commit 6d0d30e3cc8870f8bc306167c6d23b478b4295a9 Author: ModelHub XC Date: Sun Jun 14 04:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-sft-spin-10k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..72d82a3 --- /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 +Llama-2-7b-sft-spin-10k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-10k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-sft-spin-10k.IQ4_XS.gguf b/Llama-2-7b-sft-spin-10k.IQ4_XS.gguf new file mode 100644 index 0000000..b5882dc --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d36cd12d4e87d97d5db883646d944e08e911c86673ed4c133c4694661b317d +size 3647518272 diff --git a/Llama-2-7b-sft-spin-10k.Q2_K.gguf b/Llama-2-7b-sft-spin-10k.Q2_K.gguf new file mode 100644 index 0000000..81df759 --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b95aefb83483a6a7d40908a2bb0d0893c3a737a1e4f929847a099f7d2df1371 +size 2532865600 diff --git a/Llama-2-7b-sft-spin-10k.Q3_K_L.gguf b/Llama-2-7b-sft-spin-10k.Q3_K_L.gguf new file mode 100644 index 0000000..876f87e --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e274e783f3d8ce96be301198778e0ce468aee3b7e37ed1efe37c0fe25fbc6a25 +size 3597112896 diff --git a/Llama-2-7b-sft-spin-10k.Q3_K_M.gguf b/Llama-2-7b-sft-spin-10k.Q3_K_M.gguf new file mode 100644 index 0000000..e36f0d8 --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1073dca78674012f986333fceb210010a26239b37099956c872d50b2f0c0178e +size 3298006592 diff --git a/Llama-2-7b-sft-spin-10k.Q3_K_S.gguf b/Llama-2-7b-sft-spin-10k.Q3_K_S.gguf new file mode 100644 index 0000000..b5fd88f --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7628e76e6e8890a42b6ecdce437fc4d21618086c0a90475671f5845780ae743c +size 2948306496 diff --git a/Llama-2-7b-sft-spin-10k.Q4_K_M.gguf b/Llama-2-7b-sft-spin-10k.Q4_K_M.gguf new file mode 100644 index 0000000..04cfd39 --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4103a2bf677aca5f74237a6d97503633a6728b27888e46d828395d6a79fbdb5a +size 4081006144 diff --git a/Llama-2-7b-sft-spin-10k.Q4_K_S.gguf b/Llama-2-7b-sft-spin-10k.Q4_K_S.gguf new file mode 100644 index 0000000..46dbd36 --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6684cc1360d2eec960de258583ee4360968ff3d9368e7fd2db841df2f99ff4b +size 3856741952 diff --git a/Llama-2-7b-sft-spin-10k.Q5_K_M.gguf b/Llama-2-7b-sft-spin-10k.Q5_K_M.gguf new file mode 100644 index 0000000..27b4b1a --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77811d3175833516ce653cfb2e35927d6c13f345c1b4f4464ece693b1e11eab3 +size 4783158848 diff --git a/Llama-2-7b-sft-spin-10k.Q5_K_S.gguf b/Llama-2-7b-sft-spin-10k.Q5_K_S.gguf new file mode 100644 index 0000000..a85c667 --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe99e3bb73a57809b6bd998e2c870561b124e093346999d5f14ca380c13c3d5 +size 4651693632 diff --git a/Llama-2-7b-sft-spin-10k.Q6_K.gguf b/Llama-2-7b-sft-spin-10k.Q6_K.gguf new file mode 100644 index 0000000..dc9c4ac --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aadeb7d26b622d6060a55a2d4eb120a4197e107f624f6138466a523c69d8eb7 +size 5529196096 diff --git a/Llama-2-7b-sft-spin-10k.Q8_0.gguf b/Llama-2-7b-sft-spin-10k.Q8_0.gguf new file mode 100644 index 0000000..5d5aa9f --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9d422e844f1662f15fe197512a3819759ffc5d308b7404bde2dc2c0fdefe892 +size 7161091648 diff --git a/Llama-2-7b-sft-spin-10k.f16.gguf b/Llama-2-7b-sft-spin-10k.f16.gguf new file mode 100644 index 0000000..566d6ae --- /dev/null +++ b/Llama-2-7b-sft-spin-10k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a57ad5a0532f12431d5ea091dec9738fb6ca78424c82f98b25ce8a8491eb04 +size 13478106688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9ea266b --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Llama-2-7b-sft-spin-10k +language: +- en +library_name: transformers +model_name: Llama-2-7b-sft-spin-10k +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-2-7b-sft-spin-10k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-sft-spin-10k-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/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-10k-GGUF/resolve/main/Llama-2-7b-sft-spin-10k.f16.gguf) | f16 | 13.6 | 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. + +