commit ff16471626efd0d3da229cf0a0461efe163cece6 Author: ModelHub XC Date: Sat Aug 8 08:35:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-8b-dpo-full-1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..198229f --- /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-8b-dpo-full-1.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-8b-dpo-full-1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6b97cda --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: jkazdan/llama-8b-dpo-full-1 +language: +- en +library_name: transformers +model_name: llama-8b-dpo-full-1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/jkazdan/llama-8b-dpo-full-1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-8b-dpo-full-1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-8b-dpo-full-1-i1-GGUF +## 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-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-8b-dpo-full-1-GGUF/resolve/main/llama-8b-dpo-full-1.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-8b-dpo-full-1.IQ4_XS.gguf b/llama-8b-dpo-full-1.IQ4_XS.gguf new file mode 100644 index 0000000..23dfc52 --- /dev/null +++ b/llama-8b-dpo-full-1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd287689e778bbce45e8f571908fa5391c5c12d85f1ff0e2260f472c88fda2f +size 4484363744 diff --git a/llama-8b-dpo-full-1.Q2_K.gguf b/llama-8b-dpo-full-1.Q2_K.gguf new file mode 100644 index 0000000..5276f30 --- /dev/null +++ b/llama-8b-dpo-full-1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7666db8216996464268f61d515c044b0b9bdfdfff71f1e790fae0b6d7f41cc2a +size 3179132384 diff --git a/llama-8b-dpo-full-1.Q3_K_L.gguf b/llama-8b-dpo-full-1.Q3_K_L.gguf new file mode 100644 index 0000000..e2a5bc0 --- /dev/null +++ b/llama-8b-dpo-full-1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0ebb22f7363e4f691442f64df3b0b4e9f9b684e2e6959aef391d9fa3ce0959 +size 4321957344 diff --git a/llama-8b-dpo-full-1.Q3_K_M.gguf b/llama-8b-dpo-full-1.Q3_K_M.gguf new file mode 100644 index 0000000..65992ab --- /dev/null +++ b/llama-8b-dpo-full-1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e48ffe1cc74eac8b9a0bddce8079f0ca84dffda74a93ddfd8dea7b6f9833c1 +size 4018918880 diff --git a/llama-8b-dpo-full-1.Q3_K_S.gguf b/llama-8b-dpo-full-1.Q3_K_S.gguf new file mode 100644 index 0000000..3184a95 --- /dev/null +++ b/llama-8b-dpo-full-1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea315f1422a3740754c38d487a7d82c07368699204609affdeb199896ef2dcc9 +size 3664500192 diff --git a/llama-8b-dpo-full-1.Q4_K_M.gguf b/llama-8b-dpo-full-1.Q4_K_M.gguf new file mode 100644 index 0000000..beb564d --- /dev/null +++ b/llama-8b-dpo-full-1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c3b55adb831bd0c65de92bdcdfdc693d113fb105cfb71fda2af66aca9b2eead +size 4920735200 diff --git a/llama-8b-dpo-full-1.Q4_K_S.gguf b/llama-8b-dpo-full-1.Q4_K_S.gguf new file mode 100644 index 0000000..40517fb --- /dev/null +++ b/llama-8b-dpo-full-1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf53931616e3efcd909df49fb176ea51e70b9b1383daaa6e074c238aa48d702a +size 4692669920 diff --git a/llama-8b-dpo-full-1.Q5_K_M.gguf b/llama-8b-dpo-full-1.Q5_K_M.gguf new file mode 100644 index 0000000..fc8e739 --- /dev/null +++ b/llama-8b-dpo-full-1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c218c4d427c46020b5e7167ac695c6ba6fe330d1fa72506e09226d1d9f6156e6 +size 5732988384 diff --git a/llama-8b-dpo-full-1.Q5_K_S.gguf b/llama-8b-dpo-full-1.Q5_K_S.gguf new file mode 100644 index 0000000..04f6799 --- /dev/null +++ b/llama-8b-dpo-full-1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549d9862621992b565e8bb6a5b5cf540750dc17e413264582bb341995eaff43f +size 5599294944 diff --git a/llama-8b-dpo-full-1.Q6_K.gguf b/llama-8b-dpo-full-1.Q6_K.gguf new file mode 100644 index 0000000..231948d --- /dev/null +++ b/llama-8b-dpo-full-1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc44de3f609f738828f97df8a814354e1bdb6a66daa351d77a4089059211eae4 +size 6596007392 diff --git a/llama-8b-dpo-full-1.Q8_0.gguf b/llama-8b-dpo-full-1.Q8_0.gguf new file mode 100644 index 0000000..bb5bb8f --- /dev/null +++ b/llama-8b-dpo-full-1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0161a0ee4626ae2fb5737a074482cb9a1f04d158aa8f382c2fa27fb73c1d34a1 +size 8540771808 diff --git a/llama-8b-dpo-full-1.f16.gguf b/llama-8b-dpo-full-1.f16.gguf new file mode 100644 index 0000000..3c39e41 --- /dev/null +++ b/llama-8b-dpo-full-1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b37244f09e42dd586fa7b6e9074843a04b72b01c92712a856ec4c322af9f3cff +size 16068892128