commit 3f25e8329102e117943f73642501e3b19234ca6e Author: ModelHub XC Date: Sat Jul 18 02:50:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama_finetuned_description_generator_1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1429f9a --- /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_finetuned_description_generator_1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama_finetuned_description_generator_1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..87977dd --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: kavish218/llama_finetuned_description_generator_1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/kavish218/llama_finetuned_description_generator_1 + + +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_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama_finetuned_description_generator_1-GGUF/resolve/main/llama_finetuned_description_generator_1.f16.gguf) | f16 | 2.6 | 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_finetuned_description_generator_1.IQ4_XS.gguf b/llama_finetuned_description_generator_1.IQ4_XS.gguf new file mode 100644 index 0000000..062f992 --- /dev/null +++ b/llama_finetuned_description_generator_1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:152ab28f2a48004dcefdd8595df987c72a39c47b6cb55c037cef9e28b1a991e0 +size 748385088 diff --git a/llama_finetuned_description_generator_1.Q2_K.gguf b/llama_finetuned_description_generator_1.Q2_K.gguf new file mode 100644 index 0000000..298d997 --- /dev/null +++ b/llama_finetuned_description_generator_1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dced8700f191cf454dac6f6a51b292356c39d3242650e407fd9e66f7652116a5 +size 580875072 diff --git a/llama_finetuned_description_generator_1.Q3_K_L.gguf b/llama_finetuned_description_generator_1.Q3_K_L.gguf new file mode 100644 index 0000000..47645db --- /dev/null +++ b/llama_finetuned_description_generator_1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7120e6690467e5b2e1ec0829bd343e9fe0bd1b317c40ed1d4f6c180d1b187f4 +size 732525376 diff --git a/llama_finetuned_description_generator_1.Q3_K_M.gguf b/llama_finetuned_description_generator_1.Q3_K_M.gguf new file mode 100644 index 0000000..edb6bfd --- /dev/null +++ b/llama_finetuned_description_generator_1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e132166d70c6ea785b2a355b2887f0de7fbe896dfa5c748fd60006277cbb43f9 +size 690844480 diff --git a/llama_finetuned_description_generator_1.Q3_K_S.gguf b/llama_finetuned_description_generator_1.Q3_K_S.gguf new file mode 100644 index 0000000..d58f558 --- /dev/null +++ b/llama_finetuned_description_generator_1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a57f77eee72da0c465e63cf0dfaaae7f7670818f0d2efd5506e37732f7691b1f +size 641692480 diff --git a/llama_finetuned_description_generator_1.Q4_K_M.gguf b/llama_finetuned_description_generator_1.Q4_K_M.gguf new file mode 100644 index 0000000..b23201c --- /dev/null +++ b/llama_finetuned_description_generator_1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b819a579a568c9b33a192a81a42a86a181b4072c3408c33dff5f38eae6a2135 +size 807695168 diff --git a/llama_finetuned_description_generator_1.Q4_K_S.gguf b/llama_finetuned_description_generator_1.Q4_K_S.gguf new file mode 100644 index 0000000..e2e0a26 --- /dev/null +++ b/llama_finetuned_description_generator_1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:973cdc3f96d74fad32e977cbe442a09a849d4cf4881af75cc54e03c60e04a1c9 +size 775648064 diff --git a/llama_finetuned_description_generator_1.Q5_K_M.gguf b/llama_finetuned_description_generator_1.Q5_K_M.gguf new file mode 100644 index 0000000..6ca79ed --- /dev/null +++ b/llama_finetuned_description_generator_1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e868cfa6fe4f35227378e1f088e52f11b8c719ee86c9ac979edebcd5db620e +size 911504192 diff --git a/llama_finetuned_description_generator_1.Q5_K_S.gguf b/llama_finetuned_description_generator_1.Q5_K_S.gguf new file mode 100644 index 0000000..1aa85cf --- /dev/null +++ b/llama_finetuned_description_generator_1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f4188f9ab831bbbd01f6d8fb2845277fdb0e893bd4a75c703ae0c4cee0f5144 +size 892564288 diff --git a/llama_finetuned_description_generator_1.Q6_K.gguf b/llama_finetuned_description_generator_1.Q6_K.gguf new file mode 100644 index 0000000..b17b680 --- /dev/null +++ b/llama_finetuned_description_generator_1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf66a745114fedf035186c9409660a1998c1742f7c72cba68e0cadca9119421 +size 1021801280 diff --git a/llama_finetuned_description_generator_1.Q8_0.gguf b/llama_finetuned_description_generator_1.Q8_0.gguf new file mode 100644 index 0000000..fb20492 --- /dev/null +++ b/llama_finetuned_description_generator_1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9479d059c5321b6a6bae33d986e3926a60fd4b32985db0ad1507b33193bb4bce +size 1321083712 diff --git a/llama_finetuned_description_generator_1.f16.gguf b/llama_finetuned_description_generator_1.f16.gguf new file mode 100644 index 0000000..d92f8b4 --- /dev/null +++ b/llama_finetuned_description_generator_1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9085e37654c5711cd0756966e797d861b4fb0db7cf2990ec68bf63a09783ef26 +size 2479596352