commit 6ae3a08c494739c543eddd4d428c47b1a35558a7 Author: ModelHub XC Date: Thu Oct 8 06:03:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InterviewMaster-Llama3.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1e7301f --- /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 +InterviewMaster-Llama3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InterviewMaster-Llama3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InterviewMaster-Llama3.1.IQ4_XS.gguf b/InterviewMaster-Llama3.1.IQ4_XS.gguf new file mode 100644 index 0000000..92ba5d3 --- /dev/null +++ b/InterviewMaster-Llama3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfe463b3e6145cb5336808c4611ebe008738e94d79a596962ee5f0782c96b47 +size 4484363616 diff --git a/InterviewMaster-Llama3.1.Q2_K.gguf b/InterviewMaster-Llama3.1.Q2_K.gguf new file mode 100644 index 0000000..33da09e --- /dev/null +++ b/InterviewMaster-Llama3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60663738ae4b3a4fc9fa58dd7cf9d2f391c550ffcaa62c2aafe7f9437098a77 +size 3179132256 diff --git a/InterviewMaster-Llama3.1.Q3_K_L.gguf b/InterviewMaster-Llama3.1.Q3_K_L.gguf new file mode 100644 index 0000000..d16b6ae --- /dev/null +++ b/InterviewMaster-Llama3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d79d88c7215260624fb39ff41270083cbf86c80ee7031383969154c017ea67b2 +size 4321957216 diff --git a/InterviewMaster-Llama3.1.Q3_K_M.gguf b/InterviewMaster-Llama3.1.Q3_K_M.gguf new file mode 100644 index 0000000..553a81e --- /dev/null +++ b/InterviewMaster-Llama3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b17cddf176c1050545b42a169eccdc9b0998a0423a72f703dfe6957a0d743d +size 4018918752 diff --git a/InterviewMaster-Llama3.1.Q3_K_S.gguf b/InterviewMaster-Llama3.1.Q3_K_S.gguf new file mode 100644 index 0000000..0de4e6b --- /dev/null +++ b/InterviewMaster-Llama3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b76e8c2f3816906d60128a4faeda274143ae6ebde3c010142d782de779ae362 +size 3664500064 diff --git a/InterviewMaster-Llama3.1.Q4_K_M.gguf b/InterviewMaster-Llama3.1.Q4_K_M.gguf new file mode 100644 index 0000000..f1087f1 --- /dev/null +++ b/InterviewMaster-Llama3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bfcacf151585eea760015a4ab5e720421549b3c6b0f7a87410f7cef18c50cff +size 4920735072 diff --git a/InterviewMaster-Llama3.1.Q4_K_S.gguf b/InterviewMaster-Llama3.1.Q4_K_S.gguf new file mode 100644 index 0000000..6b166e3 --- /dev/null +++ b/InterviewMaster-Llama3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06a4bc819cee5b193c46682875b3536f04ad5154b4d4cad111c673a8bf4af154 +size 4692669792 diff --git a/InterviewMaster-Llama3.1.Q5_K_M.gguf b/InterviewMaster-Llama3.1.Q5_K_M.gguf new file mode 100644 index 0000000..6a4944c --- /dev/null +++ b/InterviewMaster-Llama3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e981ff3fc41e1024d152aa44c031801beac85e9e6e9f01bb8f1b4c674c77842 +size 5732988256 diff --git a/InterviewMaster-Llama3.1.Q5_K_S.gguf b/InterviewMaster-Llama3.1.Q5_K_S.gguf new file mode 100644 index 0000000..5c2ba70 --- /dev/null +++ b/InterviewMaster-Llama3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbf2127da54fe84552b410646cb596ddabd211fefbed1aac0bcf875b655773c +size 5599294816 diff --git a/InterviewMaster-Llama3.1.Q6_K.gguf b/InterviewMaster-Llama3.1.Q6_K.gguf new file mode 100644 index 0000000..affe434 --- /dev/null +++ b/InterviewMaster-Llama3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebc4e37a9de6c0a2d28f8b5fe0cacf1ec1d61040bd2d2b5596b2c46f70ae67a4 +size 6596007264 diff --git a/InterviewMaster-Llama3.1.Q8_0.gguf b/InterviewMaster-Llama3.1.Q8_0.gguf new file mode 100644 index 0000000..5343b99 --- /dev/null +++ b/InterviewMaster-Llama3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f88d7bf70d5d0cc11b7fd1feb2e5983aa6ec343d928decdf72f2f3f084bca3b +size 8540771680 diff --git a/InterviewMaster-Llama3.1.f16.gguf b/InterviewMaster-Llama3.1.f16.gguf new file mode 100644 index 0000000..a3d3d4f --- /dev/null +++ b/InterviewMaster-Llama3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04e19b37dc669ffedcd007acf3eddae0ed4be1973a587929821ddc52a77419f +size 16068892000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..86c8188 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Vijay3548/InterviewMaster-Llama3.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Vijay3548/InterviewMaster-Llama3.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InterviewMaster-Llama3.1-GGUF).*** + +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/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InterviewMaster-Llama3.1-GGUF/resolve/main/InterviewMaster-Llama3.1.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. + +