commit c87d81cc60c7aed003b33ede2ec15a6c622e10ab Author: ModelHub XC Date: Sat Jun 13 20:30:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7334f59 --- /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 +DeepSeek-llama3.1-HARI-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-llama3.1-HARI-8B.IQ4_XS.gguf b/DeepSeek-llama3.1-HARI-8B.IQ4_XS.gguf new file mode 100644 index 0000000..ac795b8 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf794fc1acbf5d96074b802dbf60e9f881b61e27b69e3733365fb7ae47fb97b +size 4484370304 diff --git a/DeepSeek-llama3.1-HARI-8B.Q2_K.gguf b/DeepSeek-llama3.1-HARI-8B.Q2_K.gguf new file mode 100644 index 0000000..3964f6f --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b27916d38a055ac7b525cb6bf8b76209892c0a7a19b26f441d3ef88d8318202b +size 3179138112 diff --git a/DeepSeek-llama3.1-HARI-8B.Q3_K_L.gguf b/DeepSeek-llama3.1-HARI-8B.Q3_K_L.gguf new file mode 100644 index 0000000..7b55c9f --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f8afc3b4e78ebb1dd4c58a7c2004e2f7a281af7a5982327a102face7239e87 +size 4321963488 diff --git a/DeepSeek-llama3.1-HARI-8B.Q3_K_M.gguf b/DeepSeek-llama3.1-HARI-8B.Q3_K_M.gguf new file mode 100644 index 0000000..11040d7 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e752d4c7d9b5239fbca430d94b41c7dc1b92165b4e8d6ae4819fb5e4aeac819a +size 4018925024 diff --git a/DeepSeek-llama3.1-HARI-8B.Q3_K_S.gguf b/DeepSeek-llama3.1-HARI-8B.Q3_K_S.gguf new file mode 100644 index 0000000..c74bd7a --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c8c321d0099874ff7c7ec79646a1dab06d9de6aa9c235b195f96d4cc46d00f +size 3664506336 diff --git a/DeepSeek-llama3.1-HARI-8B.Q4_K_M.gguf b/DeepSeek-llama3.1-HARI-8B.Q4_K_M.gguf new file mode 100644 index 0000000..bd731e1 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dc120c7ab62bd56acd869d967ff7033010eb0f0742bc23c23bd0ec764c8c7c5 +size 4920741888 diff --git a/DeepSeek-llama3.1-HARI-8B.Q4_K_S.gguf b/DeepSeek-llama3.1-HARI-8B.Q4_K_S.gguf new file mode 100644 index 0000000..f0e9559 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:452253ce66865c40ae7ed15147c76f4a97b661b11444529e3e305230c9a13b46 +size 4692676608 diff --git a/DeepSeek-llama3.1-HARI-8B.Q5_K_M.gguf b/DeepSeek-llama3.1-HARI-8B.Q5_K_M.gguf new file mode 100644 index 0000000..9d112ab --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f5c1c83760070899f6eca8251f1512e567a35396b4536014ae6a93d549c2f0 +size 5732995584 diff --git a/DeepSeek-llama3.1-HARI-8B.Q5_K_S.gguf b/DeepSeek-llama3.1-HARI-8B.Q5_K_S.gguf new file mode 100644 index 0000000..7cf8591 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e1a25d94e5e768299cc6cf00823afe99d01219ea038919dd805f9e44e00d975 +size 5599302144 diff --git a/DeepSeek-llama3.1-HARI-8B.Q6_K.gguf b/DeepSeek-llama3.1-HARI-8B.Q6_K.gguf new file mode 100644 index 0000000..16059a2 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82870301cfc8160c5365bba6992a86581c2c14a86ceb771099cd5b155ebcc5fa +size 6596015136 diff --git a/DeepSeek-llama3.1-HARI-8B.Q8_0.gguf b/DeepSeek-llama3.1-HARI-8B.Q8_0.gguf new file mode 100644 index 0000000..38d8cec --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61446c41b91662280dd26bf1fdb1a0f8354204778ed1a49a5408f9079cd4056 +size 8540781536 diff --git a/DeepSeek-llama3.1-HARI-8B.f16.gguf b/DeepSeek-llama3.1-HARI-8B.f16.gguf new file mode 100644 index 0000000..c111441 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad02e28655b53df41d965be4855ca18f9b3f4e9905132d359a8dc37d57a088da +size 16068909536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a34e0e1 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: SNUH-HARI/DeepSeek-llama3.1-HARI-8B +datasets: +- FreedomIntelligence/medical-o1-reasoning-SFT +- SNUH-HARI/KorMedLawQA +language: +- en +- ko +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- medical +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/SNUH-HARI/DeepSeek-llama3.1-HARI-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-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/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-GGUF/resolve/main/DeepSeek-llama3.1-HARI-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. + +