commit 77e141aa685a6893ff758c0b46e43e3fcdfcd815 Author: ModelHub XC Date: Thu Sep 17 23:55:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40bbbaf --- /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 +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c76ccc --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: bhaskerbobby/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/bhaskerbobby/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged + + +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/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged-GGUF/resolve/main/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.f16.gguf) | f16 | 2.3 | 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/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.IQ4_XS.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.IQ4_XS.gguf new file mode 100644 index 0000000..a80cec9 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be96a87529a3ed52ca56a8d58ab673fa1f96c454de8c3871513e625e5bf1d8e +size 609807872 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q2_K.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q2_K.gguf new file mode 100644 index 0000000..0ee65e9 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26aac891f270c427ec06214b3dc499cc0e52adfdd3a16430e90865c5b0a63652 +size 432131584 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_L.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_L.gguf new file mode 100644 index 0000000..ea49bc3 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90e4c6ff29813dba48a23e4609d9844c38898208b17b5c62a13f0cb4831da5d +size 591527424 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_M.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_M.gguf new file mode 100644 index 0000000..d3add45 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83342a7ae8de8e5ca98b35708f5ff2986010aec7e262592b69cb83f0a1fc4061 +size 548404736 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_S.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_S.gguf new file mode 100644 index 0000000..cf57334 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:116eae679c927e70ee4a58f213a7af033fe998ecfbbea56d72f28cf6f56b279a +size 499342848 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_M.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_M.gguf new file mode 100644 index 0000000..4d238bf --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343e859766b18b3457c60d44afaafe3c1f6d6b46efb61b1c280f2df64b50a8fa +size 667815424 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_S.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_S.gguf new file mode 100644 index 0000000..4ba19e0 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61298b6ea6948f490ed98fc8adf785b0b02c766b95383ee96db7f803a66a6e14 +size 639872512 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_M.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_M.gguf new file mode 100644 index 0000000..25e29ba --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296bec8d6aaaf2ec6cc5ff85c6616aa6436979111497737e2432ae3fbb1ef6f6 +size 782044672 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_S.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_S.gguf new file mode 100644 index 0000000..bd87abd --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acfc8731eb4b05fb366ffbf4be16aecd1ba1c1c0852fcebb884c375adaffd411 +size 766029312 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q6_K.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q6_K.gguf new file mode 100644 index 0000000..83e45a9 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0250a8fdef9f7b7fe2bf2877cd8ab9984a749da6b6683d04f97c93a1bd39ad +size 903413248 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q8_0.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q8_0.gguf new file mode 100644 index 0000000..f1dc3f2 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b42a1f1072661c7d6b1b74bd154e7cfa5d48319e02ce3eaa8606f5b3b55c73 +size 1169808896 diff --git a/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.f16.gguf b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.f16.gguf new file mode 100644 index 0000000..c407f93 --- /dev/null +++ b/TinyLlama-1.1B-qlora-driveThrough-Dec25-Merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f9460d4b9964402927e4280bc3c6d88152b1984f17db2e68759f842b635f921 +size 2201017856