初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF Source: Original Platform
2026-07-06 10:31:16 +08:00
commit a01afbf7b7
14 changed files with 152 additions and 0 deletions
--- a/.gitattributes
+++ 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
+JulianLou_TinyLLaMA_medical_sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+JulianLou_TinyLLaMA_medical_sft.f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/JulianLou_TinyLLaMA_medical_sft.IQ4_XS.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165d4e273d14ce621738d9f4f567d19e4360942c2d87a92bec818f46f2b2df4e
+size 21182048
--- a/JulianLou_TinyLLaMA_medical_sft.Q2_K.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482a9edaa832ec86bf0f85be4e3478a5a45909323da042417888b30cbefb6cd9
+size 21182048
--- a/JulianLou_TinyLLaMA_medical_sft.Q3_K_L.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6f7cb3f48a0a701fc3811bd4b02a43eea6d4c3fc151b0d4abe94f52ef248db
+size 21185120
--- a/JulianLou_TinyLLaMA_medical_sft.Q3_K_M.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52992612db9c90b2b866b8b3f15777599e494427a70c7121e0cac9faefc1e6b4
+size 21184352
--- a/JulianLou_TinyLLaMA_medical_sft.Q3_K_S.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc04d8de6b7c0a81110f9fd37ebb738cef52f8956a766a2f667cf5d648eaeed1
+size 21182048
--- a/JulianLou_TinyLLaMA_medical_sft.Q4_K_M.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800f39d6f860b6d62bae24d6ca6c9e0c4226f5e33df605761ef8e204f6c06a6b
+size 22217824
--- a/JulianLou_TinyLLaMA_medical_sft.Q4_K_S.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26fe3f253cdf9ea1f81a10e71da72312be802595336bdebefa367eb5b3b1fe29
+size 22213472
--- a/JulianLou_TinyLLaMA_medical_sft.Q5_K_M.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25b1c11e52228ad9397fca3ef6b6252ce7c1014668e4552749beedd989afaca
+size 22732640
--- a/JulianLou_TinyLLaMA_medical_sft.Q5_K_S.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aecaeccf56dc1de270f0643a8038d08218c071f41908572c3ab1123c02929a7
+size 22728800
--- a/JulianLou_TinyLLaMA_medical_sft.Q6_K.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75284129b5aefec9ded4d9dd53edb64cef18d631f6a3f8d11d2219f42ed826a
+size 25306720
--- a/JulianLou_TinyLLaMA_medical_sft.Q8_0.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1146e7a953892c5e714c8ae8c7a036898bb399324c2ebbc52a82b776287982
+size 25306720
--- a/JulianLou_TinyLLaMA_medical_sft.f16.gguf
+++ b/JulianLou_TinyLLaMA_medical_sft.f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb06c04350791d7af2d4af6f2b1bec68ac9b3dc27278675840fbba2310cb736
+size 40735840
--- a/README.md
+++ b/README.md
@@ -0,0 +1,69 @@
+---
+base_model: Julian2002/JulianLou_TinyLLaMA_medical_sft
+language:
+- en
+library_name: transformers
+mradermacher:
+  readme_rev: 1
+quantized_by: mradermacher
+tags: []
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags:  -->
+static quants of https://huggingface.co/Julian2002/JulianLou_TinyLLaMA_medical_sft
+
+<!-- provided-files -->
+
+***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#JulianLou_TinyLLaMA_medical_sft-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/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.IQ4_XS.gguf) | IQ4_XS | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q2_K.gguf) | Q2_K | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q3_K_S.gguf) | Q3_K_S | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q3_K_M.gguf) | Q3_K_M | 0.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q3_K_L.gguf) | Q3_K_L | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q4_K_M.gguf) | Q4_K_M | 0.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q5_K_S.gguf) | Q5_K_S | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q5_K_M.gguf) | Q5_K_M | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q6_K.gguf) | Q6_K | 0.1 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.Q8_0.gguf) | Q8_0 | 0.1 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/JulianLou_TinyLLaMA_medical_sft-GGUF/resolve/main/JulianLou_TinyLLaMA_medical_sft.f16.gguf) | f16 | 0.1 | 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.
+
+<!-- end -->