commit db5396d3d483ab6887b0c3e6a988a8e2a562dc23 Author: ModelHub XC Date: Sun Oct 18 15:13:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-8b-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1179e06 --- /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 +*.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-3-8b-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5e0ba65 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: AIRETech/llama-3-8b-DPO +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AIRETech/llama-3-8b-DPO + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-DPO-GGUF/resolve/main/llama-3-8b-DPO.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/llama-3-8b-DPO.IQ4_XS.gguf b/llama-3-8b-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..dafb4c8 --- /dev/null +++ b/llama-3-8b-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:073183ab4137974536acfd51db477d93a71c04d22d36c74a75fb2cf5b849ea74 +size 4484363296 diff --git a/llama-3-8b-DPO.Q2_K.gguf b/llama-3-8b-DPO.Q2_K.gguf new file mode 100644 index 0000000..491bbc3 --- /dev/null +++ b/llama-3-8b-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9059fc18394cf2ecc26219daa94745d70c65f2428a4f0d7941770e04ae39dbf7 +size 3179131936 diff --git a/llama-3-8b-DPO.Q3_K_L.gguf b/llama-3-8b-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..63c2dbd --- /dev/null +++ b/llama-3-8b-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:277040033d8caf7cd80c0a79f927afd999f8bda9d6db29f2ac4d5b831366f323 +size 4321956896 diff --git a/llama-3-8b-DPO.Q3_K_M.gguf b/llama-3-8b-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..1c1b68b --- /dev/null +++ b/llama-3-8b-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a08820b1d7edb97cd699dd177fc90266ea533dff7d6dccdafb819754767552 +size 4018918432 diff --git a/llama-3-8b-DPO.Q3_K_S.gguf b/llama-3-8b-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..b33431f --- /dev/null +++ b/llama-3-8b-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a96d43fa2d41d27266d782b87fd312b98fc2682e61ab5265a9e55a9d951357 +size 3664499744 diff --git a/llama-3-8b-DPO.Q4_K_M.gguf b/llama-3-8b-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..057daba --- /dev/null +++ b/llama-3-8b-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fca3ad463f86da183fde2ea04b226190ff6439aa622569033c9ddc070a6b8d1b +size 4920734752 diff --git a/llama-3-8b-DPO.Q4_K_S.gguf b/llama-3-8b-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..211427b --- /dev/null +++ b/llama-3-8b-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2541b4269fc5b7d39178fc27a4f55b4855db218fe23aa2213742c23b5007f6f4 +size 4692669472 diff --git a/llama-3-8b-DPO.Q5_K_M.gguf b/llama-3-8b-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..3e44a4f --- /dev/null +++ b/llama-3-8b-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5196acad7bf95d05cab8018286e44cfe9ef5ba0373618f3ad38124f32e55fde1 +size 5732987936 diff --git a/llama-3-8b-DPO.Q5_K_S.gguf b/llama-3-8b-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..4772fd9 --- /dev/null +++ b/llama-3-8b-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168b38ddd45d090b6bc9d7efbb82fd1c392c518258aea4c8fd6c81375b8c8953 +size 5599294496 diff --git a/llama-3-8b-DPO.Q6_K.gguf b/llama-3-8b-DPO.Q6_K.gguf new file mode 100644 index 0000000..905ceb5 --- /dev/null +++ b/llama-3-8b-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f085f7913342d30acc5bb1d3816edb4f6ca6b9d8c8232cfb607692e384c188 +size 6596006944 diff --git a/llama-3-8b-DPO.Q8_0.gguf b/llama-3-8b-DPO.Q8_0.gguf new file mode 100644 index 0000000..e4744e9 --- /dev/null +++ b/llama-3-8b-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a087c424046b47b178a9d52c29c831c363aed82eb796a54746e6f1e1778df5 +size 8540771360 diff --git a/llama-3-8b-DPO.f16.gguf b/llama-3-8b-DPO.f16.gguf new file mode 100644 index 0000000..935c599 --- /dev/null +++ b/llama-3-8b-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0871b91199bf05b8555aa4604fd24e9b59f74c6c1f1ec42c649deee287895da9 +size 16068891680