commit 46a562960e179bae43aaa521405b2c78a1d0880a Author: ModelHub XC Date: Sat Apr 11 01:46:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Medichat-Llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bad0f78 --- /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 +Medichat-Llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medichat-Llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Medichat-Llama3-8B.IQ4_XS.gguf b/Medichat-Llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..2e31015 --- /dev/null +++ b/Medichat-Llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2695fc63d9594019374bc1f076045da6d6f77548b662b070a6157df6adf7fef +size 4484366080 diff --git a/Medichat-Llama3-8B.Q2_K.gguf b/Medichat-Llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..88fa2bb --- /dev/null +++ b/Medichat-Llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d296c17f8420db6c55558e48379bbdee7784edfaf93de5d4b877aabd2e70ff +size 3179134720 diff --git a/Medichat-Llama3-8B.Q3_K_L.gguf b/Medichat-Llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..33d14e1 --- /dev/null +++ b/Medichat-Llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54446e4e90f6de3b3f4dbf87756075f73c77f0d9da4066d5773636d734b552d9 +size 4321959680 diff --git a/Medichat-Llama3-8B.Q3_K_M.gguf b/Medichat-Llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..8a93d35 --- /dev/null +++ b/Medichat-Llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65dac55f1b01eac5d3d21ab53e43109ce35a03ba895f79adaf98f840465485f +size 4018921216 diff --git a/Medichat-Llama3-8B.Q3_K_S.gguf b/Medichat-Llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..1bf7633 --- /dev/null +++ b/Medichat-Llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d31de6f7335051e0193d120e298ca11696516c1a160951095328b6ccc6957c35 +size 3664502528 diff --git a/Medichat-Llama3-8B.Q4_K_M.gguf b/Medichat-Llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..5711bd2 --- /dev/null +++ b/Medichat-Llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464a97ca81a344e375fd76f6ef96a6025ae265eaa16d3354001891f26cf7348f +size 4920737536 diff --git a/Medichat-Llama3-8B.Q4_K_S.gguf b/Medichat-Llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..0ae36ab --- /dev/null +++ b/Medichat-Llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ceeeba7cc98563fa852e1f066df75072af0547838b326b1a81c95320c9974c +size 4692672256 diff --git a/Medichat-Llama3-8B.Q5_K_M.gguf b/Medichat-Llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..02a3773 --- /dev/null +++ b/Medichat-Llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3e0e461ffc4c062dfef37b237371f405bfaa15b30f64f8462201ebb07f8e39 +size 5732990720 diff --git a/Medichat-Llama3-8B.Q5_K_S.gguf b/Medichat-Llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..8999f56 --- /dev/null +++ b/Medichat-Llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d928ef7f702c75e7f94ff97a9e51a567992f03788cadd2718ec0b68b1dd1623 +size 5599297280 diff --git a/Medichat-Llama3-8B.Q6_K.gguf b/Medichat-Llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..52eaf7e --- /dev/null +++ b/Medichat-Llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b12103d3328423720c569b5c0ac4cffc8112256b86540a96b419eaa5c0f5ba64 +size 6596009728 diff --git a/Medichat-Llama3-8B.Q8_0.gguf b/Medichat-Llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..0a5e60f --- /dev/null +++ b/Medichat-Llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b4d9ff10921111ffab43b568be591c047da6f3674ea51b2b856972d25d1f21 +size 8540774144 diff --git a/Medichat-Llama3-8B.f16.gguf b/Medichat-Llama3-8B.f16.gguf new file mode 100644 index 0000000..70191c5 --- /dev/null +++ b/Medichat-Llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48bc140d5eeaf25d869a73e4df3f7086b40e6df508a8144b92b0968ebda55d0c +size 16068894464 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4e14d53 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: sethuiyer/Medichat-Llama3-8B +datasets: +- mlabonne/orpo-dpo-mix-40k +- Open-Orca/SlimOrca-Dedup +- jondurbin/airoboros-3.2 +- microsoft/orca-math-word-problems-200k +- m-a-p/Code-Feedback +- MaziyarPanahi/WizardLM_evol_instruct_V2_196k +- ruslanmv/ai-medical-chatbot +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- mergekit +- merge +- medical +--- +## About + + + + + + +static quants of https://huggingface.co/sethuiyer/Medichat-Llama3-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Medichat-Llama3-8B-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/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Medichat-Llama3-8B-GGUF/resolve/main/Medichat-Llama3-8B.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. + +