commit 6b1030fda3b3dad4915d193668927461629035f7 Author: ModelHub XC Date: Sat Jun 27 04:54:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b731824 --- /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 +BetterLlama-3.2-3b-Chain_of_thought.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BetterLlama-3.2-3b-Chain_of_thought.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BetterLlama-3.2-3b-Chain_of_thought.IQ4_XS.gguf b/BetterLlama-3.2-3b-Chain_of_thought.IQ4_XS.gguf new file mode 100644 index 0000000..aedad8f --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1099041fe2885a32f1d27848c59dafe68cd1b5c91d642d330bd3fd5f0e92ad78 +size 1840907392 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q2_K.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q2_K.gguf new file mode 100644 index 0000000..4bcc5ec --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77a88fb7dacfadaac6fd4456170e7751f8e1b2b0d750e9a120145c46de38ede +size 1363936384 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_L.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_L.gguf new file mode 100644 index 0000000..fe121e7 --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e934aba499fe3f983feb7636f7508991e45aa501791e24baeedf559891672b2b +size 1815348352 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_M.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_M.gguf new file mode 100644 index 0000000..7ee01fc --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ec50bc65639654058ef9a34a42863be0147cf1a7dea154e150d8e1fb5fe701 +size 1687159936 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_S.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_S.gguf new file mode 100644 index 0000000..8e11bcb --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0167958fa42c4382c9a9a46df2607d6a821b67d58f1a8013039665be8b108f +size 1542849664 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q4_K_M.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q4_K_M.gguf new file mode 100644 index 0000000..f3e8d62 --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b442f836fe85d4de88f93dfa036f2d2d1615f15c8641bd185c70e2b8a785551 +size 2019378304 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q4_K_S.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q4_K_S.gguf new file mode 100644 index 0000000..56bc840 --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798d6f66419332b0dc9d07c3970cde8a9255db507fb804468157d594e82b0ea9 +size 1928201344 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q5_K_M.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q5_K_M.gguf new file mode 100644 index 0000000..fe9198e --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b74b6759b7837aff519fa5c6796f9d43d65f43ec32254972b0ec7d3200973c72 +size 2322154624 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q5_K_S.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q5_K_S.gguf new file mode 100644 index 0000000..262fdcd --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133c4c666976794151a278072f35836cba7bb3d49cff7dc48120794e3fe55cd8 +size 2269512832 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q6_K.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q6_K.gguf new file mode 100644 index 0000000..67695e4 --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61d73e5a4fe9e0853923d83ee518073a30f0fb19bf179788d876502eba9753c +size 2643854464 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.Q8_0.gguf b/BetterLlama-3.2-3b-Chain_of_thought.Q8_0.gguf new file mode 100644 index 0000000..1c40059 --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a282dbdf8a3ee150920c2b8233f9d3a05252b1b7c21932e615ba623fddc4df62 +size 3421899904 diff --git a/BetterLlama-3.2-3b-Chain_of_thought.f16.gguf b/BetterLlama-3.2-3b-Chain_of_thought.f16.gguf new file mode 100644 index 0000000..9c60790 --- /dev/null +++ b/BetterLlama-3.2-3b-Chain_of_thought.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0713d712090faf4814170a9eea5ec11d72f07762cb2314cbd1306e45d34fd74 +size 6433688704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..63f5049 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Chetanreddy1/BetterLlama-3.2-3b-Chain_of_thought +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/Chetanreddy1/BetterLlama-3.2-3b-Chain_of_thought + + +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/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BetterLlama-3.2-3b-Chain_of_thought-GGUF/resolve/main/BetterLlama-3.2-3b-Chain_of_thought.f16.gguf) | f16 | 6.5 | 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. + +