commit 12c32287fc4cc765397a410b35e9c06a6e060f37 Author: ModelHub XC Date: Fri Jun 26 07:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ee32d6d --- /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 +Fireball-R1-Llama-3.1-8B-Medical-COT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-R1-Llama-3.1-8B-Medical-COT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.IQ4_XS.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.IQ4_XS.gguf new file mode 100644 index 0000000..64b1a60 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8595fea2720a9497717f4c329e8cbb2c95e5e99a9b73d5e87ff7183b70ca9041 +size 4484373280 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q2_K.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q2_K.gguf new file mode 100644 index 0000000..e01fc88 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d8ef6c8412af694029c02e2cc610b8781bff112928324ea9f8933fc04b81ab7 +size 3179141920 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_L.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_L.gguf new file mode 100644 index 0000000..e252b8b --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e84a8a8b558aca27d0ce875dcd1d55d984a5ce2e7a99af4d8a908f92898cf4 +size 4321966880 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_M.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_M.gguf new file mode 100644 index 0000000..91c11f6 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a136541be853c32d9d049ae7c26148d0b57f554d90f1ed1107a56235cd5f3046 +size 4018928416 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_S.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_S.gguf new file mode 100644 index 0000000..b1572af --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e285f4ef30f1b9d073ebbddcb8c3c4b0ff67c0058a127e765356427733a504 +size 3664509728 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_M.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_M.gguf new file mode 100644 index 0000000..87eaeb7 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ea58ec40682e86df84f5b26e1b0c2b5010a213a213d9c54b6d8d49e9905b32 +size 4920744736 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_S.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_S.gguf new file mode 100644 index 0000000..738bfc2 --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffbd5a707ec1544c4d23b1a571e39528ab6bd6505585de920ff4a16b1cfc141 +size 4692679456 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_M.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_M.gguf new file mode 100644 index 0000000..2d2064d --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9428f9b6925008e4954b366da0a7286b1b3be3f9b7999297dbbae71c8bc724d3 +size 5732997920 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_S.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_S.gguf new file mode 100644 index 0000000..4558b1b --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cdd152edce2932ccb5fbb76dbb91966e4cb5f69310e0d534bb8d8fbad670b74 +size 5599304480 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q6_K.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q6_K.gguf new file mode 100644 index 0000000..1afbf9a --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29debb71d87e8ee3f4a978f220f5f21346c4d6d71b8c992aeffdbc6005f5c03c +size 6596016928 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.Q8_0.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q8_0.gguf new file mode 100644 index 0000000..10cf30a --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ac43b31200d48f7ee11d8f618ca0280cf2b523caeaea511c41306b23fef301 +size 8540781344 diff --git a/Fireball-R1-Llama-3.1-8B-Medical-COT.f16.gguf b/Fireball-R1-Llama-3.1-8B-Medical-COT.f16.gguf new file mode 100644 index 0000000..b5c60be --- /dev/null +++ b/Fireball-R1-Llama-3.1-8B-Medical-COT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896b6f66d3615d5f1ef41a77c8ac1ebf6e8ba6fc932b7bd47f423e544c1f7171 +size 16068901664 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0fa04b8 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT +datasets: +- FreedomIntelligence/medical-o1-reasoning-SFT +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-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/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-R1-Llama-3.1-8B-Medical-COT-GGUF/resolve/main/Fireball-R1-Llama-3.1-8B-Medical-COT.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. + +