commit 4578ae907b516a4a5f0acee7c98618acf177fde5 Author: ModelHub XC Date: Thu Jun 25 17:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/story-gen_llama-sft-partial-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7d882cb --- /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 +story-gen_llama-sft-partial.f16.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +story-gen_llama-sft-partial.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8e16715 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: mehuldamani/story-gen_llama-sft-partial +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mehuldamani/story-gen_llama-sft-partial + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#story-gen_llama-sft-partial-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/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/story-gen_llama-sft-partial-GGUF/resolve/main/story-gen_llama-sft-partial.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/story-gen_llama-sft-partial.IQ4_XS.gguf b/story-gen_llama-sft-partial.IQ4_XS.gguf new file mode 100644 index 0000000..c3856c5 --- /dev/null +++ b/story-gen_llama-sft-partial.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57cfb4b32790f6c25539158c7127f52adc6791642dcc8f460840ec4b543e54d5 +size 4484367776 diff --git a/story-gen_llama-sft-partial.Q2_K.gguf b/story-gen_llama-sft-partial.Q2_K.gguf new file mode 100644 index 0000000..d66eb48 --- /dev/null +++ b/story-gen_llama-sft-partial.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58449d2f28c14c4d151e7aa8df759652e2737f755361f18524c7f6cc113c4f0a +size 3179136416 diff --git a/story-gen_llama-sft-partial.Q3_K_L.gguf b/story-gen_llama-sft-partial.Q3_K_L.gguf new file mode 100644 index 0000000..4175585 --- /dev/null +++ b/story-gen_llama-sft-partial.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35497471f991285a40d69e7e8e76e0f351dd270ba7d8461e1745fe102356091e +size 4321961376 diff --git a/story-gen_llama-sft-partial.Q3_K_M.gguf b/story-gen_llama-sft-partial.Q3_K_M.gguf new file mode 100644 index 0000000..d262dd3 --- /dev/null +++ b/story-gen_llama-sft-partial.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ca10dbfe201197755651c7d598173c2d83a517f4ff3c56bcaa7820f7e6aac5 +size 4018922912 diff --git a/story-gen_llama-sft-partial.Q3_K_S.gguf b/story-gen_llama-sft-partial.Q3_K_S.gguf new file mode 100644 index 0000000..7573e75 --- /dev/null +++ b/story-gen_llama-sft-partial.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c4d7267b6f2ba90c20290b294d5d446e6c7dc5047e47fe95165a47c835356e +size 3664504224 diff --git a/story-gen_llama-sft-partial.Q4_K_M.gguf b/story-gen_llama-sft-partial.Q4_K_M.gguf new file mode 100644 index 0000000..0032d53 --- /dev/null +++ b/story-gen_llama-sft-partial.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e385fef041f730633db3555b58d1eae6d8739b43bbe9ebb72ce52301cd3fc26b +size 4920739232 diff --git a/story-gen_llama-sft-partial.Q4_K_S.gguf b/story-gen_llama-sft-partial.Q4_K_S.gguf new file mode 100644 index 0000000..1ebf23f --- /dev/null +++ b/story-gen_llama-sft-partial.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba7f9155a6691942c40d845433659d1caf593efb693bf6571872f7576b3e970 +size 4692673952 diff --git a/story-gen_llama-sft-partial.Q5_K_M.gguf b/story-gen_llama-sft-partial.Q5_K_M.gguf new file mode 100644 index 0000000..b62f037 --- /dev/null +++ b/story-gen_llama-sft-partial.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb16bebbf73194075bf2eab31a2263205a2b43fee531747e21adf26e5c8e1ba2 +size 5732992416 diff --git a/story-gen_llama-sft-partial.Q5_K_S.gguf b/story-gen_llama-sft-partial.Q5_K_S.gguf new file mode 100644 index 0000000..71e789a --- /dev/null +++ b/story-gen_llama-sft-partial.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2591c911b7f4fb80f9b89e46b2d93ddc385fc19d3185412a2f87d52c82aee8 +size 5599298976 diff --git a/story-gen_llama-sft-partial.Q6_K.gguf b/story-gen_llama-sft-partial.Q6_K.gguf new file mode 100644 index 0000000..527d850 --- /dev/null +++ b/story-gen_llama-sft-partial.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54bc57ff7c76030d2acf65a74af481cb7b5165992b4cc25761d3d94d52d1a5fc +size 6596011424 diff --git a/story-gen_llama-sft-partial.Q8_0.gguf b/story-gen_llama-sft-partial.Q8_0.gguf new file mode 100644 index 0000000..5c41d85 --- /dev/null +++ b/story-gen_llama-sft-partial.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86d4a52054501061c9e0d62dd58658c077528e942dc989487b3e9d3c2e0b2d39 +size 8540775840 diff --git a/story-gen_llama-sft-partial.f16.gguf b/story-gen_llama-sft-partial.f16.gguf new file mode 100644 index 0000000..103c896 --- /dev/null +++ b/story-gen_llama-sft-partial.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43787ccd2fea26f35dd18d4de0aae6bed5cb7cc45b2f5e46a75c1e3cccc0c3af +size 16068896160