commit 688ccfd873fca8cb99f28d8f2b01cbfbf16404eb Author: ModelHub XC Date: Sat Aug 29 05:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ac8cdc3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Codellama-7b-hf-SFT-GSM8k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-GSM8k.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Codellama-7b-hf-SFT-GSM8k.IQ4_XS.gguf b/Codellama-7b-hf-SFT-GSM8k.IQ4_XS.gguf new file mode 100644 index 0000000..52b77ec --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74688c6aff3f21809fbddb5318d0300154f4138903631ed54d54f7d2082dbf6f +size 3647606272 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q2_K.gguf b/Codellama-7b-hf-SFT-GSM8k.Q2_K.gguf new file mode 100644 index 0000000..0977e4e --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395b343db81488eceb7e108549ebb51a59c9b9a720097cc8d671ff779667ce56 +size 2532940288 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q3_K_L.gguf b/Codellama-7b-hf-SFT-GSM8k.Q3_K_L.gguf new file mode 100644 index 0000000..8e35ec1 --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f92666ca7d1888f3647fdfbba8f8522e5571a1a34514b0021d1e98b118056e +size 3597194240 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q3_K_M.gguf b/Codellama-7b-hf-SFT-GSM8k.Q3_K_M.gguf new file mode 100644 index 0000000..ad7ccc0 --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef0f11d5c3b63ccedb199a3cfe787343afe9dfd8cdd22d2ddf52cff6d78dbaad +size 3298087936 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q3_K_S.gguf b/Codellama-7b-hf-SFT-GSM8k.Q3_K_S.gguf new file mode 100644 index 0000000..3c1c3f0 --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4864ade77b97dda34cc929f1bd0450ae2a60026bd69f93c1f75372ef10d4ca64 +size 2948387840 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q4_0_4_4.gguf b/Codellama-7b-hf-SFT-GSM8k.Q4_0_4_4.gguf new file mode 100644 index 0000000..744f758 --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb252df4e86d8e42c0022dfa0ee8bd9be31f89078e0537c05f9f3da8733fd40b +size 3825899008 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q4_K_M.gguf b/Codellama-7b-hf-SFT-GSM8k.Q4_K_M.gguf new file mode 100644 index 0000000..51271c3 --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27eba853ea9a667fc1e9d2b1cc4ba1bffcb815e313302bfce6e180aa156a3bda +size 4081096192 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q4_K_S.gguf b/Codellama-7b-hf-SFT-GSM8k.Q4_K_S.gguf new file mode 100644 index 0000000..f400aad --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142b1d70a3e9ff69d08639579bf0b4594ffa3f078549fb9d35efa4279a863e8d +size 3856832000 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q5_K_M.gguf b/Codellama-7b-hf-SFT-GSM8k.Q5_K_M.gguf new file mode 100644 index 0000000..ddd053d --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c832e1517c52b06d59a0acf23a2cc454d1919f82290280d8d349041918c22e7 +size 4783257088 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q5_K_S.gguf b/Codellama-7b-hf-SFT-GSM8k.Q5_K_S.gguf new file mode 100644 index 0000000..4cab180 --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade0760ee8ed9732143e04bc13b9c21e53561c14d46221a7b9eebdfab56ab053 +size 4651791872 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q6_K.gguf b/Codellama-7b-hf-SFT-GSM8k.Q6_K.gguf new file mode 100644 index 0000000..dc7b4ad --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc04473a6cf3f2455bdd890d293a251581db9809a2a44f3ced268124af5ffb4b +size 5529303040 diff --git a/Codellama-7b-hf-SFT-GSM8k.Q8_0.gguf b/Codellama-7b-hf-SFT-GSM8k.Q8_0.gguf new file mode 100644 index 0000000..eb6c64b --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6505b391325ce66dc56c9aa8c5bef5e0eed70d583c6c5f061c9139b1aca7527a +size 7161230336 diff --git a/Codellama-7b-hf-SFT-GSM8k.f16.gguf b/Codellama-7b-hf-SFT-GSM8k.f16.gguf new file mode 100644 index 0000000..6a21b27 --- /dev/null +++ b/Codellama-7b-hf-SFT-GSM8k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39f8432ac7f2a04dc6ad5f04b16aeb5a80837c277abc14e1c3d5890521d2f672 +size 13478368256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..587cf9c --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: lqtrung1998/Codellama-7b-hf-SFT-GSM8k +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lqtrung1998/Codellama-7b-hf-SFT-GSM8k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-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/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-GSM8k.f16.gguf) | f16 | 13.6 | 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. + +