commit 299cd3acaf190bfc3737a8d9326538b8649b11f9 Author: ModelHub XC Date: Wed Apr 22 01:38:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Humanish-LLama3-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..65060b4 --- /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 +Humanish-LLama3-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Humanish-LLama3-8B-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Humanish-LLama3-8B-Instruct.IQ4_XS.gguf b/Humanish-LLama3-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..88f99f5 --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccff226bc1a744e5b978a9d97cfb9d3576ed001ebb66530b7ea378d1bf9c6ec8 +size 4484364128 diff --git a/Humanish-LLama3-8B-Instruct.Q2_K.gguf b/Humanish-LLama3-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..ba25817 --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056c5a3948fcb321e0b982438b21f8ffdf52ec25996e81f297cc694b11a75f82 +size 3179132768 diff --git a/Humanish-LLama3-8B-Instruct.Q3_K_L.gguf b/Humanish-LLama3-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..7434f6c --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72ddf9113b92df24a96c2919089ccd15ee1a14e60a9aab5073392998fd874d2b +size 4321957728 diff --git a/Humanish-LLama3-8B-Instruct.Q3_K_M.gguf b/Humanish-LLama3-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..973f050 --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e986471b84a1a4d05240f9285915f15478e5e651eccfbb88c0c5c5f9b74f3912 +size 4018919264 diff --git a/Humanish-LLama3-8B-Instruct.Q3_K_S.gguf b/Humanish-LLama3-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..61ffb52 --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ce3b5854240fbf7f200d955272e8dde209e83e58da07253de48bce5939592e +size 3664500576 diff --git a/Humanish-LLama3-8B-Instruct.Q4_0_4_4.gguf b/Humanish-LLama3-8B-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..83057e4 --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0250371cc833ee89496ad97c0d5eea48b3cd5f5fcfd4d3366c837c624fbd9603 +size 4661213024 diff --git a/Humanish-LLama3-8B-Instruct.Q4_K_M.gguf b/Humanish-LLama3-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..ab9d44e --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f62bcf47a899e825dad6e32e2ccbde2d77e8c3fd4d5d046fda94e2ea9b8df94d +size 4920735584 diff --git a/Humanish-LLama3-8B-Instruct.Q4_K_S.gguf b/Humanish-LLama3-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..b1160e7 --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:766ad7d6b1b8ed8582f5026aee09c30477074469b3ed004a92cc57cc980d10cb +size 4692670304 diff --git a/Humanish-LLama3-8B-Instruct.Q5_K_M.gguf b/Humanish-LLama3-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..c093a4c --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b32890609c5f82e1697b450bc306a90a513e64d5f9443be20bd46b1426a3f25 +size 5732988768 diff --git a/Humanish-LLama3-8B-Instruct.Q5_K_S.gguf b/Humanish-LLama3-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..3625990 --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b4813f3642a0d578316676144b0fe340e749181017c2c6801fd866fb81cc31 +size 5599295328 diff --git a/Humanish-LLama3-8B-Instruct.Q6_K.gguf b/Humanish-LLama3-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..17327e7 --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c2155de9d67bb083fa1c26e1c4d245d7f787edd6e2b0e7d6f8c10ab6aa2ac4 +size 6596007776 diff --git a/Humanish-LLama3-8B-Instruct.Q8_0.gguf b/Humanish-LLama3-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..17238fe --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2bbc6fd503884958d0dd8db026d08282208d48110623cefb4043292e6e3e8e6 +size 8540772192 diff --git a/Humanish-LLama3-8B-Instruct.f16.gguf b/Humanish-LLama3-8B-Instruct.f16.gguf new file mode 100644 index 0000000..9ff527f --- /dev/null +++ b/Humanish-LLama3-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81daaa6e23573422991fa8d4ec916bf4a9405dd0843dafae4a5631908d24de30 +size 16068892512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..82ebc27 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: HumanLLMs/Human-Like-LLama3-8B-Instruct +datasets: +- HumanLLMs/Human-Like-DPO-Dataset +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- axolotl +- dpo +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/HumanLLMs/Human-Like-LLama3-8B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-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/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Humanish-LLama3-8B-Instruct-GGUF/resolve/main/Humanish-LLama3-8B-Instruct.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. + +