commit 0f81806713e2dd433ddfc3215bf0a72f1d10d89a Author: ModelHub XC Date: Mon Apr 27 12:42:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cce1440 --- /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-warmup-GSM8k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-7b-hf-SFT-warmup-GSM8k.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.IQ4_XS.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.IQ4_XS.gguf new file mode 100644 index 0000000..2522c4d --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dccfd219a9a3ea330d4bb038815266f9c17300e26724003a5bef7bc1502a699c +size 3647606304 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q2_K.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q2_K.gguf new file mode 100644 index 0000000..05a7227 --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cfdf234ce0d7af3a11373257bda4b328d72d915f2fb546f11a75d33505f9c1f +size 2532940320 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_L.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_L.gguf new file mode 100644 index 0000000..5e755a3 --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ddd6fb040a2ae9c7a0f61ae21f5afd3f7371f87ddc2c75997f7a5fcf9cdcf08 +size 3597194272 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_M.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_M.gguf new file mode 100644 index 0000000..306d574 --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:664951c356001f3aaac4b8769136b652df722cceb737f7f86df4af06e4c53c0a +size 3298087968 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_S.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_S.gguf new file mode 100644 index 0000000..537ccca --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d704fa85b34ffdedc4d0264a7c4651c2ba3a7c7880fffbf711afdb6090992ec +size 2948387872 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_0_4_4.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_0_4_4.gguf new file mode 100644 index 0000000..43b93df --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5295ad4f02b966535d68e53ff442ba69d38153cb6a16d47b3f7ac1d9abd9ffbe +size 3825899040 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_M.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_M.gguf new file mode 100644 index 0000000..167f5ae --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a13b64782a5ccacf0f300ae2d3e2ba1164be95ff04df7fd93b0e1cf2e8f5533 +size 4081096224 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_S.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_S.gguf new file mode 100644 index 0000000..7271faa --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da1fb9b7357f75a122ce4ce8cf16334fdf87666ec0a10f80174e20b187b3f87 +size 3856832032 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_M.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_M.gguf new file mode 100644 index 0000000..9564d58 --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41acb060d8a316787bb8d2ec17b027f00a54526ed1bba0726e7453c6d603694d +size 4783257120 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_S.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_S.gguf new file mode 100644 index 0000000..9706bed --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9edf0a21b27a851551a5fd1f3ca6ea603a990b4910367891f25aa26f6ba278 +size 4651791904 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q6_K.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q6_K.gguf new file mode 100644 index 0000000..3dcceec --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7717dd3d88e385fa12135a8d66d33fb55994eb3872455a77c9f63f8f2feb02e +size 5529303072 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.Q8_0.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.Q8_0.gguf new file mode 100644 index 0000000..14455f2 --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0178391fd8a3ef10b5a6e883d1c5c6a3a0b658b4629c090b8dde10113319fb6f +size 7161230368 diff --git a/Codellama-7b-hf-SFT-warmup-GSM8k.f16.gguf b/Codellama-7b-hf-SFT-warmup-GSM8k.f16.gguf new file mode 100644 index 0000000..dac0278 --- /dev/null +++ b/Codellama-7b-hf-SFT-warmup-GSM8k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcfdf1bd3bfcee99e5b3dcd7f56d21807385ca57ae569ab1759c086339e5b2c4 +size 13478368288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..34ef982 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: lqtrung1998/Codellama-7b-hf-SFT-warmup-GSM8k +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lqtrung1998/Codellama-7b-hf-SFT-warmup-GSM8k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-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-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-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-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-GSM8k.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-7b-hf-SFT-warmup-GSM8k-GGUF/resolve/main/Codellama-7b-hf-SFT-warmup-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. + +