commit cf00acede2be6157440e457de8630ae9b7bc71a2 Author: ModelHub XC Date: Mon Jul 6 08:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33611b9 --- /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 +llama-3.1-8B-icd10-codeinstruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-icd10-codeinstruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2899c9b --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Shaleen123/llama-3.1-8B-icd10-codeinstruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Shaleen123/llama-3.1-8B-icd10-codeinstruct + + +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/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-icd10-codeinstruct-GGUF/resolve/main/llama-3.1-8B-icd10-codeinstruct.f16.gguf) | f16 | 16.2 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/llama-3.1-8B-icd10-codeinstruct.IQ4_XS.gguf b/llama-3.1-8B-icd10-codeinstruct.IQ4_XS.gguf new file mode 100644 index 0000000..6564ed8 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e44a36d540c79a391e75e4ecde9f9056a9a4599bd73b8627312918f5255c413 +size 4484367808 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q2_K.gguf b/llama-3.1-8B-icd10-codeinstruct.Q2_K.gguf new file mode 100644 index 0000000..bf21f43 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3567f76c58aead2a1f076ab5242cade304335975910129d5365afd7bb74a6c5 +size 3179136448 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q3_K_L.gguf b/llama-3.1-8B-icd10-codeinstruct.Q3_K_L.gguf new file mode 100644 index 0000000..f9faac8 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385bfeaefbef44b12e38cfca46255c11e3893bc0988b8d8e86ba899c47731d72 +size 4321961408 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q3_K_M.gguf b/llama-3.1-8B-icd10-codeinstruct.Q3_K_M.gguf new file mode 100644 index 0000000..aab5b76 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a2a57bed5389c68fdea0e584b0b80ccd9c77880b3a9e6ba1f68a88aab83d12 +size 4018922944 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q3_K_S.gguf b/llama-3.1-8B-icd10-codeinstruct.Q3_K_S.gguf new file mode 100644 index 0000000..4c1f078 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acb6a30178abfcfc351093c95b281279b75fc87de05cea4672aecf6d140ffdd7 +size 3664504256 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q4_0_4_4.gguf b/llama-3.1-8B-icd10-codeinstruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..f100382 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48fa937d967dd578c491d8d11fc23ff9c14145b3272286640614030cebfb384a +size 4661216704 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q4_K_M.gguf b/llama-3.1-8B-icd10-codeinstruct.Q4_K_M.gguf new file mode 100644 index 0000000..82ecb0c --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ffaa1512135b622cb5dac40364e5e4dea3027aea1aa16c9e08e4ff0b8be5d07 +size 4920739264 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q4_K_S.gguf b/llama-3.1-8B-icd10-codeinstruct.Q4_K_S.gguf new file mode 100644 index 0000000..1cefc7e --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66918c7d40b9f3d77689df04e47108a6dbb30ba33ccbb314250e0587eb4525d1 +size 4692673984 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q5_K_M.gguf b/llama-3.1-8B-icd10-codeinstruct.Q5_K_M.gguf new file mode 100644 index 0000000..ed963de --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19cc5d7bf797de2fb76a184174bf9ec64da4215f984773641e3ede1e54aed28 +size 5732992448 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q5_K_S.gguf b/llama-3.1-8B-icd10-codeinstruct.Q5_K_S.gguf new file mode 100644 index 0000000..3849259 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bee949149ee29151297810afa003ac9c0871bb956af1a9bb1d7c2ca276de842 +size 5599299008 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q6_K.gguf b/llama-3.1-8B-icd10-codeinstruct.Q6_K.gguf new file mode 100644 index 0000000..d54fca5 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b0d3c2bd851e10a85428aa59ef36d5d058f34a61551a83e90fdb5cfe2cb3392 +size 6596011456 diff --git a/llama-3.1-8B-icd10-codeinstruct.Q8_0.gguf b/llama-3.1-8B-icd10-codeinstruct.Q8_0.gguf new file mode 100644 index 0000000..358ae99 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6f24eb0dd17fc1bcc078f49f8796e0b001fd60cbc6f46aee73a02b51df2911a +size 8540775872 diff --git a/llama-3.1-8B-icd10-codeinstruct.f16.gguf b/llama-3.1-8B-icd10-codeinstruct.f16.gguf new file mode 100644 index 0000000..1f0dfe8 --- /dev/null +++ b/llama-3.1-8B-icd10-codeinstruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8624ba357e20ba7173f4eb967108050f4b2ca815d950c37ff1b659bcc56a30d5 +size 16068896192