commit 03a7fe9c739509321990665822bff27a059e0a48 Author: ModelHub XC Date: Tue Apr 21 23:03:42 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..beea75b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-Chat-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-v1.0.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c008b6 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 +datasets: +- cerebras/SlimPajama-627B +- bigcode/starcoderdata +- HuggingFaceH4/ultrachat_200k +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-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-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.7 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/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. + + diff --git a/TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf b/TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..64b1087 --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb8aae6b730afc8bbeae515e8b6fb0687d8896741c58034effc0c6471c8649c1 +size 609809056 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf b/TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf new file mode 100644 index 0000000..5544b0e --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb416bc8264c27f45375dd15c861f87fd435738961e53e1bdf97d89626bc2689 +size 432132768 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf b/TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..7246b1b --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c324a6fd14f293ba9fa8ffb2c3ecef7d99d55b0ee36790614abe094963a361 +size 591528608 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf b/TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..37bfbbb --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f5f96835f5cedcc317e7d56b4815494fb602bb25e24b8414835d0a7ec8e76b +size 548405920 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf b/TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..2dd0277 --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7bc7741229a3c7082e4ebe3046d3dd65bf106b03cd0153b53ed66e02d461b65 +size 499344032 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q4_0_4_4.gguf b/TinyLlama-1.1B-Chat-v1.0.Q4_0_4_4.gguf new file mode 100644 index 0000000..16ec85b --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ddc7e3361944b5cd8e27ec4a512a2729124a8528317a866d86740fb91f6afdd +size 636727968 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf b/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..8e61d38 --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70737cdeae63476bd36561010297a650bf9a6ba235a0e31e7325e16a84beeff7 +size 667816608 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf b/TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..fda2432 --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e22630e4ee9a4f92bf958f9347800b0d619ea3a9f9f845d3b697d57f4a5630 +size 639873696 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf b/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..ba00692 --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb070040a8be94b8d69aa2604c3a8f5e1a8e75a1ceed6f6b32f6d7cdbbef1d8 +size 782045856 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf b/TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..543a511 --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1301718b649f22438c807251a8b272ffe7b645e42afb5559d143815fb02c813 +size 766030496 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf b/TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf new file mode 100644 index 0000000..04e91ec --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23b26ae371286f251532a8a8738846738131248c2cb58c1a93197f117a14aca +size 903414432 diff --git a/TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf b/TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf new file mode 100644 index 0000000..2e960e7 --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721abf014c83163b40ca52d465f3084f436303700cdce168463027004dfd4945 +size 1169810080 diff --git a/TinyLlama-1.1B-Chat-v1.0.f16.gguf b/TinyLlama-1.1B-Chat-v1.0.f16.gguf new file mode 100644 index 0000000..7810aa3 --- /dev/null +++ b/TinyLlama-1.1B-Chat-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83b5b067440dc582f8a9c217c3a17c15234a5c7ce1899f54d3a9f0f2007245a +size 2201019040