commit a0c31aaa2e46751672a084de5f2f8754d83d0f71 Author: ModelHub XC Date: Sun May 31 03:56:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PaperPrediction-RL-llama-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5fae70e --- /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 +PaperPrediction-RL-llama-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PaperPrediction-RL-llama-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PaperPrediction-RL-llama-1B.IQ4_XS.gguf b/PaperPrediction-RL-llama-1B.IQ4_XS.gguf new file mode 100644 index 0000000..0e6c1de --- /dev/null +++ b/PaperPrediction-RL-llama-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2deda416ba621e85624191ecc77eae77586e73a1014f26f924af927d8097b616 +size 748380512 diff --git a/PaperPrediction-RL-llama-1B.Q2_K.gguf b/PaperPrediction-RL-llama-1B.Q2_K.gguf new file mode 100644 index 0000000..4cc6cdb --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a4960267b66659a6220b5abae5ed7997199657a3efbfef50a9b002d3b20ddc +size 580870496 diff --git a/PaperPrediction-RL-llama-1B.Q3_K_L.gguf b/PaperPrediction-RL-llama-1B.Q3_K_L.gguf new file mode 100644 index 0000000..b5519ee --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ee97a18e98607871e338a334539095b2fc2f119db53ef3997b4a276aabe07c +size 732520800 diff --git a/PaperPrediction-RL-llama-1B.Q3_K_M.gguf b/PaperPrediction-RL-llama-1B.Q3_K_M.gguf new file mode 100644 index 0000000..d276717 --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c4fae5618280c3f73dbe60f6bdd92ced564598a76f5a763af701048c5f1bb0 +size 690839904 diff --git a/PaperPrediction-RL-llama-1B.Q3_K_S.gguf b/PaperPrediction-RL-llama-1B.Q3_K_S.gguf new file mode 100644 index 0000000..048ba67 --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61923f06cf6acca7b929f091ec13167381aeb083c74f4bb90cf904d9dfe35ad +size 641687904 diff --git a/PaperPrediction-RL-llama-1B.Q4_K_M.gguf b/PaperPrediction-RL-llama-1B.Q4_K_M.gguf new file mode 100644 index 0000000..22feb82 --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb97f3c1b3c9e3e4dd26fe211a47affc88a972ceebc5d2abd90384879a51c78 +size 807690592 diff --git a/PaperPrediction-RL-llama-1B.Q4_K_S.gguf b/PaperPrediction-RL-llama-1B.Q4_K_S.gguf new file mode 100644 index 0000000..7014081 --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e0b52e5642c58def5257291033edd7c739143ef5031ee145fc09bddf1140d8 +size 775643488 diff --git a/PaperPrediction-RL-llama-1B.Q5_K_M.gguf b/PaperPrediction-RL-llama-1B.Q5_K_M.gguf new file mode 100644 index 0000000..07f3b5b --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee9cfe4378c9061e934f388a496028ba23ac8cec02ab0a52243440bd69bac95 +size 911499616 diff --git a/PaperPrediction-RL-llama-1B.Q5_K_S.gguf b/PaperPrediction-RL-llama-1B.Q5_K_S.gguf new file mode 100644 index 0000000..b11f5ad --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97851313e2d6303b9a2ed2bcb49e26da05183c7a3702e96d890814116d9bc4f +size 892559712 diff --git a/PaperPrediction-RL-llama-1B.Q6_K.gguf b/PaperPrediction-RL-llama-1B.Q6_K.gguf new file mode 100644 index 0000000..d93c921 --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:216b299a6e46d1370d4ba41e9b86aff67f71cc8114ca24f1b65089becca3a1b3 +size 1021796704 diff --git a/PaperPrediction-RL-llama-1B.Q8_0.gguf b/PaperPrediction-RL-llama-1B.Q8_0.gguf new file mode 100644 index 0000000..11c2a51 --- /dev/null +++ b/PaperPrediction-RL-llama-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb1671111ab2c417f0a4ab65616dd733e185dabd7ae8100d85c18628979c95c +size 1321079136 diff --git a/PaperPrediction-RL-llama-1B.f16.gguf b/PaperPrediction-RL-llama-1B.f16.gguf new file mode 100644 index 0000000..dd886ad --- /dev/null +++ b/PaperPrediction-RL-llama-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f91a67da67f4372fe7d23051a79a7eda21d7e5a4266b2ce442cc260fd48938 +size 2479591776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2a09ce8 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: weihezhai/PaperPrediction-RL-llama-1B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/weihezhai/PaperPrediction-RL-llama-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PaperPrediction-RL-llama-1B-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/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PaperPrediction-RL-llama-1B-GGUF/resolve/main/PaperPrediction-RL-llama-1B.f16.gguf) | f16 | 2.6 | 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. + +