commit f7bab836a570d7c01f77b3c0957dd7d33ac095f7 Author: ModelHub XC Date: Wed Sep 30 16:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-coedit-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..140a22d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-3.2-1B-coedit.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-coedit.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-coedit.IQ3_M.gguf b/Llama-3.2-1B-coedit.IQ3_M.gguf new file mode 100644 index 0000000..ff58f55 --- /dev/null +++ b/Llama-3.2-1B-coedit.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1446a679c9d8790cad4e4ff2306ecb0e8d47fc21ad1d0080af9e081db99fcbb +size 657285472 diff --git a/Llama-3.2-1B-coedit.IQ3_S.gguf b/Llama-3.2-1B-coedit.IQ3_S.gguf new file mode 100644 index 0000000..b804acc --- /dev/null +++ b/Llama-3.2-1B-coedit.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ff9b20e582f01dde1a63e5fae7e1d05ea4ee91184e23b689b35e3348c7bfd4 +size 643916128 diff --git a/Llama-3.2-1B-coedit.IQ3_XS.gguf b/Llama-3.2-1B-coedit.IQ3_XS.gguf new file mode 100644 index 0000000..eeb353e --- /dev/null +++ b/Llama-3.2-1B-coedit.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c6150727cfddeb656c7e2c24d8d71c61248632aa52be7038cac67578bc7682e +size 621109600 diff --git a/Llama-3.2-1B-coedit.IQ4_XS.gguf b/Llama-3.2-1B-coedit.IQ4_XS.gguf new file mode 100644 index 0000000..d0c6b44 --- /dev/null +++ b/Llama-3.2-1B-coedit.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28311da325d7e7530812129a93fba2c512d27059cf1ad4780c65806775d70687 +size 748380512 diff --git a/Llama-3.2-1B-coedit.Q2_K.gguf b/Llama-3.2-1B-coedit.Q2_K.gguf new file mode 100644 index 0000000..65f1db6 --- /dev/null +++ b/Llama-3.2-1B-coedit.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0936a997e6fc8d29f5a58f217f96fba455f078046a4c8f700a9382f7c9977f +size 580870496 diff --git a/Llama-3.2-1B-coedit.Q3_K_L.gguf b/Llama-3.2-1B-coedit.Q3_K_L.gguf new file mode 100644 index 0000000..ee481ac --- /dev/null +++ b/Llama-3.2-1B-coedit.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356a51bc23780b6e482720086d523ce8adc46f62e70eb70d407d2bc5e2cff4c0 +size 732520800 diff --git a/Llama-3.2-1B-coedit.Q3_K_M.gguf b/Llama-3.2-1B-coedit.Q3_K_M.gguf new file mode 100644 index 0000000..c460196 --- /dev/null +++ b/Llama-3.2-1B-coedit.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d00dd6012dc91e5746397a0616ba7b2bd862d1b49838c73bcb3799ae32633855 +size 690839904 diff --git a/Llama-3.2-1B-coedit.Q3_K_S.gguf b/Llama-3.2-1B-coedit.Q3_K_S.gguf new file mode 100644 index 0000000..d169eb7 --- /dev/null +++ b/Llama-3.2-1B-coedit.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378eed7d124dd6ca34a7a71f39b4acf60dc506c7e91c6bbf0a236effa4190ea0 +size 641687904 diff --git a/Llama-3.2-1B-coedit.Q4_K_M.gguf b/Llama-3.2-1B-coedit.Q4_K_M.gguf new file mode 100644 index 0000000..086fe45 --- /dev/null +++ b/Llama-3.2-1B-coedit.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2338d97b2a7a4408d8bb0d6dcb6f0fa7929aa32667795dc8a2d3a8a1387c4dd1 +size 807690592 diff --git a/Llama-3.2-1B-coedit.Q4_K_S.gguf b/Llama-3.2-1B-coedit.Q4_K_S.gguf new file mode 100644 index 0000000..e3de345 --- /dev/null +++ b/Llama-3.2-1B-coedit.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99e8e10624e3cb9cd12dce476f23b1120e497f4797dc13da1fc5b6e68b8aa2e8 +size 775643488 diff --git a/Llama-3.2-1B-coedit.Q5_K_M.gguf b/Llama-3.2-1B-coedit.Q5_K_M.gguf new file mode 100644 index 0000000..07c7939 --- /dev/null +++ b/Llama-3.2-1B-coedit.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b830ce621d1363e847de05baafb3c6a5446fe2b5c2ae102e3b9a8777cc09c50 +size 911499616 diff --git a/Llama-3.2-1B-coedit.Q5_K_S.gguf b/Llama-3.2-1B-coedit.Q5_K_S.gguf new file mode 100644 index 0000000..7c340c4 --- /dev/null +++ b/Llama-3.2-1B-coedit.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b2e8656e4ea94f9e27f6e97c6fd45c79f0adc8f64cc710421ecdbb975c02ba +size 892559712 diff --git a/Llama-3.2-1B-coedit.Q6_K.gguf b/Llama-3.2-1B-coedit.Q6_K.gguf new file mode 100644 index 0000000..135082e --- /dev/null +++ b/Llama-3.2-1B-coedit.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa482ea311dea33d13ec51e6bcf4105b81c46fd7d8d3678c76eb2a2507b2b74 +size 1021796704 diff --git a/Llama-3.2-1B-coedit.Q8_0.gguf b/Llama-3.2-1B-coedit.Q8_0.gguf new file mode 100644 index 0000000..109a5af --- /dev/null +++ b/Llama-3.2-1B-coedit.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75dbc50727b9d3c537fa49254e5232e47adca9ca4127d2334237a366e0bd1972 +size 1321079136 diff --git a/Llama-3.2-1B-coedit.f16.gguf b/Llama-3.2-1B-coedit.f16.gguf new file mode 100644 index 0000000..cc23012 --- /dev/null +++ b/Llama-3.2-1B-coedit.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ca37fbc9739f5a7dfab4aac98d0b839f979399f5fc87ef7b77175ced251bb7 +size 2479591776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..395adc3 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: orankhu/Llama-3.2-1B-coedit +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +--- +## About + + + + + + +static quants of https://huggingface.co/orankhu/Llama-3.2-1B-coedit + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-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/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.IQ3_XS.gguf) | IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.IQ3_S.gguf) | IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.IQ3_M.gguf) | IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-coedit-GGUF/resolve/main/Llama-3.2-1B-coedit.f16.gguf) | f16 | 2.6 | 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. + +