commit 465f63a0f376c7d8f634ce1dab40f2149131100a Author: ModelHub XC Date: Mon Oct 12 16:45:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/Llama-3-Instruct-8B-SimPO-ExPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a3191d8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +*.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 +Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf new file mode 100644 index 0000000..013d0b1 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a704a2c9f9ec1325fcd0ba5c5697d905e463ba8ca18510f55f9b6d0c1cbc77e6 +size 3179131136 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf new file mode 100644 index 0000000..84afc9b --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb749486385a8c894e563f05ba9965dfd8fd374e0e43c342400c0898e8666f6c +size 4321956096 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf new file mode 100644 index 0000000..e87129f --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a7f4094830b74ff903c3a936fc4640c3073b104a7345b2d9c569cff490e8c3 +size 4018917632 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf new file mode 100644 index 0000000..08d1f60 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c9e9336fe759dc9c940d88486586a795e017acb30de5a08d41e03dcd0da37d7 +size 3664498944 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q4_0.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_0.gguf new file mode 100644 index 0000000..f0c3093 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07216d406e3a213ca463f0c7a3f04aaf56a0c1691608dadd83cdae2f6901105 +size 4661211392 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q4_1.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_1.gguf new file mode 100644 index 0000000..c2dfac1 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325e45cd55308ded23f648fa7ac64dc754b60fb0656c356ef6c2befd6282761c +size 5130252544 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf new file mode 100644 index 0000000..a8d46b4 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b897bee30f5b44661e18620ea8c27d8a00d3da73c846aa90f751da40ab6e7d1 +size 4920733952 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf new file mode 100644 index 0000000..e04d7a2 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5acc6c3b484e0621a5da04d7bbd70b56395e7c2c8547deda3cd6b4a0eccd30d +size 4692668672 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q5_0.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_0.gguf new file mode 100644 index 0000000..ac23efe --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b00830403ba241ed76741cb043c0c39147b0bb3db41c508df63c46166eb25d +size 5599293696 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q5_1.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_1.gguf new file mode 100644 index 0000000..9e88476 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac2fefb90a0fb7f4abb4aaebd163ad7bd720221cd29c6bcc99ab9969f0316f1 +size 6068334848 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf new file mode 100644 index 0000000..790647c --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93250a08f46e9adb10423a307e23bc718a4f1f19037b460b64180c508c575310 +size 5732987136 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf new file mode 100644 index 0000000..3e8e3e1 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83581b3a9c379c956f34d12b07481edd0b206e34ab8bd20aaba45edf8c77fbf +size 5599293696 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf new file mode 100644 index 0000000..908ea4c --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a48c7b1e4fc537bb2a36e1d0f359f9eaaa6a85dd347fb8f2df095c0929bd84c +size 6596006144 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf new file mode 100644 index 0000000..767812b --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:156a694ad53b1b93c3bd123e9f017e1b39f241b195fc4a189fc26435ee0408f1 +size 8540770560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c1d54c --- /dev/null +++ b/README.md @@ -0,0 +1,53 @@ +--- +language: +- en +license: llama3 +pipeline_tag: text-generation +base_model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO +--- + +# Llama-3-Instruct-8B-SimPO-ExPO-GGUF +This is quantized version of [chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO](https://huggingface.co/chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO) created using llama.cpp +## Model Description + +The extrapolated (ExPO) model based on [`princeton-nlp/Llama-3-Instruct-8B-SimPO`](https://huggingface.co/princeton-nlp/Llama-3-Instruct-8B-SimPO) and [`meta-llama/Meta-Llama-3-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper. + +Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. + +This extrapolated model achieves the **40.6%** win rate and **45.8%** LC win rate on **AlpacaEval 2.0**, outperforming the original `Llama-3-Instruct-8B-SimPO`'s 40.5% and 44.7%, respectively. + +## Evaluation Results + +Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_alpaca)): + +| | Win Rate (Ori) | LC Win Rate (Ori) | Win Rate (+ ExPO) | LC Win Rate (+ ExPO) | +| ------------------------------------ | -------------- | ----------------- | ----------------- | -------------------- | +| `HuggingFaceH4/zephyr-7b-alpha` | 6.7% | 10.0% | **10.6%** | **13.6%** | +| `HuggingFaceH4/zephyr-7b-beta` | 10.2% | 13.2% | **11.1%** | **14.0%** | +| `berkeley-nest/Starling-LM-7B-alpha` | 15.0% | 18.3% | **18.2%** | **19.5%** | +| `Nexusflow/Starling-LM-7B-beta` | 26.6% | 25.8% | **29.6%** | **26.4%** | +| `snorkelai/Snorkel-Mistral-PairRM` | 24.7% | 24.0% | **28.8%** | **26.4%** | +| `RLHFlow/LLaMA3-iterative-DPO-final` | 29.2% | 36.0% | **32.7%** | **37.8%** | +| `internlm/internlm2-chat-1.8b` | 3.8% | 4.0% | **5.2%** | **4.3%** | +| `internlm/internlm2-chat-7b` | 20.5% | 18.3% | **28.1%** | **22.7%** | +| `internlm/internlm2-chat-20b` | 36.1% | 24.9% | **46.2%** | **27.2%** | +| `allenai/tulu-2-dpo-7b` | 8.5% | 10.2% | **11.5%** | **11.7%** | +| `allenai/tulu-2-dpo-13b` | 11.2% | 15.5% | **15.6%** | **17.6%** | +| `allenai/tulu-2-dpo-70b` | 15.4% | 21.2% | **23.0%** | **25.7%** | + +Evaluation results on the **MT-Bench** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_mtbench)): + +| | Original | + ExPO | +| ------------------------------------ | -------- | -------- | +| `HuggingFaceH4/zephyr-7b-alpha` | 6.85 | **6.87** | +| `HuggingFaceH4/zephyr-7b-beta` | 7.02 | **7.06** | +| `berkeley-nest/Starling-LM-7B-alpha` | 7.82 | **7.91** | +| `Nexusflow/Starling-LM-7B-beta` | 8.10 | **8.18** | +| `snorkelai/Snorkel-Mistral-PairRM` | 7.63 | **7.69** | +| `RLHFlow/LLaMA3-iterative-DPO-final` | 8.08 | **8.45** | +| `internlm/internlm2-chat-1.8b` | 5.17 | **5.26** | +| `internlm/internlm2-chat-7b` | 7.72 | **7.80** | +| `internlm/internlm2-chat-20b` | 8.13 | **8.26** | +| `allenai/tulu-2-dpo-7b` | 6.35 | **6.38** | +| `allenai/tulu-2-dpo-13b` | 7.00 | **7.26** | +| `allenai/tulu-2-dpo-70b` | 7.79 | **8.03** | \ 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