commit 90885a3d6577f32cd529a2b49140ed49105888a2 Author: ModelHub XC Date: Tue Sep 22 00:33:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9f60f66 --- /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 +Blueberry-TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Blueberry-TinyLlama-1.1B-Chat-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..17cc167 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bc25dc90ecb45bd5cf1b8cb028e6c4ca8dcf5b4d057c29703033e74a1e936b2 +size 609808320 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf new file mode 100644 index 0000000..ff0c711 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587717585cf5fc9570c17b0764b5362a28c11c2fa52f2a19bb8532017cdc6196 +size 432132032 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..1c024f5 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1515f94afa97ded3317b610202678712761ebb53b4abb8dc6ac4f84b5b0b0026 +size 591527872 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..431dbe7 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b19b6acaf39bf3b4646b292d63f9014fc8b9664975a93905bb379e923afb4085 +size 548405184 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..5ae3ddd --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a4fe05359d0a502ba0fb85e65436b40df4c0d6fc1a6c851f0f06c3be9dbe6f7 +size 499343296 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..cac3357 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22160f4bfdada2c4ed4cd0c185b3cf063a73c6176f5ca78eeaaa5523c8a2b217 +size 667815872 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..99ed0c8 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1b85663f65d94b896302d88fcc6cf2edd55c138ba336ff21cda5155cbabe71 +size 639872960 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..0e5b247 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:327b01cece283b736b32433531da583718f94c2fc8aae954f2ac89cb1381dd18 +size 782045120 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..d399190 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7ffa5c5c991dc0d7c2a858824db3bbe3064529c7686fdaff4d9f3fac703330 +size 766029760 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf new file mode 100644 index 0000000..77d9e5c --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8658f220de8092b65190b4da8add9c6b7a3e15ed65f31f577fa108b351ef54d +size 903413696 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf new file mode 100644 index 0000000..61e0b21 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48de91ed1e881b9b65ded3082a919846fe29d063e5e3386ecf1534a8812c7571 +size 1169809344 diff --git a/Blueberry-TinyLlama-1.1B-Chat-v1.0.f16.gguf b/Blueberry-TinyLlama-1.1B-Chat-v1.0.f16.gguf new file mode 100644 index 0000000..ffa1e58 --- /dev/null +++ b/Blueberry-TinyLlama-1.1B-Chat-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c6d708f808f9ac9c5f8e3e03d9735d10a420154ec52a1310dbe5c804269b4a +size 2201018304 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b0fc3a7 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: shreyanth/Blueberry-TinyLlama-1.1B-Chat-v1.0 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/shreyanth/Blueberry-TinyLlama-1.1B-Chat-v1.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Blueberry-TinyLlama-1.1B-Chat-v1.0-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/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Blueberry-TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/Blueberry-TinyLlama-1.1B-Chat-v1.0.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. + +