commit bf592a1f07014da9758c59003ab7916beb3e4e2e Author: ModelHub XC Date: Thu Aug 6 09:33:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-capro-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1e610ff --- /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 +llama-capro.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-capro.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f172bde --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: teclabs/llama-capro +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- llama-3 +- gguf +- quantized +- indian-accounting +- ind-as +- finance +- accounting +- ca +--- +## About + + + + + + + + + +static quants of https://huggingface.co/teclabs/llama-capro + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-capro-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/llama-capro-GGUF/resolve/main/llama-capro.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-capro-GGUF/resolve/main/llama-capro.f16.gguf) | f16 | 16.2 | 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/llama-capro.IQ4_XS.gguf b/llama-capro.IQ4_XS.gguf new file mode 100644 index 0000000..772572b --- /dev/null +++ b/llama-capro.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d79273fe977fcb58165c123f30df20a0c79b3b8cdfe103d977ddc7e8952a3c3 +size 4484368288 diff --git a/llama-capro.Q2_K.gguf b/llama-capro.Q2_K.gguf new file mode 100644 index 0000000..6d8b093 --- /dev/null +++ b/llama-capro.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331ba023daa624fc4567f38f76db3450c3c3c265efef7af44f5ae943c43b71c2 +size 3179136928 diff --git a/llama-capro.Q3_K_L.gguf b/llama-capro.Q3_K_L.gguf new file mode 100644 index 0000000..8162f60 --- /dev/null +++ b/llama-capro.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a94a310fe1ebd77b05a869c7403227fa187f35e6b40608a678ac0fde4a5673 +size 4321961888 diff --git a/llama-capro.Q3_K_M.gguf b/llama-capro.Q3_K_M.gguf new file mode 100644 index 0000000..27101c0 --- /dev/null +++ b/llama-capro.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb6488b141662ef4685fd78091809efe1e740e254f48e002a4e6a5035d51770 +size 4018923424 diff --git a/llama-capro.Q3_K_S.gguf b/llama-capro.Q3_K_S.gguf new file mode 100644 index 0000000..dc1b13b --- /dev/null +++ b/llama-capro.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:219a0c13c5ec121c2c5e8eef265ca8f8b9faef42d5c39f718af1b780533d6534 +size 3664504736 diff --git a/llama-capro.Q4_K_M.gguf b/llama-capro.Q4_K_M.gguf new file mode 100644 index 0000000..2d65289 --- /dev/null +++ b/llama-capro.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75727b4ac9ffe26134b3cce19969735a73e3028812ab91fd5c95db3586be1d87 +size 4920739744 diff --git a/llama-capro.Q4_K_S.gguf b/llama-capro.Q4_K_S.gguf new file mode 100644 index 0000000..3dde955 --- /dev/null +++ b/llama-capro.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca554d5dda89eab1964f4e419c4edc52d7c5f7482d642c008fcb4e09bdcc71a4 +size 4692674464 diff --git a/llama-capro.Q5_K_M.gguf b/llama-capro.Q5_K_M.gguf new file mode 100644 index 0000000..6fd587f --- /dev/null +++ b/llama-capro.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42759d26da5fe678965d55ed3e004e5de3bc07b641b01a4a8368b0adb7791e9b +size 5732992928 diff --git a/llama-capro.Q5_K_S.gguf b/llama-capro.Q5_K_S.gguf new file mode 100644 index 0000000..5bbd051 --- /dev/null +++ b/llama-capro.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb3c7bd619b67e9b362e68c74848ba24741b0c12c6223e9509e7e1e5222dc4ab +size 5599299488 diff --git a/llama-capro.Q6_K.gguf b/llama-capro.Q6_K.gguf new file mode 100644 index 0000000..4530d04 --- /dev/null +++ b/llama-capro.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e073a4e16d7e444927918ac00d74e42e510cf9440a9a7ac2908d2607df4efde +size 6596011936 diff --git a/llama-capro.Q8_0.gguf b/llama-capro.Q8_0.gguf new file mode 100644 index 0000000..23c6f79 --- /dev/null +++ b/llama-capro.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00082480a7de50c8e101b349f3db6069379f2256ca1ab360dffd242e3b810d8c +size 8540776352 diff --git a/llama-capro.f16.gguf b/llama-capro.f16.gguf new file mode 100644 index 0000000..41c69cc --- /dev/null +++ b/llama-capro.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8cc20bb889bbc6e46bc8418ebb05c9b2d422aa1e8fa4c3f7470cf4b4b2e436 +size 16068896672