commit 02dbd30883a839818817d5ae40e0fc33e4aca547 Author: ModelHub XC Date: Mon Jul 6 20:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ahma-2-4B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7bb6998 --- /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 +Ahma-2-4B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ahma-2-4B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ahma-2-4B-Instruct.IQ4_XS.gguf b/Ahma-2-4B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..903f665 --- /dev/null +++ b/Ahma-2-4B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cf143eece24ce7951adf072884b5ca0c2e3a5103be3d61b1bba718ab86991d1 +size 2279490016 diff --git a/Ahma-2-4B-Instruct.Q2_K.gguf b/Ahma-2-4B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..0247b36 --- /dev/null +++ b/Ahma-2-4B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456daeeb77bac618bbb5ad6ce071ccb10faa278957fe5c09feb5348c533bfbba +size 1729028576 diff --git a/Ahma-2-4B-Instruct.Q3_K_L.gguf b/Ahma-2-4B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..61e61ec --- /dev/null +++ b/Ahma-2-4B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ceec9ef32f4d5ad891d99b03a4694885bd63dcdeabe1e9db285c9f0546893c +size 2235949536 diff --git a/Ahma-2-4B-Instruct.Q3_K_M.gguf b/Ahma-2-4B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..328f1e2 --- /dev/null +++ b/Ahma-2-4B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9f36ccf2c87064b2fb5979fde3d2ed2e4c4c291817b22bb901e6b1bcc9e1b6 +size 2098323936 diff --git a/Ahma-2-4B-Instruct.Q3_K_S.gguf b/Ahma-2-4B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..779a6f6 --- /dev/null +++ b/Ahma-2-4B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ad0fe598d86ec5e04da473fbb5a7142a4bac107af519a44750b1029c0049dc +size 1937228256 diff --git a/Ahma-2-4B-Instruct.Q4_K_M.gguf b/Ahma-2-4B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..9751a96 --- /dev/null +++ b/Ahma-2-4B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4eee655333906fe4131a88f1e57e631e48b3e6fa10f14748ddb8daca2b63f95 +size 2489758176 diff --git a/Ahma-2-4B-Instruct.Q4_K_S.gguf b/Ahma-2-4B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..813e240 --- /dev/null +++ b/Ahma-2-4B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e855099574ccf3135e4ceb48fba146bbad58916e8578e44132a26dedb7c35da8 +size 2377794016 diff --git a/Ahma-2-4B-Instruct.Q5_K_M.gguf b/Ahma-2-4B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7afc6b3 --- /dev/null +++ b/Ahma-2-4B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:838f9987db001934fa1051642de11a9401c774ebab8bcc4eccfd99e5c262473b +size 2829562336 diff --git a/Ahma-2-4B-Instruct.Q5_K_S.gguf b/Ahma-2-4B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..b4248ee --- /dev/null +++ b/Ahma-2-4B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:054d2c2a4d231a57523ddff24660e0ce533412c842f1d0c296ca5f76720d6aad +size 2764456416 diff --git a/Ahma-2-4B-Instruct.Q6_K.gguf b/Ahma-2-4B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..98f81d3 --- /dev/null +++ b/Ahma-2-4B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a61b51b2e336f9274fe800c701cbe6b7c45ca90473ec499708dc2785cb62fc +size 3190604256 diff --git a/Ahma-2-4B-Instruct.Q8_0.gguf b/Ahma-2-4B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..2b910ad --- /dev/null +++ b/Ahma-2-4B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4341f993403dd983f362901aec401ffd4a5e5720f90064295cbd9d29a3e5eccb +size 4130226656 diff --git a/Ahma-2-4B-Instruct.f16.gguf b/Ahma-2-4B-Instruct.f16.gguf new file mode 100644 index 0000000..b68424b --- /dev/null +++ b/Ahma-2-4B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123e12f572c37c01eb5774ef8b3321b221fe680e5cce2386824c9eaafa346393 +size 7767474656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2aa21ee --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Finnish-NLP/Ahma-2-4B-Instruct +language: +- fi +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- finnish +- gemma +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Finnish-NLP/Ahma-2-4B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Ahma-2-4B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-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/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ahma-2-4B-Instruct-GGUF/resolve/main/Ahma-2-4B-Instruct.f16.gguf) | f16 | 7.9 | 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. + +