commit 14936f0ada62e6d36e2615caf3b0dcc6526e8b30 Author: ModelHub XC Date: Mon Jul 6 19:31:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TwinLlama-3.2-1B-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5c7ff1a --- /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 +TwinLlama-3.2-1B-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-1B-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5cb226d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: jessemeng/TwinLlama-3.2-1B-DPO +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/jessemeng/TwinLlama-3.2-1B-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/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-1B-DPO-GGUF/resolve/main/TwinLlama-3.2-1B-DPO.f16.gguf) | f16 | 2.6 | 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/TwinLlama-3.2-1B-DPO.IQ4_XS.gguf b/TwinLlama-3.2-1B-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..53566a8 --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57ff88854f21c608c34df0585973f11c99ba2f63acc93c42ac488462ff578ef4 +size 748381408 diff --git a/TwinLlama-3.2-1B-DPO.Q2_K.gguf b/TwinLlama-3.2-1B-DPO.Q2_K.gguf new file mode 100644 index 0000000..f3a313f --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f44514eabf4e04812bab6bdb98cfc32af89b57f8af9760cc62c59f47d52c207 +size 580871392 diff --git a/TwinLlama-3.2-1B-DPO.Q3_K_L.gguf b/TwinLlama-3.2-1B-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..af58a82 --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f6e4a336137b42c6bd5d1ddb98e30930bb43753664d951cfd21357786a5f84 +size 732521696 diff --git a/TwinLlama-3.2-1B-DPO.Q3_K_M.gguf b/TwinLlama-3.2-1B-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..e412d61 --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4afb89b7c94db775d1cf2702fc99bc753126f1b241a986df6c868f38b67744e6 +size 690840800 diff --git a/TwinLlama-3.2-1B-DPO.Q3_K_S.gguf b/TwinLlama-3.2-1B-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..58475ed --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a0b877ba5d458c2b18a71b6563cbf245e453e1cb880bfb8acb437c231d5229 +size 641688800 diff --git a/TwinLlama-3.2-1B-DPO.Q4_K_M.gguf b/TwinLlama-3.2-1B-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..7a61eba --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac2f60df6360a134a49d9b87e464a2b32284f26e41e76a6eb1be124a11c2951f +size 807691488 diff --git a/TwinLlama-3.2-1B-DPO.Q4_K_S.gguf b/TwinLlama-3.2-1B-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..e58295d --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8589b676490738d7ceed3b1bfda00ef6d5bf0a20a887a3c75e4461a8e6fa213d +size 775644384 diff --git a/TwinLlama-3.2-1B-DPO.Q5_K_M.gguf b/TwinLlama-3.2-1B-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..628513b --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde42b293e3c2502861d594a97443a185abee6b890828ae7898b5a6bf9537901 +size 911500512 diff --git a/TwinLlama-3.2-1B-DPO.Q5_K_S.gguf b/TwinLlama-3.2-1B-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..cb78a67 --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6379a9c8a08063f0dd0499afe9c8729323c78d955b538eb6822d95ec56df6b0e +size 892560608 diff --git a/TwinLlama-3.2-1B-DPO.Q6_K.gguf b/TwinLlama-3.2-1B-DPO.Q6_K.gguf new file mode 100644 index 0000000..6c0ebfb --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a529e5e20e4928a1634606de9d7d74eb0ac168de1128041690b6024e2dc8d3d0 +size 1021797600 diff --git a/TwinLlama-3.2-1B-DPO.Q8_0.gguf b/TwinLlama-3.2-1B-DPO.Q8_0.gguf new file mode 100644 index 0000000..6e33571 --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ff9a5904ce2a7943cdee59ae5e801b6781000e8fb1b0851b1aa1e0ef5960b3 +size 1321080032 diff --git a/TwinLlama-3.2-1B-DPO.f16.gguf b/TwinLlama-3.2-1B-DPO.f16.gguf new file mode 100644 index 0000000..3cb84ac --- /dev/null +++ b/TwinLlama-3.2-1B-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f9bd8b8d42a442bb7c0ce4ffe282747853eadd2854fdbe04c4c40f5f7adf33 +size 2479592672