commit d3222e704a87a321c43572cc212b6a1637ee8ba5 Author: ModelHub XC Date: Sat Sep 19 15:42:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Agent-Merge-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..93ec833 --- /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-Agent-Merge.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Agent-Merge.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Agent-Merge.IQ4_XS.gguf b/Llama-Agent-Merge.IQ4_XS.gguf new file mode 100644 index 0000000..ecda256 --- /dev/null +++ b/Llama-Agent-Merge.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac7e55c13e63bd8a5cb6b020b2dc3387d7bb2ed3b9069be7bb64ec779db2d4e +size 1840908800 diff --git a/Llama-Agent-Merge.Q2_K.gguf b/Llama-Agent-Merge.Q2_K.gguf new file mode 100644 index 0000000..aeb7e0b --- /dev/null +++ b/Llama-Agent-Merge.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459e31f8be0656e43b6c5e79df50378a00065612fb62c3477d102eadd903a6f2 +size 1363937792 diff --git a/Llama-Agent-Merge.Q3_K_L.gguf b/Llama-Agent-Merge.Q3_K_L.gguf new file mode 100644 index 0000000..db143da --- /dev/null +++ b/Llama-Agent-Merge.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41117761b178c445d990db57c3b90b4eb4674f4cf5f43449edc26d0e883d2e17 +size 1815349760 diff --git a/Llama-Agent-Merge.Q3_K_M.gguf b/Llama-Agent-Merge.Q3_K_M.gguf new file mode 100644 index 0000000..453e92d --- /dev/null +++ b/Llama-Agent-Merge.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:413668c1c10e7720a79e87228081a76bad8b0a5e07a9eda5681cb712496f59bd +size 1687161344 diff --git a/Llama-Agent-Merge.Q3_K_S.gguf b/Llama-Agent-Merge.Q3_K_S.gguf new file mode 100644 index 0000000..2ea1969 --- /dev/null +++ b/Llama-Agent-Merge.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09211950ff4bfbe36379a32932b36620214328519eb2e540e63eaa9d0f237ad0 +size 1542851072 diff --git a/Llama-Agent-Merge.Q4_K_M.gguf b/Llama-Agent-Merge.Q4_K_M.gguf new file mode 100644 index 0000000..cb9ac07 --- /dev/null +++ b/Llama-Agent-Merge.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119fec4803fe81590c900cb1269b2573a61c74fb4f30d53dfab7d46b5fadd36c +size 2019379712 diff --git a/Llama-Agent-Merge.Q4_K_S.gguf b/Llama-Agent-Merge.Q4_K_S.gguf new file mode 100644 index 0000000..3feb010 --- /dev/null +++ b/Llama-Agent-Merge.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6173c589fbe1a93f06d243faf70fc4d703665dfaf89708b47dde252c2a7f4634 +size 1928202752 diff --git a/Llama-Agent-Merge.Q5_K_M.gguf b/Llama-Agent-Merge.Q5_K_M.gguf new file mode 100644 index 0000000..b6e5026 --- /dev/null +++ b/Llama-Agent-Merge.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec7101573f1e31120628f98cb3a402828b3f810929a7bb80b4eecd78fc0eb04 +size 2322156032 diff --git a/Llama-Agent-Merge.Q5_K_S.gguf b/Llama-Agent-Merge.Q5_K_S.gguf new file mode 100644 index 0000000..12b733d --- /dev/null +++ b/Llama-Agent-Merge.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fbfa542d59e203e4b3ee5ade80e05242b8b70ad45246c1af23142dae6a02405 +size 2269514240 diff --git a/Llama-Agent-Merge.Q6_K.gguf b/Llama-Agent-Merge.Q6_K.gguf new file mode 100644 index 0000000..f591858 --- /dev/null +++ b/Llama-Agent-Merge.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8429fa842560faf32546401b1a4b8119f8fad7b070917190018d0c86be51ee63 +size 2643855872 diff --git a/Llama-Agent-Merge.Q8_0.gguf b/Llama-Agent-Merge.Q8_0.gguf new file mode 100644 index 0000000..0c39c8a --- /dev/null +++ b/Llama-Agent-Merge.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77db54a32ece8238b709dcd212602d25eddf2203d9b8c5b4be65e3c2358b2430 +size 3421901312 diff --git a/Llama-Agent-Merge.f16.gguf b/Llama-Agent-Merge.f16.gguf new file mode 100644 index 0000000..3bac9b4 --- /dev/null +++ b/Llama-Agent-Merge.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8ebe4a6d7aa70ba37fdaf430c5ef28402107d8604cb2c633e6908dd840f28ec +size 6433690112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6f439ca --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Gunulhona/Llama-Agent-Merge +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Gunulhona/Llama-Agent-Merge + + +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-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Agent-Merge-GGUF/resolve/main/Llama-Agent-Merge.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. + +