commit 66c0f8c8ddc08d7ba00e0194a0b31b6fbfa1aeca Author: ModelHub XC Date: Tue Sep 29 08:39:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-sft-spin-4k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a4e087e --- /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-4k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-spin-4k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-sft-spin-4k.IQ4_XS.gguf b/Llama-2-7b-sft-spin-4k.IQ4_XS.gguf new file mode 100644 index 0000000..8d6b462 --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be1d0654a37fa44030f0b825038cf1a3a02add4db1af9ba6fb897bfba0aeaee7 +size 3647518272 diff --git a/Llama-2-7b-sft-spin-4k.Q2_K.gguf b/Llama-2-7b-sft-spin-4k.Q2_K.gguf new file mode 100644 index 0000000..0ade0db --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f111f145b6fd077c336481af5b7efc7ec829c4b707466d81b223ed6977906960 +size 2532865600 diff --git a/Llama-2-7b-sft-spin-4k.Q3_K_L.gguf b/Llama-2-7b-sft-spin-4k.Q3_K_L.gguf new file mode 100644 index 0000000..e8dd59f --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff589dffb5040f8bdfefd5c98cfba674b494c4ec894b3e1b11153d28b1ef454 +size 3597112896 diff --git a/Llama-2-7b-sft-spin-4k.Q3_K_M.gguf b/Llama-2-7b-sft-spin-4k.Q3_K_M.gguf new file mode 100644 index 0000000..a70368f --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60803aecee7ee91cb741bb1c7d25e9aa98b877eb87db0c8ff1784562da35f8ab +size 3298006592 diff --git a/Llama-2-7b-sft-spin-4k.Q3_K_S.gguf b/Llama-2-7b-sft-spin-4k.Q3_K_S.gguf new file mode 100644 index 0000000..6df6327 --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb00a0b768d9f62a4c632f97fe8dfc5712450045e60c6c2d36e1c8d3240a9e5b +size 2948306496 diff --git a/Llama-2-7b-sft-spin-4k.Q4_K_M.gguf b/Llama-2-7b-sft-spin-4k.Q4_K_M.gguf new file mode 100644 index 0000000..182d09a --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00509318b9272f0b0a5e3675cb10370ec1fe687a0069e6dcf59571d5ad65a803 +size 4081006144 diff --git a/Llama-2-7b-sft-spin-4k.Q4_K_S.gguf b/Llama-2-7b-sft-spin-4k.Q4_K_S.gguf new file mode 100644 index 0000000..4dc9faf --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a0f07b3c1582b7bf8e5472f235d98ad5368bc76d9aff53043c59952647a9d6 +size 3856741952 diff --git a/Llama-2-7b-sft-spin-4k.Q5_K_M.gguf b/Llama-2-7b-sft-spin-4k.Q5_K_M.gguf new file mode 100644 index 0000000..b613115 --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6293515239534c142977ab98d289124fe3db6fcb316ca359abe0922ebc6d18 +size 4783158848 diff --git a/Llama-2-7b-sft-spin-4k.Q5_K_S.gguf b/Llama-2-7b-sft-spin-4k.Q5_K_S.gguf new file mode 100644 index 0000000..c9e7de0 --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd7b5434958557961cb5eacedb4c4203e5918d98a2e731a04705366ec15adf8 +size 4651693632 diff --git a/Llama-2-7b-sft-spin-4k.Q6_K.gguf b/Llama-2-7b-sft-spin-4k.Q6_K.gguf new file mode 100644 index 0000000..ffe0904 --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a3e76e317dd5b9bd167e10fa07336c431098e361c4252f3794606c874437fd +size 5529196096 diff --git a/Llama-2-7b-sft-spin-4k.Q8_0.gguf b/Llama-2-7b-sft-spin-4k.Q8_0.gguf new file mode 100644 index 0000000..8123165 --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d749bb8f1eefc8644768f29e2a963ea9a68479bcb8c50856afeb82e20fa729 +size 7161091648 diff --git a/Llama-2-7b-sft-spin-4k.f16.gguf b/Llama-2-7b-sft-spin-4k.f16.gguf new file mode 100644 index 0000000..88304e3 --- /dev/null +++ b/Llama-2-7b-sft-spin-4k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cbc17d179a22cf4c548802d06e2503851349a70b15cf8f0286772f65f82d03e +size 13478106688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa84a21 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Llama-2-7b-sft-spin-4k +language: +- en +library_name: transformers +model_name: Llama-2-7b-sft-spin-4k +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-2-7b-sft-spin-4k + + +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-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-spin-4k-GGUF/resolve/main/Llama-2-7b-sft-spin-4k.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. + +