commit 264d7a3a0dadc87229d8592284c8e3b7c42b680f Author: ModelHub XC Date: Tue Oct 20 14:00:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/lambda-llama-3-8b-ipo-test-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5aa4e65 --- /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 +lambda-llama-3-8b-ipo-test.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lambda-llama-3-8b-ipo-test.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5f8811e --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: tanliboy/lambda-llama-3-8b-ipo-test +datasets: +- HuggingFaceH4/ultrafeedback_binarized +- tanliboy/orca_dpo_pairs +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- dpo +- generated_from_trainer +- trl +- dpo +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/tanliboy/lambda-llama-3-8b-ipo-test + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#lambda-llama-3-8b-ipo-test-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/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/lambda-llama-3-8b-ipo-test-GGUF/resolve/main/lambda-llama-3-8b-ipo-test.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/lambda-llama-3-8b-ipo-test.IQ4_XS.gguf b/lambda-llama-3-8b-ipo-test.IQ4_XS.gguf new file mode 100644 index 0000000..2960a6e --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e8a3c0d8f3a79e118f659496643865e32758e7f176a599c3438c153f8c6dfe +size 4484368704 diff --git a/lambda-llama-3-8b-ipo-test.Q2_K.gguf b/lambda-llama-3-8b-ipo-test.Q2_K.gguf new file mode 100644 index 0000000..707256c --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee46dc83075f8fad386d568e01c869b72b99c360fc0e6cd3de643b7da9fa7e39 +size 3179137344 diff --git a/lambda-llama-3-8b-ipo-test.Q3_K_L.gguf b/lambda-llama-3-8b-ipo-test.Q3_K_L.gguf new file mode 100644 index 0000000..00a3709 --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5959fe8202f80aaed7dd32c3b8af79596c64789d7f0d2d0548221d9ad97c918 +size 4321962304 diff --git a/lambda-llama-3-8b-ipo-test.Q3_K_M.gguf b/lambda-llama-3-8b-ipo-test.Q3_K_M.gguf new file mode 100644 index 0000000..59c97a1 --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed0c5d854997dfee7b40f81bd6d1fbf9b7c7a6de6b8b29017ac685fa4fce956 +size 4018923840 diff --git a/lambda-llama-3-8b-ipo-test.Q3_K_S.gguf b/lambda-llama-3-8b-ipo-test.Q3_K_S.gguf new file mode 100644 index 0000000..b147fb5 --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c285a54742ac1c993504f311c296e82e790f0bc2d57a5a1486952a6729062db +size 3664505152 diff --git a/lambda-llama-3-8b-ipo-test.Q4_K_M.gguf b/lambda-llama-3-8b-ipo-test.Q4_K_M.gguf new file mode 100644 index 0000000..a3d1d30 --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4968e972c0969ab9873183ce8082163c6713787bd62096620b9dadd4e849d798 +size 4920740160 diff --git a/lambda-llama-3-8b-ipo-test.Q4_K_S.gguf b/lambda-llama-3-8b-ipo-test.Q4_K_S.gguf new file mode 100644 index 0000000..afed870 --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f95f15a934885155b34c1a9e1c11507bfedb37fc2a823a119d2275ed35febbe +size 4692674880 diff --git a/lambda-llama-3-8b-ipo-test.Q5_K_M.gguf b/lambda-llama-3-8b-ipo-test.Q5_K_M.gguf new file mode 100644 index 0000000..00a75a0 --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301563a9b77a0b491a5ce8ee5cf300ab9d1356bb0a05f044aeb59f71fd79caf3 +size 5732993344 diff --git a/lambda-llama-3-8b-ipo-test.Q5_K_S.gguf b/lambda-llama-3-8b-ipo-test.Q5_K_S.gguf new file mode 100644 index 0000000..e2dead5 --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:404519e93259d63a3473520969bc24d54811ca950b248ebd7fd2535452fb9f4e +size 5599299904 diff --git a/lambda-llama-3-8b-ipo-test.Q6_K.gguf b/lambda-llama-3-8b-ipo-test.Q6_K.gguf new file mode 100644 index 0000000..eb41c89 --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f51a4ccd100f3efb36970b5e2923f79fb99b281a2eae206cfda6bb5e87050b6 +size 6596012352 diff --git a/lambda-llama-3-8b-ipo-test.Q8_0.gguf b/lambda-llama-3-8b-ipo-test.Q8_0.gguf new file mode 100644 index 0000000..505eead --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d4806fc892324cb3a59aa46d91d61a1c9ea41fdbbdf8b3aa4a338f6d1a0f08 +size 8540776768 diff --git a/lambda-llama-3-8b-ipo-test.f16.gguf b/lambda-llama-3-8b-ipo-test.f16.gguf new file mode 100644 index 0000000..8eb06aa --- /dev/null +++ b/lambda-llama-3-8b-ipo-test.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe7bf6c028f20a76bc91548033b9d14e292026afb4abad5b02373472676eed9 +size 16068897088