commit 0cf47438e47de9d7761275e0cd0dbcc8e336e42b Author: ModelHub XC Date: Sat May 30 21:55:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7cf2336 --- /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 +doctor-meta-llama-3-8B-1-lora.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.f16.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +doctor-meta-llama-3-8B-1-lora.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3123c20 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: cello78/doctor-meta-llama-3-8B-1-lora +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/cello78/doctor-meta-llama-3-8B-1-lora + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#doctor-meta-llama-3-8B-1-lora-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/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/doctor-meta-llama-3-8B-1-lora-GGUF/resolve/main/doctor-meta-llama-3-8B-1-lora.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. + + diff --git a/doctor-meta-llama-3-8B-1-lora.IQ4_XS.gguf b/doctor-meta-llama-3-8B-1-lora.IQ4_XS.gguf new file mode 100644 index 0000000..c078f00 --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc5481366f7f67176949e24fb8a9c6e31311ca127d4c32a6a0f1d74f4df7dfed +size 4484363456 diff --git a/doctor-meta-llama-3-8B-1-lora.Q2_K.gguf b/doctor-meta-llama-3-8B-1-lora.Q2_K.gguf new file mode 100644 index 0000000..503757b --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e0a568edce3afbb294cc522ab3061c280b61bcc7f4b079ff06c79e8daa69b0 +size 3179132096 diff --git a/doctor-meta-llama-3-8B-1-lora.Q3_K_L.gguf b/doctor-meta-llama-3-8B-1-lora.Q3_K_L.gguf new file mode 100644 index 0000000..8731d79 --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f42ca6a31d31be8290ed5c98a1d7dddf6a4a2d266b72a0dafbf9de2d96401b3 +size 4321957056 diff --git a/doctor-meta-llama-3-8B-1-lora.Q3_K_M.gguf b/doctor-meta-llama-3-8B-1-lora.Q3_K_M.gguf new file mode 100644 index 0000000..4a49e03 --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c727c9faeb9db5258ec9883777641a8c0777cc901e3d75258c0ce32504d5009d +size 4018918592 diff --git a/doctor-meta-llama-3-8B-1-lora.Q3_K_S.gguf b/doctor-meta-llama-3-8B-1-lora.Q3_K_S.gguf new file mode 100644 index 0000000..68fb91e --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c88725b062c5effc2f242cf7e1a07e56e179fb969b63a82578102f418421239 +size 3664499904 diff --git a/doctor-meta-llama-3-8B-1-lora.Q4_K_M.gguf b/doctor-meta-llama-3-8B-1-lora.Q4_K_M.gguf new file mode 100644 index 0000000..e38e1f8 --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42044c578863155bda91ee9f5a62b59672f1128e9a2499147d9fec2be29bbe42 +size 4920734912 diff --git a/doctor-meta-llama-3-8B-1-lora.Q4_K_S.gguf b/doctor-meta-llama-3-8B-1-lora.Q4_K_S.gguf new file mode 100644 index 0000000..d35e51a --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c8530b2266a62ac96a0f8a08a01d6aa6fe8c4cfd3186eda46b49dce46645d5 +size 4692669632 diff --git a/doctor-meta-llama-3-8B-1-lora.Q5_K_M.gguf b/doctor-meta-llama-3-8B-1-lora.Q5_K_M.gguf new file mode 100644 index 0000000..a13cb49 --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5cb805e644875ae0fff80c6d32e235d42f2abb929480840b75cfa5f4487c07 +size 5732988096 diff --git a/doctor-meta-llama-3-8B-1-lora.Q5_K_S.gguf b/doctor-meta-llama-3-8B-1-lora.Q5_K_S.gguf new file mode 100644 index 0000000..25d9cf8 --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0211ac2002c56ce604626238b5e54e1d35a565e38337f5a8971d0d091e092720 +size 5599294656 diff --git a/doctor-meta-llama-3-8B-1-lora.Q6_K.gguf b/doctor-meta-llama-3-8B-1-lora.Q6_K.gguf new file mode 100644 index 0000000..b2255ae --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12314caf424363bb22678d668204e245a55d11d6b9086ce5999e429d9a2c986 +size 6596007104 diff --git a/doctor-meta-llama-3-8B-1-lora.Q8_0.gguf b/doctor-meta-llama-3-8B-1-lora.Q8_0.gguf new file mode 100644 index 0000000..e3a42da --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b63cb12f7263ae3025578a474700811620605a84f94d001761acb30e405d99 +size 8540771520 diff --git a/doctor-meta-llama-3-8B-1-lora.f16.gguf b/doctor-meta-llama-3-8B-1-lora.f16.gguf new file mode 100644 index 0000000..da60771 --- /dev/null +++ b/doctor-meta-llama-3-8B-1-lora.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:152ba60b766e7d9acd7647d906950f7f6826fe309ebc947697028ab46f621f7d +size 16068891840