commit ce4b5e2fe257f2bd5cb2f892000af4e0b18bc6f2 Author: ModelHub XC Date: Sat Oct 10 19:37:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tinyllama-medical-chat-v1.4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1f410b1 --- /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 +tinyllama-medical-chat-v1.4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-medical-chat-v1.4.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b0840c --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: falan42/tinyllama-medical-chat-v1.4 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/falan42/tinyllama-medical-chat-v1.4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#tinyllama-medical-chat-v1.4-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/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-medical-chat-v1.4-GGUF/resolve/main/tinyllama-medical-chat-v1.4.f16.gguf) | f16 | 2.3 | 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/tinyllama-medical-chat-v1.4.IQ4_XS.gguf b/tinyllama-medical-chat-v1.4.IQ4_XS.gguf new file mode 100644 index 0000000..ea441e0 --- /dev/null +++ b/tinyllama-medical-chat-v1.4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f5c72a5c5c27a4467362250dba6a2a36ecc20fcfbb53f01e59d6c1db70a29c +size 609808128 diff --git a/tinyllama-medical-chat-v1.4.Q2_K.gguf b/tinyllama-medical-chat-v1.4.Q2_K.gguf new file mode 100644 index 0000000..ffaf688 --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7507d539784cdcf45ce56273975a9c982d0d2e4d85e33f705a339c51b43bf9c1 +size 432131840 diff --git a/tinyllama-medical-chat-v1.4.Q3_K_L.gguf b/tinyllama-medical-chat-v1.4.Q3_K_L.gguf new file mode 100644 index 0000000..736a8e9 --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f47adfc8744db17893a7aa14b6fda389643ffdc5968010e92478f74a4b7710a +size 591527680 diff --git a/tinyllama-medical-chat-v1.4.Q3_K_M.gguf b/tinyllama-medical-chat-v1.4.Q3_K_M.gguf new file mode 100644 index 0000000..a7d855a --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43a1d2e845ad8fa168153e8e8234228f92032264fe51a99168851096a1bdba31 +size 548404992 diff --git a/tinyllama-medical-chat-v1.4.Q3_K_S.gguf b/tinyllama-medical-chat-v1.4.Q3_K_S.gguf new file mode 100644 index 0000000..51dbf00 --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c20c250879108a2411690f3c9946d547878b82417f1b8cd25f0ee0b8de23edbe +size 499343104 diff --git a/tinyllama-medical-chat-v1.4.Q4_K_M.gguf b/tinyllama-medical-chat-v1.4.Q4_K_M.gguf new file mode 100644 index 0000000..24d89e2 --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6f5fa4ccf92adaea02dba6f79cd2417c711797220c499aba8693a8a01376df7 +size 667815680 diff --git a/tinyllama-medical-chat-v1.4.Q4_K_S.gguf b/tinyllama-medical-chat-v1.4.Q4_K_S.gguf new file mode 100644 index 0000000..684c1f8 --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c21e11d8d5f7605e5f929a2d257ffd07273f15720e926122d12ff3c6bc8386c +size 639872768 diff --git a/tinyllama-medical-chat-v1.4.Q5_K_M.gguf b/tinyllama-medical-chat-v1.4.Q5_K_M.gguf new file mode 100644 index 0000000..ab8209f --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58574724c4c911612eb125ab2fadb01ba3d7e46659b30e95350b687fbf98030 +size 782044928 diff --git a/tinyllama-medical-chat-v1.4.Q5_K_S.gguf b/tinyllama-medical-chat-v1.4.Q5_K_S.gguf new file mode 100644 index 0000000..adc482c --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a2efc39053bdd600f041fcdbeff05f511f61c830b44f29e1263b7fdee54e86 +size 766029568 diff --git a/tinyllama-medical-chat-v1.4.Q6_K.gguf b/tinyllama-medical-chat-v1.4.Q6_K.gguf new file mode 100644 index 0000000..d0af4b7 --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02878c7a542442dacaeed4b9174b281dd51dbecd6dbc6c28eba4d799d13abc03 +size 903413504 diff --git a/tinyllama-medical-chat-v1.4.Q8_0.gguf b/tinyllama-medical-chat-v1.4.Q8_0.gguf new file mode 100644 index 0000000..c65057d --- /dev/null +++ b/tinyllama-medical-chat-v1.4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fbf52f119c82e31c777ff8aa247693ef185d3098e06bac81bd4a7d476c5bce7 +size 1169809152 diff --git a/tinyllama-medical-chat-v1.4.f16.gguf b/tinyllama-medical-chat-v1.4.f16.gguf new file mode 100644 index 0000000..0c63fbf --- /dev/null +++ b/tinyllama-medical-chat-v1.4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe95eb2c2e8ce5dc5b2a33d51bfa89440b89a9fa39f59ee6e5cc503fd344c9a1 +size 2201018112