commit d8cb733cda137baf314e12163b12bf450fba603e Author: ModelHub XC Date: Sat Oct 24 21:12:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d205a54 --- /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 +Pythia-2.8B-HH-RLHF-Iterative-SamPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Pythia-2.8B-HH-RLHF-Iterative-SamPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.IQ4_XS.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.IQ4_XS.gguf new file mode 100644 index 0000000..ad8349e --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a95ab7fa4f6c139488318b1f4c54ee293bb288264b7ea0f5c19c13cf6c0b0d7f +size 1533348192 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q2_K.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q2_K.gguf new file mode 100644 index 0000000..fb8e528 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf1a2a2965a5eae51a39af22afdfbff9a19cafe33364ce63cfa9ca25f6e4a71 +size 1086135360 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_L.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_L.gguf new file mode 100644 index 0000000..34b7e8a --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:311f89391e9a50048822383a9ae2aec0c03c8f817a9c2914e4ff53a2f72009c9 +size 1602196160 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_M.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_M.gguf new file mode 100644 index 0000000..a5d66e5 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a22baf5757b777ea0c3c34bb66d78e240635e571c55341c933fcdef51dccc520 +size 1477677760 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_S.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_S.gguf new file mode 100644 index 0000000..6bc4811 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a431fe83bb0df498dd2275b0119a09affce35f4c92074a10c9a53de94d2609 +size 1248301760 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_M.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_M.gguf new file mode 100644 index 0000000..f7b97f5 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f473ace76ee836e7e4b0cb4e1a671a28567e22e6d0d8caebcd59c7448777bddf +size 1786407136 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_S.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_S.gguf new file mode 100644 index 0000000..0b171e1 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788def86c64ec890ba77377421e230658d2ac5110abe8f1efb48609167e0cbb9 +size 1612736736 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_M.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_M.gguf new file mode 100644 index 0000000..9a3b263 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:678b73922ce3c474d11337b7afa4cf42e1592d18d0170570febbea7b2e322943 +size 2069554976 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_S.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_S.gguf new file mode 100644 index 0000000..c8607f8 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ca0371101697e16c5f2b1eff09d6edfae99d39c3af1479ac55c2a9894a83e2 +size 1930290976 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q6_K.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q6_K.gguf new file mode 100644 index 0000000..e660179 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a2d935880fe29465da92db75b0cac1837dc1f073046027511caaf9106d118dc +size 2281618784 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q8_0.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q8_0.gguf new file mode 100644 index 0000000..51a7f6b --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dd2503c066286769d65a94b8cee54396177d7453ca7836d498f95dccf245de3 +size 2953447008 diff --git a/Pythia-2.8B-HH-RLHF-Iterative-SamPO.f16.gguf b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.f16.gguf new file mode 100644 index 0000000..b7ab1b9 --- /dev/null +++ b/Pythia-2.8B-HH-RLHF-Iterative-SamPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade3ec32211f6f4c1e9f487ee8407cec82ec3bab14007ebc68c0d3861a17edbd +size 5554072608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c06d99d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO +datasets: +- Anthropic/hh-rlhf +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-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/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q2_K.gguf) | Q2_K | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_S.gguf) | Q3_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q4_K_M.gguf) | Q4_K_M | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q5_K_M.gguf) | Q5_K_M | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q6_K.gguf) | Q6_K | 2.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.Q8_0.gguf) | Q8_0 | 3.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF/resolve/main/Pythia-2.8B-HH-RLHF-Iterative-SamPO.f16.gguf) | f16 | 5.7 | 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. + +