commit 3289292fde458bc242f0267813f9acca45ba7d28 Author: ModelHub XC Date: Fri Jun 12 11:04:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..14b4bee --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +airoboros-gpt-3.5-turbo-100k-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-gpt-3.5-turbo-100k-7b.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d9fc1a0 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: jondurbin/airoboros-gpt-3.5-turbo-100k-7b +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/jondurbin/airoboros-gpt-3.5-turbo-100k-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-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/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/airoboros-gpt-3.5-turbo-100k-7b-GGUF/resolve/main/airoboros-gpt-3.5-turbo-100k-7b.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. + + diff --git a/airoboros-gpt-3.5-turbo-100k-7b.IQ4_XS.gguf b/airoboros-gpt-3.5-turbo-100k-7b.IQ4_XS.gguf new file mode 100644 index 0000000..ce7272a --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f94ab4b71cd8654457bb4d9cb91f89af82ebede1fd47f9149735e4628c81d5 +size 3647517152 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q2_K.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q2_K.gguf new file mode 100644 index 0000000..1e848b4 --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8cace207024e05def4b45e00f6754f82deea3cb6937d911399066a364fa3026 +size 2532864480 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_L.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_L.gguf new file mode 100644 index 0000000..7e4af2c --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8921c94ad9986a12704ab4c1b0b865c26585897ca91016d83447316a655e2782 +size 3597111776 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_M.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_M.gguf new file mode 100644 index 0000000..ddf2c6c --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becd429f7058fc7e3d58fee0e7c8bee16769aefbf50f20cbbba511c8b8cdd192 +size 3298005472 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_S.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_S.gguf new file mode 100644 index 0000000..e534978 --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb3bd6d3b64f39d6afaeb023a1252f13cc6599cef407ebb85752c19de836eea +size 2948305376 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q4_0_4_4.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q4_0_4_4.gguf new file mode 100644 index 0000000..5096f9f --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb69b0f6f987652d5d4dcccc37a245b25429ebe952d24763c4e1197c9beb899 +size 3825807840 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q4_K_M.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q4_K_M.gguf new file mode 100644 index 0000000..4ecf0dc --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d5d454fcb64fdb4f74eacd00e63b840ed97863bd4b82ea287e00841e7a504e +size 4081005024 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q4_K_S.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q4_K_S.gguf new file mode 100644 index 0000000..9955871 --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b94815e4d413368427d4ac25142fb330322fa070c5076f07d630f6aa97767df3 +size 3856740832 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q5_K_M.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q5_K_M.gguf new file mode 100644 index 0000000..4ec182a --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2acc4e3b7887be37825f8c314dba671f8d724b679e26c09270b60b90de1a07 +size 4783157728 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q5_K_S.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q5_K_S.gguf new file mode 100644 index 0000000..9723a5e --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc2b3dce7eff1b9b38635fab90031244d0a6573bfbd1e8b50742f1205b1c79e +size 4651692512 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q6_K.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q6_K.gguf new file mode 100644 index 0000000..c1ba9f2 --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cda4368b1aeddb4c0c950425645ed0f0be6dd41c0a83533a14b6c1247ba6119 +size 5529194976 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.Q8_0.gguf b/airoboros-gpt-3.5-turbo-100k-7b.Q8_0.gguf new file mode 100644 index 0000000..e7c7fb9 --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc2b57405a4465ceb513b510f8cdacb95ba5fc1427dd574346d3deabdf9da06 +size 7161090528 diff --git a/airoboros-gpt-3.5-turbo-100k-7b.f16.gguf b/airoboros-gpt-3.5-turbo-100k-7b.f16.gguf new file mode 100644 index 0000000..7272496 --- /dev/null +++ b/airoboros-gpt-3.5-turbo-100k-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3fd6082de05eba6b114005572904eda6cd24eabfd1d6f268225813e3eb0c4d +size 13478105568