commit 643396b6ed91b9666f0a353724b50d0e7b869caa Author: ModelHub XC Date: Wed Sep 23 08:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2052ab9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Llama3-v2-iterative-DPO-iter2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-v2-iterative-DPO-iter2.IQ4_XS.gguf b/Llama3-v2-iterative-DPO-iter2.IQ4_XS.gguf new file mode 100644 index 0000000..ab62d98 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ab12691148eac6655e0be5b71cd9e4081b8f8b1dc7a07d5b1958c5f08578d5c +size 4484363456 diff --git a/Llama3-v2-iterative-DPO-iter2.Q2_K.gguf b/Llama3-v2-iterative-DPO-iter2.Q2_K.gguf new file mode 100644 index 0000000..c023fbf --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f226f7660f807359b2b096f13d1365a1e9d2f859476150339bd41bb5555bca2 +size 3179132096 diff --git a/Llama3-v2-iterative-DPO-iter2.Q3_K_L.gguf b/Llama3-v2-iterative-DPO-iter2.Q3_K_L.gguf new file mode 100644 index 0000000..520bd1c --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16683590305545c11cd97e2e82009833d5548fa07d11fd5be61a6fa17f62d3fe +size 4321957056 diff --git a/Llama3-v2-iterative-DPO-iter2.Q3_K_M.gguf b/Llama3-v2-iterative-DPO-iter2.Q3_K_M.gguf new file mode 100644 index 0000000..9ae585f --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4879e746953a2131f4e4e9e0254f86f46218430af114b098eb6ce5a19838d1ce +size 4018918592 diff --git a/Llama3-v2-iterative-DPO-iter2.Q3_K_S.gguf b/Llama3-v2-iterative-DPO-iter2.Q3_K_S.gguf new file mode 100644 index 0000000..d7439b9 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ed9255537ac648cf416ae70e5a61ffe451b8e27a266c7915bcc16e8d4900c1 +size 3664499904 diff --git a/Llama3-v2-iterative-DPO-iter2.Q4_0_4_4.gguf b/Llama3-v2-iterative-DPO-iter2.Q4_0_4_4.gguf new file mode 100644 index 0000000..bda5e2e --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9592e3d30c8b15fad16a50bdaaff4b14b7266c992684914c5f27af40aac6fa7a +size 4661212352 diff --git a/Llama3-v2-iterative-DPO-iter2.Q4_K_M.gguf b/Llama3-v2-iterative-DPO-iter2.Q4_K_M.gguf new file mode 100644 index 0000000..4d5324c --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96753e4c0cf02759537ffea6d014a5f3a04c638e08de5fd00103ed5faef8a34 +size 4920734912 diff --git a/Llama3-v2-iterative-DPO-iter2.Q4_K_S.gguf b/Llama3-v2-iterative-DPO-iter2.Q4_K_S.gguf new file mode 100644 index 0000000..024f500 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c47c59c58f07180ec7c5b68035a1be6d7334de21ba1d4372ea2b813b3ffeaf9 +size 4692669632 diff --git a/Llama3-v2-iterative-DPO-iter2.Q5_K_M.gguf b/Llama3-v2-iterative-DPO-iter2.Q5_K_M.gguf new file mode 100644 index 0000000..a28e9db --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e8aae21fc1a9317a35c2afa6219f82bc299a17506cee1f9d9e1c90d7c0658e +size 5732988096 diff --git a/Llama3-v2-iterative-DPO-iter2.Q5_K_S.gguf b/Llama3-v2-iterative-DPO-iter2.Q5_K_S.gguf new file mode 100644 index 0000000..b24b87d --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8247ff399a2050fecfff2bd46cde56f4cb96e4d960648502b537742395f3b1af +size 5599294656 diff --git a/Llama3-v2-iterative-DPO-iter2.Q6_K.gguf b/Llama3-v2-iterative-DPO-iter2.Q6_K.gguf new file mode 100644 index 0000000..9b2a87d --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a859e56363674707dd4a6c4a1353476cb2c75e9049051580b18bbae6c928dd5 +size 6596007104 diff --git a/Llama3-v2-iterative-DPO-iter2.Q8_0.gguf b/Llama3-v2-iterative-DPO-iter2.Q8_0.gguf new file mode 100644 index 0000000..7e003df --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477cff7f55592f515cbb3951a26205913fe1f0307e08f67b4952440cf914f0b1 +size 8540771520 diff --git a/Llama3-v2-iterative-DPO-iter2.f16.gguf b/Llama3-v2-iterative-DPO-iter2.f16.gguf new file mode 100644 index 0000000..5fcfb46 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c156508ff900a6cb63abb781d55b291849a5508ea70b7e24251969bf308da07e +size 16068891840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b7386a --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: RLHFlow/Llama3-v2-iterative-DPO-iter2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/RLHFlow/Llama3-v2-iterative-DPO-iter2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-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/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter2-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter2.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. + +