commit f3adc99f86a9baa5eaf81f9024d908dd257383b0 Author: ModelHub XC Date: Sat Jun 13 11:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama2-fine-tuned-dolly-15k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fad34c1 --- /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 +llama2-fine-tuned-dolly-15k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-fine-tuned-dolly-15k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3db8d1a --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Sreenijaj/llama2-fine-tuned-dolly-15k +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Sreenijaj/llama2-fine-tuned-dolly-15k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama2-fine-tuned-dolly-15k-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/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-fine-tuned-dolly-15k-GGUF/resolve/main/llama2-fine-tuned-dolly-15k.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. + + diff --git a/llama2-fine-tuned-dolly-15k.IQ4_XS.gguf b/llama2-fine-tuned-dolly-15k.IQ4_XS.gguf new file mode 100644 index 0000000..ad0009e --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b378a088a9fb43218b159800a014e7ee4ae0c7752b948a6e3c3a181e0eb4f7 +size 3647517344 diff --git a/llama2-fine-tuned-dolly-15k.Q2_K.gguf b/llama2-fine-tuned-dolly-15k.Q2_K.gguf new file mode 100644 index 0000000..1fdce42 --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7494824378d4b3a03ba7ccb1261d67fdc446bd8e0300cbe33c192621d91823 +size 2532864672 diff --git a/llama2-fine-tuned-dolly-15k.Q3_K_L.gguf b/llama2-fine-tuned-dolly-15k.Q3_K_L.gguf new file mode 100644 index 0000000..317a4bc --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a05a7527a521428953a054bdd3e2dcda90c69901f7a2de1073998145d9b356f +size 3597111968 diff --git a/llama2-fine-tuned-dolly-15k.Q3_K_M.gguf b/llama2-fine-tuned-dolly-15k.Q3_K_M.gguf new file mode 100644 index 0000000..0e8fbbe --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d547e0bb7196baa64cf715fa742b3cc53b125dc0b1c7dd39125e714e5a8a3ace +size 3298005664 diff --git a/llama2-fine-tuned-dolly-15k.Q3_K_S.gguf b/llama2-fine-tuned-dolly-15k.Q3_K_S.gguf new file mode 100644 index 0000000..2f4fa6e --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78b6bdfc7d48aa8247b49121b32600e7b652cfe9d657297dff931ff1d4cf0db8 +size 2948305568 diff --git a/llama2-fine-tuned-dolly-15k.Q4_K_M.gguf b/llama2-fine-tuned-dolly-15k.Q4_K_M.gguf new file mode 100644 index 0000000..ce1cb32 --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6952fdd0ee8a08025aa72289472bd1dfd302ba4db7e0afde2853e7a01596b9cd +size 4081005216 diff --git a/llama2-fine-tuned-dolly-15k.Q4_K_S.gguf b/llama2-fine-tuned-dolly-15k.Q4_K_S.gguf new file mode 100644 index 0000000..b3ad7fb --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2edae653a6ff220b0cd0f692316eab96ae0cbfac0503e99085bcd5c195096236 +size 3856741024 diff --git a/llama2-fine-tuned-dolly-15k.Q5_K_M.gguf b/llama2-fine-tuned-dolly-15k.Q5_K_M.gguf new file mode 100644 index 0000000..0c8223d --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:390680af060b69f1ed27fe5df739dbfec0bf7ee88a056a5a76a55d225fb5ec3e +size 4783157920 diff --git a/llama2-fine-tuned-dolly-15k.Q5_K_S.gguf b/llama2-fine-tuned-dolly-15k.Q5_K_S.gguf new file mode 100644 index 0000000..2ec9179 --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e5a84d1c82de58c2658461fca71a4543e7aaaef342317715e42f0cbcb898a8 +size 4651692704 diff --git a/llama2-fine-tuned-dolly-15k.Q6_K.gguf b/llama2-fine-tuned-dolly-15k.Q6_K.gguf new file mode 100644 index 0000000..5a61b1d --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57de86e45707ad8b759e43d39a02fa23fd2e428eba1778ca44bfdec44d560d96 +size 5529195168 diff --git a/llama2-fine-tuned-dolly-15k.Q8_0.gguf b/llama2-fine-tuned-dolly-15k.Q8_0.gguf new file mode 100644 index 0000000..d7e2c76 --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01a0c9928bea3a9e75bfc8c05156498a8d5e8712d76a1f1fa86de1523984f2e5 +size 7161090720 diff --git a/llama2-fine-tuned-dolly-15k.f16.gguf b/llama2-fine-tuned-dolly-15k.f16.gguf new file mode 100644 index 0000000..9a42ff1 --- /dev/null +++ b/llama2-fine-tuned-dolly-15k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6eb6917cd01e0ef02ce5fff7765f89eb997dc369fce174acb270cfd23cc518 +size 13478105760