commit c7df21baaca77814cbf8a2d2a60667b691cabd35 Author: ModelHub XC Date: Mon Jun 15 16:20:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hammer-4b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b5cc56c --- /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 +Hammer-4b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hammer-4b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hammer-4b.IQ4_XS.gguf b/Hammer-4b.IQ4_XS.gguf new file mode 100644 index 0000000..2768a53 --- /dev/null +++ b/Hammer-4b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09be08a53a84ec54beffcd60d6a625562252f7648b8e8f04f0c8b4c62dafce73 +size 2231622912 diff --git a/Hammer-4b.Q2_K.gguf b/Hammer-4b.Q2_K.gguf new file mode 100644 index 0000000..b1eb80b --- /dev/null +++ b/Hammer-4b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd1bafeaea8ffb0e6eccb87b0a8fbd3f2d5bb88056913abc50858d7456e18074 +size 1619775008 diff --git a/Hammer-4b.Q3_K_L.gguf b/Hammer-4b.Q3_K_L.gguf new file mode 100644 index 0000000..7c24226 --- /dev/null +++ b/Hammer-4b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60ae331c4a5ed433ff08120b87543daebd5665777fba93eabfc587bbcc33da28 +size 2173865376 diff --git a/Hammer-4b.Q3_K_M.gguf b/Hammer-4b.Q3_K_M.gguf new file mode 100644 index 0000000..b6e4bdd --- /dev/null +++ b/Hammer-4b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1105a89bf16c981b26371584111732e1aaa350f5803c8e42d0a9173678b87fe +size 2025917856 diff --git a/Hammer-4b.Q3_K_S.gguf b/Hammer-4b.Q3_K_S.gguf new file mode 100644 index 0000000..2f1261f --- /dev/null +++ b/Hammer-4b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4385bb33ab30dcc095a28eb0714f2da65c0471e0e1430401ce031efb146991d +size 1856220576 diff --git a/Hammer-4b.Q4_K_M.gguf b/Hammer-4b.Q4_K_M.gguf new file mode 100644 index 0000000..86d8fd7 --- /dev/null +++ b/Hammer-4b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a72ea7f62eb870d3dcefabafd80b28c60cef9cc4d9e117da902b33e9f249c5 +size 2454084192 diff --git a/Hammer-4b.Q4_K_S.gguf b/Hammer-4b.Q4_K_S.gguf new file mode 100644 index 0000000..4ec9237 --- /dev/null +++ b/Hammer-4b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744dfdf347fb980e4ff74a327b54fd7270f9be08e4b5be0344dd2e206d9317ba +size 2343389792 diff --git a/Hammer-4b.Q5_K_M.gguf b/Hammer-4b.Q5_K_M.gguf new file mode 100644 index 0000000..1c6d0e7 --- /dev/null +++ b/Hammer-4b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84eb989e9ad6e38fffb7bfe4ac3e1505dfcb2b6bca2ed1ff5e20b37a0cd1011b +size 2838482912 diff --git a/Hammer-4b.Q5_K_S.gguf b/Hammer-4b.Q5_K_S.gguf new file mode 100644 index 0000000..a2cfcbc --- /dev/null +++ b/Hammer-4b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7904bc4303d47318da3a2ef5a51fcc8e3c419eb4dac49f97ecd4c2323ad9838 +size 2774073312 diff --git a/Hammer-4b.Q6_K.gguf b/Hammer-4b.Q6_K.gguf new file mode 100644 index 0000000..27d4435 --- /dev/null +++ b/Hammer-4b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6167e99352a70ef2f8143e0c11150359ea3de82bdb73b7dc536154bffd987057 +size 3246906560 diff --git a/Hammer-4b.Q8_0.gguf b/Hammer-4b.Q8_0.gguf new file mode 100644 index 0000000..94c09b4 --- /dev/null +++ b/Hammer-4b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2316ee04985e3b3dc60891113e79bab240becca8f29a5fed0b24df3a1a9647ad +size 4203152384 diff --git a/Hammer-4b.f16.gguf b/Hammer-4b.f16.gguf new file mode 100644 index 0000000..39d406f --- /dev/null +++ b/Hammer-4b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b696814a20bc16f5f36d9eb88b597aabb60e6b9939e9b6372595b5dee43227 +size 7904749184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..945ea85 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: MadeAgents/Hammer-4b +datasets: +- Salesforce/xlam-function-calling-60k +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen1.5-4B-Chat/blob/main/LICENSE +license_name: tongyi-qianwen-research +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/MadeAgents/Hammer-4b + + +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/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q2_K.gguf) | Q2_K | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hammer-4b-GGUF/resolve/main/Hammer-4b.f16.gguf) | f16 | 8.0 | 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. + +