Undi95/LLM-SLERP-MergeTest/tree/main (Thanks @Vali) + + +## Description + +This repo contains fp16 files of ReMM-SLERP, a recreation of the original MythoMax, but updated and merged with SLERP. + + +## Models used + + +- TheBloke/Llama-2-13B-fp16 (base) +- The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 +- jondurbin/airoboros-l2-13b-2.1 +- NousResearch/Nous-Hermes-Llama2-13b +- The-Face-Of-Goonery/Huginn-13b-v1.2 +- ReML-L2-13B (Private recreation trial of an updated Mythologic-L2-13B) + + +## Prompt template: Alpaca + +``` +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +{prompt} + +### Response: + +``` + +Special thanks to Sushi kek +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__ReMM-SLERP-L2-13B) + +| Metric | Value | +|-----------------------|---------------------------| +| Avg. | 50.99 | +| ARC (25-shot) | 60.92 | +| HellaSwag (10-shot) | 83.56 | +| MMLU (5-shot) | 55.33 | +| TruthfulQA (0-shot) | 51.97 | +| Winogrande (5-shot) | 75.22 | +| GSM8K (5-shot) | 9.17 | +| DROP (3-shot) | 20.76 | \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..d9699c6 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "The-Face-Of-Goonery_Huginn-13b-v1.2", + "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": "float32", + "transformers_version": "4.32.1", + "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..a4daf79 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.32.1", + "use_cache": false +} diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin new file mode 100644 index 0000000..72e3ff4 --- /dev/null +++ b/pytorch_model-00001-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfde1ced841d4e22fb2874f427493ffb3959d835cff2944ba109169213de0576 +size 20956496958 diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin new file mode 100644 index 0000000..c1d87b3 --- /dev/null +++ b/pytorch_model-00002-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7763499d3a8473302bc63c061338f35ebb0510178b339d9cf1dd641ba444d62 +size 20720568491 diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin new file mode 100644 index 0000000..5f53208 --- /dev/null +++ b/pytorch_model-00003-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c218def97b9987c0881aad7b0c6e3d200c2060cc795d9a23977222fff7ba2ae1 +size 10386517359 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..5d063ec --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b968f5b39e9f916313499312b0d1625c9ad02dcef1c4e6b6af5e038f5f8cd2b +size 29894 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "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..b090c75 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,32 @@ +{ + "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 + }, + "use_default_system_prompt": true +}