commit 4770c8dbd3d03bf332ae424bcd99335e9c652d61 Author: ModelHub XC Date: Thu May 7 19:16:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-2-finetuned-storytelling-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4509371 --- /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 +llama-2-finetuned-storytelling.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-finetuned-storytelling.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a95cd26 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: lindtsey/llama-2-finetuned-storytelling +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lindtsey/llama-2-finetuned-storytelling + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-2-finetuned-storytelling-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/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-finetuned-storytelling-GGUF/resolve/main/llama-2-finetuned-storytelling.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/llama-2-finetuned-storytelling.IQ4_XS.gguf b/llama-2-finetuned-storytelling.IQ4_XS.gguf new file mode 100644 index 0000000..57cb383 --- /dev/null +++ b/llama-2-finetuned-storytelling.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97927cddfa7b7c50af80221a76b19b9fae05e40db9b36fb9d0bcc28907caa4a +size 3647517472 diff --git a/llama-2-finetuned-storytelling.Q2_K.gguf b/llama-2-finetuned-storytelling.Q2_K.gguf new file mode 100644 index 0000000..6243f2f --- /dev/null +++ b/llama-2-finetuned-storytelling.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb9fee8abe2013b53e154228457d5462c0eb906bd1e56e9cee5c23f4b046784a +size 2532864800 diff --git a/llama-2-finetuned-storytelling.Q3_K_L.gguf b/llama-2-finetuned-storytelling.Q3_K_L.gguf new file mode 100644 index 0000000..02e5398 --- /dev/null +++ b/llama-2-finetuned-storytelling.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c981a09b9db83786a502232ba41f650600a92570754c062f8eacf56df0943cea +size 3597112096 diff --git a/llama-2-finetuned-storytelling.Q3_K_M.gguf b/llama-2-finetuned-storytelling.Q3_K_M.gguf new file mode 100644 index 0000000..80021ff --- /dev/null +++ b/llama-2-finetuned-storytelling.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b6c380de4be05623b34fda0fe9aa31edb19a46235af12df79cab3e336adda1 +size 3298005792 diff --git a/llama-2-finetuned-storytelling.Q3_K_S.gguf b/llama-2-finetuned-storytelling.Q3_K_S.gguf new file mode 100644 index 0000000..1c183ba --- /dev/null +++ b/llama-2-finetuned-storytelling.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc138427e85abce253de32bcd4fba4264a591f74a1bee9bdbb57cf4bb5d297f7 +size 2948305696 diff --git a/llama-2-finetuned-storytelling.Q4_K_M.gguf b/llama-2-finetuned-storytelling.Q4_K_M.gguf new file mode 100644 index 0000000..041ae55 --- /dev/null +++ b/llama-2-finetuned-storytelling.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c351fe2b45f6a371e075cc9be1048aa43342f1fa3bdf3b48bec4d50148a4c91 +size 4081005344 diff --git a/llama-2-finetuned-storytelling.Q4_K_S.gguf b/llama-2-finetuned-storytelling.Q4_K_S.gguf new file mode 100644 index 0000000..e96a658 --- /dev/null +++ b/llama-2-finetuned-storytelling.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ec0802d49b24b55605b0598577aad917bacb51412642f514fa0265f1b32cbd +size 3856741152 diff --git a/llama-2-finetuned-storytelling.Q5_K_M.gguf b/llama-2-finetuned-storytelling.Q5_K_M.gguf new file mode 100644 index 0000000..fc3961e --- /dev/null +++ b/llama-2-finetuned-storytelling.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:932e0714da3e496cb80cac227e03f132fc8e622ba748c3a2ec6491b991bdf071 +size 4783158048 diff --git a/llama-2-finetuned-storytelling.Q5_K_S.gguf b/llama-2-finetuned-storytelling.Q5_K_S.gguf new file mode 100644 index 0000000..be4cde5 --- /dev/null +++ b/llama-2-finetuned-storytelling.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a9c1bcce9630499a3ef81f728dd069c706e260e8a34b19d7e25cb57614ca872 +size 4651692832 diff --git a/llama-2-finetuned-storytelling.Q6_K.gguf b/llama-2-finetuned-storytelling.Q6_K.gguf new file mode 100644 index 0000000..b76d83c --- /dev/null +++ b/llama-2-finetuned-storytelling.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9674d04c91744aab36285b21e20a4933692aa84375b8c939504cdcc6bc76affe +size 5529195296 diff --git a/llama-2-finetuned-storytelling.Q8_0.gguf b/llama-2-finetuned-storytelling.Q8_0.gguf new file mode 100644 index 0000000..d7e5080 --- /dev/null +++ b/llama-2-finetuned-storytelling.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a810101fd26ff3c0c7fc3bae8d46017131713ba6a9eb70df4babedcddbe8bd +size 7161090848 diff --git a/llama-2-finetuned-storytelling.f16.gguf b/llama-2-finetuned-storytelling.f16.gguf new file mode 100644 index 0000000..80276cf --- /dev/null +++ b/llama-2-finetuned-storytelling.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab80c3e22a36403443b72a23d2ffa01d02993acdc78f5272517fae849627345 +size 13478105888