commit 190851ea7abeb46559792c86397d105e2d62b749 Author: ModelHub XC Date: Mon Apr 27 04:59:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1d8219 --- /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-iter3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-v2-iterative-DPO-iter3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-v2-iterative-DPO-iter3.IQ4_XS.gguf b/Llama3-v2-iterative-DPO-iter3.IQ4_XS.gguf new file mode 100644 index 0000000..889e5f4 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45debbd4d3bbba364a14b4c35e2d57b361b37f4e84f73c7739ab7b676a9b23e9 +size 4484363456 diff --git a/Llama3-v2-iterative-DPO-iter3.Q2_K.gguf b/Llama3-v2-iterative-DPO-iter3.Q2_K.gguf new file mode 100644 index 0000000..c74c7d7 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e360e8c14826b75de5713cccb600aa56e270ff083b56ccdb0fd7d73a336a77 +size 3179132096 diff --git a/Llama3-v2-iterative-DPO-iter3.Q3_K_L.gguf b/Llama3-v2-iterative-DPO-iter3.Q3_K_L.gguf new file mode 100644 index 0000000..9f0ae85 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1188ef605a2bd7e5cd838a499624956ec04a4d848a71358fe148f8787252ed9 +size 4321957056 diff --git a/Llama3-v2-iterative-DPO-iter3.Q3_K_M.gguf b/Llama3-v2-iterative-DPO-iter3.Q3_K_M.gguf new file mode 100644 index 0000000..6d81343 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682114d9cecf4b7fe58064891c71fac02ec6150ab18e04d1d70d59deebad679d +size 4018918592 diff --git a/Llama3-v2-iterative-DPO-iter3.Q3_K_S.gguf b/Llama3-v2-iterative-DPO-iter3.Q3_K_S.gguf new file mode 100644 index 0000000..a150866 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a30c5b4c79b991a4bd46b18b5b3602fcd9ff3f07c151ba58563e4e2b0ded35 +size 3664499904 diff --git a/Llama3-v2-iterative-DPO-iter3.Q4_0_4_4.gguf b/Llama3-v2-iterative-DPO-iter3.Q4_0_4_4.gguf new file mode 100644 index 0000000..6efdb83 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64e11c36ea2c544dd32a1cc4d8450cfcd06b44ec6e74bec846fa7aac0a4c090 +size 4661212352 diff --git a/Llama3-v2-iterative-DPO-iter3.Q4_K_M.gguf b/Llama3-v2-iterative-DPO-iter3.Q4_K_M.gguf new file mode 100644 index 0000000..82f8ab0 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10e177c5067fbecc92cf7205ae098978c28691b9fdc9f5daf5bbc6ea2aebe52a +size 4920734912 diff --git a/Llama3-v2-iterative-DPO-iter3.Q4_K_S.gguf b/Llama3-v2-iterative-DPO-iter3.Q4_K_S.gguf new file mode 100644 index 0000000..a4d0b7b --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9da11bc7038a0b20cb5f21956404527a8bce33e24ee5b0666248f008717c102f +size 4692669632 diff --git a/Llama3-v2-iterative-DPO-iter3.Q5_K_M.gguf b/Llama3-v2-iterative-DPO-iter3.Q5_K_M.gguf new file mode 100644 index 0000000..7220216 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1e24aa1ae3df8c85513316437e0920ec799cde18e00412f4d1cb376dfd16ba +size 5732988096 diff --git a/Llama3-v2-iterative-DPO-iter3.Q5_K_S.gguf b/Llama3-v2-iterative-DPO-iter3.Q5_K_S.gguf new file mode 100644 index 0000000..c64f5ce --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4289f866da73b6c42294b9e3649c24088c10d2bc306ea1797ba9a59b6320c5e7 +size 5599294656 diff --git a/Llama3-v2-iterative-DPO-iter3.Q6_K.gguf b/Llama3-v2-iterative-DPO-iter3.Q6_K.gguf new file mode 100644 index 0000000..20ebbea --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e87cecee4adf79a825f2aec6a92765cedd7ea9d1c55ef36816f3b3209f1c8a +size 6596007104 diff --git a/Llama3-v2-iterative-DPO-iter3.Q8_0.gguf b/Llama3-v2-iterative-DPO-iter3.Q8_0.gguf new file mode 100644 index 0000000..4aac603 --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2890c7b8213a98022874d8ea7689be16bf296ccf5f8a3e152ffc367c18a98668 +size 8540771520 diff --git a/Llama3-v2-iterative-DPO-iter3.f16.gguf b/Llama3-v2-iterative-DPO-iter3.f16.gguf new file mode 100644 index 0000000..736fbce --- /dev/null +++ b/Llama3-v2-iterative-DPO-iter3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41d0b4ec744a10b8c93f1b3cae3ba31b83fb1dc9cd7f999f9addac5f16c83d1a +size 16068891840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9daf45b --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: RLHFlow/Llama3-v2-iterative-DPO-iter3 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/RLHFlow/Llama3-v2-iterative-DPO-iter3 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-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-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.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-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-v2-iterative-DPO-iter3-GGUF/resolve/main/Llama3-v2-iterative-DPO-iter3.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. + +