commit 30be28672c5dce43f9420d788a1672d641ea3714 Author: ModelHub XC Date: Sat Oct 3 06:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-ragia-8b-dpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2155626 --- /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-ragia-8b-dpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-8b-dpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-ragia-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..d938cad --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: regia-ai/llama-ragia-8b-dpo +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/regia-ai/llama-ragia-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-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-8b-dpo.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-ragia-8b-dpo-GGUF/resolve/main/llama-ragia-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-ragia-8b-dpo.IQ4_XS.gguf b/llama-ragia-8b-dpo.IQ4_XS.gguf new file mode 100644 index 0000000..8f52521 --- /dev/null +++ b/llama-ragia-8b-dpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16492b57214468144911a3bc687cb62a6e92d6fb119bcbfe901a56882afd0a70 +size 4484367808 diff --git a/llama-ragia-8b-dpo.Q2_K.gguf b/llama-ragia-8b-dpo.Q2_K.gguf new file mode 100644 index 0000000..ac21bdf --- /dev/null +++ b/llama-ragia-8b-dpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d8254d9468993af7f6327179ffa3a93ad973b0d23b7e49b4f14f03a09087cd +size 3179136448 diff --git a/llama-ragia-8b-dpo.Q3_K_L.gguf b/llama-ragia-8b-dpo.Q3_K_L.gguf new file mode 100644 index 0000000..291e299 --- /dev/null +++ b/llama-ragia-8b-dpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9055488764f539f5194ae788ec291f11aa0ce879be668337d47db8727bdcc5d4 +size 4321961408 diff --git a/llama-ragia-8b-dpo.Q3_K_M.gguf b/llama-ragia-8b-dpo.Q3_K_M.gguf new file mode 100644 index 0000000..d147196 --- /dev/null +++ b/llama-ragia-8b-dpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f767fe0dac59b6792777a062bb17ce3a6bd0d468f41de282b5d1c743dff673a +size 4018922944 diff --git a/llama-ragia-8b-dpo.Q3_K_S.gguf b/llama-ragia-8b-dpo.Q3_K_S.gguf new file mode 100644 index 0000000..7c74fcb --- /dev/null +++ b/llama-ragia-8b-dpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5efca4079e8f6d6e82d8c375a21196bd40a77d0f6997a6d8e98d40e8f7f51836 +size 3664504256 diff --git a/llama-ragia-8b-dpo.Q4_K_M.gguf b/llama-ragia-8b-dpo.Q4_K_M.gguf new file mode 100644 index 0000000..0b8958d --- /dev/null +++ b/llama-ragia-8b-dpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dd287ea90ab8893302a95ea1e251470d1d2cb59263ea94cb83c9d288a411da3 +size 4920739264 diff --git a/llama-ragia-8b-dpo.Q4_K_S.gguf b/llama-ragia-8b-dpo.Q4_K_S.gguf new file mode 100644 index 0000000..922a783 --- /dev/null +++ b/llama-ragia-8b-dpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2747fa16ca2f95772285cc9d56d681348265675d87019baa9dadea262399a9a5 +size 4692673984 diff --git a/llama-ragia-8b-dpo.Q5_K_M.gguf b/llama-ragia-8b-dpo.Q5_K_M.gguf new file mode 100644 index 0000000..8e55b55 --- /dev/null +++ b/llama-ragia-8b-dpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de75e00a4f588bd25200f7b46a5bfe79c6115c75f2117091f0eead0ae0919daf +size 5732992448 diff --git a/llama-ragia-8b-dpo.Q5_K_S.gguf b/llama-ragia-8b-dpo.Q5_K_S.gguf new file mode 100644 index 0000000..d39838a --- /dev/null +++ b/llama-ragia-8b-dpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7df32b5b9a8caae34d3be0df6fcd850d4c52a53182ebe404cd42fe33d6a90945 +size 5599299008 diff --git a/llama-ragia-8b-dpo.Q6_K.gguf b/llama-ragia-8b-dpo.Q6_K.gguf new file mode 100644 index 0000000..3ba6817 --- /dev/null +++ b/llama-ragia-8b-dpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610d6c4d05b9e4ee56b82595f2f56c9e93e93fba9c017cc484a5df179a4f5a14 +size 6596011456 diff --git a/llama-ragia-8b-dpo.Q8_0.gguf b/llama-ragia-8b-dpo.Q8_0.gguf new file mode 100644 index 0000000..cde5897 --- /dev/null +++ b/llama-ragia-8b-dpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856dacaf0bce5fbca9cd2ef62a22501a0ef7673ae5b27c67f9e4ace21f7ed04a +size 8540775872 diff --git a/llama-ragia-8b-dpo.f16.gguf b/llama-ragia-8b-dpo.f16.gguf new file mode 100644 index 0000000..1619ee8 --- /dev/null +++ b/llama-ragia-8b-dpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38831972b5246841711b2c8774a9f02448c62b3cdfcaa1b412057d5383b6941c +size 16068896192