commit a2ad0a954711c309da11aa1772c4520b21618ef9 Author: ModelHub XC Date: Wed Jul 8 17:43:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TwinLlama-3.2-3B-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bf9b888 --- /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-3.2-3B-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.2-3B-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..88bbc98 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: michaelnguyen11/TwinLlama-3.2-3B-DPO +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/michaelnguyen11/TwinLlama-3.2-3B-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-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.2-3B-DPO-GGUF/resolve/main/TwinLlama-3.2-3B-DPO.f16.gguf) | f16 | 6.5 | 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-3.2-3B-DPO.IQ4_XS.gguf b/TwinLlama-3.2-3B-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..d025ca2 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:277e23837478517582121a37c0e8d9ec89b62cd82c8ef6946cb3778714680cef +size 1840907776 diff --git a/TwinLlama-3.2-3B-DPO.Q2_K.gguf b/TwinLlama-3.2-3B-DPO.Q2_K.gguf new file mode 100644 index 0000000..5a67f09 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91386854aaeaf3479fef86f1026e4b42a8af07c641b14b33b5a7ed61dea6abdf +size 1363936768 diff --git a/TwinLlama-3.2-3B-DPO.Q3_K_L.gguf b/TwinLlama-3.2-3B-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..5f0b354 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd908e8d5d1284ac15b70ffb44323c292c18a2487c17f300fcedde344bc7a0cf +size 1815348736 diff --git a/TwinLlama-3.2-3B-DPO.Q3_K_M.gguf b/TwinLlama-3.2-3B-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..a61f73f --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bdbedb5a4d6670f5b1498ba8b2cfa6339e79ea889e9b1aba62a8c2823f7991b +size 1687160320 diff --git a/TwinLlama-3.2-3B-DPO.Q3_K_S.gguf b/TwinLlama-3.2-3B-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..9abb906 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2de7524542e31e630a4f5d572385fb18169e8830874ceea9f6f7ef2afb59602 +size 1542850048 diff --git a/TwinLlama-3.2-3B-DPO.Q4_K_M.gguf b/TwinLlama-3.2-3B-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..b8f7532 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad5f207ff2bc313b36bd68e1adf993822595731c1c2fc28ff35e6ee0de85bc8b +size 2019378688 diff --git a/TwinLlama-3.2-3B-DPO.Q4_K_S.gguf b/TwinLlama-3.2-3B-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..1db39fa --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5a8968355a453bbf74260e81bf48daf66fd58bbfebfbb972db3945daf8b3cd +size 1928201728 diff --git a/TwinLlama-3.2-3B-DPO.Q5_K_M.gguf b/TwinLlama-3.2-3B-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..0379405 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946687b2c7dc7fccc7994b45a838a23b608345a7b099be55a3a16e64a03e670e +size 2322155008 diff --git a/TwinLlama-3.2-3B-DPO.Q5_K_S.gguf b/TwinLlama-3.2-3B-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..588ee99 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6d5c41d1edc0beeb9898c82080e6473d309d416807dab8473f2c911094e5cc +size 2269513216 diff --git a/TwinLlama-3.2-3B-DPO.Q6_K.gguf b/TwinLlama-3.2-3B-DPO.Q6_K.gguf new file mode 100644 index 0000000..3fcc75c --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c10edd4e0de4ba1fc31d4001e672fbb2d3566354ba9c0b0387d256cbec35b0 +size 2643854848 diff --git a/TwinLlama-3.2-3B-DPO.Q8_0.gguf b/TwinLlama-3.2-3B-DPO.Q8_0.gguf new file mode 100644 index 0000000..0733ec0 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9cc23111dc1380a279541873751340b125f9dd1ef043c5485fc24279404f47d +size 3421900288 diff --git a/TwinLlama-3.2-3B-DPO.f16.gguf b/TwinLlama-3.2-3B-DPO.f16.gguf new file mode 100644 index 0000000..8efcdf2 --- /dev/null +++ b/TwinLlama-3.2-3B-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294da4c816eb099ce51831617798579e9e9c772424f4928a97aa09bc7a225943 +size 6433689088