commit 388f3196c53153a4a69f2ab5cdeb72a8d5f0075e Author: ModelHub XC Date: Thu May 14 18:23:43 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tinyllama-1.1b-layla-v4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8a30551 --- /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-layla-v4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-layla-v4.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8511121 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: l3utterfly/tinyllama-1.1b-layla-v4 +language: +- en +library_name: transformers +license: apache-2.0 +model_creator: l3utterfly +model_name: tinyllama-1.1b-layla-v4 +model_type: llama2 +quantized_by: mradermacher +tags: +- finetuned +- text-generation +- autotrain_compatible +- endpoints_compatible +- chatml +--- +## About + + + + + + +static quants of https://huggingface.co/l3utterfly/tinyllama-1.1b-layla-v4 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-i1-GGUF +## 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-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-1.1b-layla-v4-GGUF/resolve/main/tinyllama-1.1b-layla-v4.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-layla-v4.IQ4_XS.gguf b/tinyllama-1.1b-layla-v4.IQ4_XS.gguf new file mode 100644 index 0000000..43c37c9 --- /dev/null +++ b/tinyllama-1.1b-layla-v4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0633fd1aaf587ec491ca7b4e5649de1885c4ebb25158fd4ad407734f5b6dcf03 +size 609807968 diff --git a/tinyllama-1.1b-layla-v4.Q2_K.gguf b/tinyllama-1.1b-layla-v4.Q2_K.gguf new file mode 100644 index 0000000..769edb1 --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607a41eed9bf4e34efc7302a3f640378352004877675f19a4cc10962e6c664f5 +size 432131680 diff --git a/tinyllama-1.1b-layla-v4.Q3_K_L.gguf b/tinyllama-1.1b-layla-v4.Q3_K_L.gguf new file mode 100644 index 0000000..6d89ecf --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:862ff73c0c484fceee32225f89bc7dc3dd003fda0056da3f980e613ba9f4506a +size 591527520 diff --git a/tinyllama-1.1b-layla-v4.Q3_K_M.gguf b/tinyllama-1.1b-layla-v4.Q3_K_M.gguf new file mode 100644 index 0000000..3694fa9 --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a3edd1b7f6475fcf5c06a99196d4e5bb78287649d51fc0258604761a9f88857 +size 548404832 diff --git a/tinyllama-1.1b-layla-v4.Q3_K_S.gguf b/tinyllama-1.1b-layla-v4.Q3_K_S.gguf new file mode 100644 index 0000000..1398b19 --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05872143d95d93a502630a19ef404c9a9204fb758d13084eed5819944b3ec3fb +size 499342944 diff --git a/tinyllama-1.1b-layla-v4.Q4_K_M.gguf b/tinyllama-1.1b-layla-v4.Q4_K_M.gguf new file mode 100644 index 0000000..ac9841a --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0129c70cd247abf40c50251c220d023ecfa8fd3596a88a70ba7c493c04f9691 +size 667815520 diff --git a/tinyllama-1.1b-layla-v4.Q4_K_S.gguf b/tinyllama-1.1b-layla-v4.Q4_K_S.gguf new file mode 100644 index 0000000..1e9b2ca --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289bf40da595e00b5938ab4ef1935d2d15f40e0a7d7f617891c8fd8bdb13a87e +size 639872608 diff --git a/tinyllama-1.1b-layla-v4.Q5_K_M.gguf b/tinyllama-1.1b-layla-v4.Q5_K_M.gguf new file mode 100644 index 0000000..260d4a9 --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b810fb01b321823c1bee1238c9dd24fda854ea533fc71221fe183df0be224d +size 782044768 diff --git a/tinyllama-1.1b-layla-v4.Q5_K_S.gguf b/tinyllama-1.1b-layla-v4.Q5_K_S.gguf new file mode 100644 index 0000000..e056cb6 --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcbd5c99e029291d8c3fd1d768183028f5d769f5f1c2a0e5fe05020b6668fd19 +size 766029408 diff --git a/tinyllama-1.1b-layla-v4.Q6_K.gguf b/tinyllama-1.1b-layla-v4.Q6_K.gguf new file mode 100644 index 0000000..aee1e25 --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46637388fc408498b213cee895419886878d837066aad98bba11c7466afa30e0 +size 903413344 diff --git a/tinyllama-1.1b-layla-v4.Q8_0.gguf b/tinyllama-1.1b-layla-v4.Q8_0.gguf new file mode 100644 index 0000000..09655c4 --- /dev/null +++ b/tinyllama-1.1b-layla-v4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e846cd4778befc27da9c9a0288ca212a0e37b813177984eabf841fc2dbf5ee4c +size 1169808992 diff --git a/tinyllama-1.1b-layla-v4.f16.gguf b/tinyllama-1.1b-layla-v4.f16.gguf new file mode 100644 index 0000000..425569a --- /dev/null +++ b/tinyllama-1.1b-layla-v4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e4b40c81e9dad406d1bbdf7cfaf57a699a8fdf4b6b10b6ead2adf4f99731ebd +size 2201017952