commit c112f41940e947f27adec3014c55e7139694dc96 Author: ModelHub XC Date: Mon Oct 5 01:05:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47796b6 --- /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-Instruct-Iterative-SamPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Iterative-SamPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.IQ4_XS.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.IQ4_XS.gguf new file mode 100644 index 0000000..c3f43b5 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d55aa0e2862aeae2ef0f5426ccf7949da91da2780409c9e33040c2b6944d8f +size 4484363840 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q2_K.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q2_K.gguf new file mode 100644 index 0000000..7875bed --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db3badf7f010bbde3939e2a8c9498a58e5b0dfc612948f9c6bfd9e8dd77e3d87 +size 3179132480 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_L.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_L.gguf new file mode 100644 index 0000000..780cde2 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcdd83ab9247144234c0e5ddcd378839fec2757e368718991e504d1f3ae01f33 +size 4321957440 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_M.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_M.gguf new file mode 100644 index 0000000..97ce4b6 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df22e74a2cfcfcb46acff856445cb766b91e0a7503235f283f4ec6e0e5f7d94e +size 4018918976 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_S.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_S.gguf new file mode 100644 index 0000000..ac12b06 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36581988111770501f1ea04a8a8ab4ee2ddfa6993e575ac306adc8afe3c58303 +size 3664500288 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_M.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_M.gguf new file mode 100644 index 0000000..e794116 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7adc8c98fc5e8a480524c51d12d439821e53fcbd5e7ddf4d8256c002bc03127d +size 4920735296 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_S.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_S.gguf new file mode 100644 index 0000000..ba52a8e --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26dff846676cff465d02965ecb537ce4ca2b1dcd98e940d19984be0613b1c98 +size 4692670016 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_M.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_M.gguf new file mode 100644 index 0000000..dff64b4 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bddbec27714402e612a4509efeb98d8a7c643a3a5da09673c7238b7a5abef3c3 +size 5732988480 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_S.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_S.gguf new file mode 100644 index 0000000..8e90d45 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:423611e953a2cd035ce9bf606d292e794938917b1fded910dd87f2051cd65307 +size 5599295040 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q6_K.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q6_K.gguf new file mode 100644 index 0000000..77644f1 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1172e28e72a00617d4b1551f3be1d8457d23c3c11328ccabc54b0997d778a2 +size 6596007488 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.Q8_0.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.Q8_0.gguf new file mode 100644 index 0000000..bf7a266 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a1fd4c0d475d7fa9b51277d618818757309487b5d2ae12ea407861b0f89c5c +size 8540771904 diff --git a/Llama-3-8B-Instruct-Iterative-SamPO.f16.gguf b/Llama-3-8B-Instruct-Iterative-SamPO.f16.gguf new file mode 100644 index 0000000..b221487 --- /dev/null +++ b/Llama-3-8B-Instruct-Iterative-SamPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e1df4e3352dc0657e068f6ada7164e42396461483f31e615841fb4414ee6c3 +size 16068892224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..266ace2 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Junrulu/Llama-3-8B-Instruct-Iterative-SamPO +datasets: +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Junrulu/Llama-3-8B-Instruct-Iterative-SamPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B-Instruct-Iterative-SamPO-GGUF).*** + +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-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Iterative-SamPO-GGUF/resolve/main/Llama-3-8B-Instruct-Iterative-SamPO.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. + +