commit 984b336f1455fd10c92a939de138ee22cd398d53 Author: ModelHub XC Date: Wed Apr 22 13:35:43 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7638999 --- /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 +DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.f16.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DPO-Kimlan-Llama-2-7b-hf-tw.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.IQ4_XS.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.IQ4_XS.gguf new file mode 100644 index 0000000..41f35ce --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f17bb84f8d2dbbb9adfa939397faad50c902418b14a288bcc67649877ad23556 +size 3647517440 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q2_K.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q2_K.gguf new file mode 100644 index 0000000..fc7c57a --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85ae1ab117faa58b855f225db2630d7c85853efd6ac5d829aadcbcdf3237635b +size 2532864768 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_L.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_L.gguf new file mode 100644 index 0000000..9ac5252 --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5faa63ada2d8cca6953314f4c1f2b005362405cf17c712a43934c733cfd8cae +size 3597112064 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_M.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_M.gguf new file mode 100644 index 0000000..d1335c9 --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff12674474d5249c82a3ac7318d8e3a3b08725e94ac69b56efb97cdd5f0b86af +size 3298005760 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_S.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_S.gguf new file mode 100644 index 0000000..8a32227 --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47e7eaccd59a761dbd458ab8f1434c9fe25ce73a28f13395564784ab4c4cd6ae +size 2948305664 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_M.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_M.gguf new file mode 100644 index 0000000..0b3bf1e --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a73f544d8d276453cb9fe4cc15392e14f53552ee2bfbfbb0dbf7476cebc6fd +size 4081005312 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_S.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_S.gguf new file mode 100644 index 0000000..43cd0b2 --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9553cf72a7258cda4dc4d174da060535ef37a79c455789e0a13fe96d70e9a750 +size 3856741120 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_M.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_M.gguf new file mode 100644 index 0000000..f9331d9 --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2fbe07f6c5e99fcdbd0209f9ec1804a9be55e364f0878e0f6848768dffa842 +size 4783158016 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_S.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_S.gguf new file mode 100644 index 0000000..46d767f --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd47bb62a65bced7e382813903f6becd32a3c5ffb9c2d533115dc449f9db3fa +size 4651692800 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q6_K.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q6_K.gguf new file mode 100644 index 0000000..4f0f7ae --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874d51a4a329b58c091ad0fa8ff572f65eec79769b947f8c8ea4df4399ad6dcb +size 5529195264 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.Q8_0.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.Q8_0.gguf new file mode 100644 index 0000000..bf123d8 --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22930ffaf82cb94800772ae9c9b135725c18133a57d12afc1cbe89f5d48f2767 +size 7161090816 diff --git a/DPO-Kimlan-Llama-2-7b-hf-tw.f16.gguf b/DPO-Kimlan-Llama-2-7b-hf-tw.f16.gguf new file mode 100644 index 0000000..1e62a41 --- /dev/null +++ b/DPO-Kimlan-Llama-2-7b-hf-tw.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e327b20aa5d785e52eb42dea2e9e2863fd1f3e0393e2ae84da950f19663d2f4 +size 13478105856 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d312fe6 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: elliotthwangmsa/DPO-Kimlan-Llama-2-7b-hf-tw +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/elliotthwangmsa/DPO-Kimlan-Llama-2-7b-hf-tw + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DPO-Kimlan-Llama-2-7b-hf-tw-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/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DPO-Kimlan-Llama-2-7b-hf-tw-GGUF/resolve/main/DPO-Kimlan-Llama-2-7b-hf-tw.f16.gguf) | f16 | 13.6 | 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. + +