commit 6bb1d4697dffcb6a3001311abbe0aa066153e380 Author: ModelHub XC Date: Mon Oct 5 00:31:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama2-children-stories100M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..94ef35e --- /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 +llama2-children-stories100M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama2-children-stories100M.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..9d1a2bf --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: usamaalimalang/llama2-children-stories100M +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/usamaalimalang/llama2-children-stories100M + + +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/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-children-stories100M-GGUF/resolve/main/llama2-children-stories100M.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/llama2-children-stories100M.IQ4_XS.gguf b/llama2-children-stories100M.IQ4_XS.gguf new file mode 100644 index 0000000..032611a --- /dev/null +++ b/llama2-children-stories100M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef0c0f4fd6477720715bf6a6a2d5495a6f65d744bddab8f7b16050e9396cc3d +size 3647517184 diff --git a/llama2-children-stories100M.Q2_K.gguf b/llama2-children-stories100M.Q2_K.gguf new file mode 100644 index 0000000..e25192e --- /dev/null +++ b/llama2-children-stories100M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ea9d67f97cb565339d50829334c3d282f4f7a2e079ebc685e98de84741471d +size 2532864512 diff --git a/llama2-children-stories100M.Q3_K_L.gguf b/llama2-children-stories100M.Q3_K_L.gguf new file mode 100644 index 0000000..2c68d3f --- /dev/null +++ b/llama2-children-stories100M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d629e14a72917929d4ee4209e8fc2ef84cf8cf4e4eabb561923ae2f039accf6b +size 3597111808 diff --git a/llama2-children-stories100M.Q3_K_M.gguf b/llama2-children-stories100M.Q3_K_M.gguf new file mode 100644 index 0000000..b0424b0 --- /dev/null +++ b/llama2-children-stories100M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630550dc6787352ccc3f71f66d668bfb27e661711fd7b1adfd20396aadbec0e3 +size 3298005504 diff --git a/llama2-children-stories100M.Q3_K_S.gguf b/llama2-children-stories100M.Q3_K_S.gguf new file mode 100644 index 0000000..4f1a77d --- /dev/null +++ b/llama2-children-stories100M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5da5c273c3811432fea65716199c88a55b1d2edefc1f8462924c340000c2fe5 +size 2948305408 diff --git a/llama2-children-stories100M.Q4_0_4_4.gguf b/llama2-children-stories100M.Q4_0_4_4.gguf new file mode 100644 index 0000000..3950cf7 --- /dev/null +++ b/llama2-children-stories100M.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d806a75162358e021a28eb53847ab0ca96a5179519327f4fdd676563976cba +size 3825807872 diff --git a/llama2-children-stories100M.Q4_K_M.gguf b/llama2-children-stories100M.Q4_K_M.gguf new file mode 100644 index 0000000..df3618e --- /dev/null +++ b/llama2-children-stories100M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f26f448877f99421ab7a31ae4948e2c9eba051d383dcac513fa6993c420081 +size 4081005056 diff --git a/llama2-children-stories100M.Q4_K_S.gguf b/llama2-children-stories100M.Q4_K_S.gguf new file mode 100644 index 0000000..8e5a84e --- /dev/null +++ b/llama2-children-stories100M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1cb93f889bead60a9cbf39a8f187e8e13212089e2fa7f5e61b7433aa665712 +size 3856740864 diff --git a/llama2-children-stories100M.Q5_K_M.gguf b/llama2-children-stories100M.Q5_K_M.gguf new file mode 100644 index 0000000..6ea3970 --- /dev/null +++ b/llama2-children-stories100M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c5c0f898f3bdab147b1aa95d00f77a1b501bad7031d7558bbf49e0cac9c227f +size 4783157760 diff --git a/llama2-children-stories100M.Q5_K_S.gguf b/llama2-children-stories100M.Q5_K_S.gguf new file mode 100644 index 0000000..6207356 --- /dev/null +++ b/llama2-children-stories100M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e8f43b5b98c7499586f5a7f5859287c245f077e40e7db59abd8b4838e1f507 +size 4651692544 diff --git a/llama2-children-stories100M.Q6_K.gguf b/llama2-children-stories100M.Q6_K.gguf new file mode 100644 index 0000000..fb61565 --- /dev/null +++ b/llama2-children-stories100M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7ef3135bb7752124b5bdd756141d5acaa07b9e9f01a18f9c25431fe4222ece +size 5529195008 diff --git a/llama2-children-stories100M.Q8_0.gguf b/llama2-children-stories100M.Q8_0.gguf new file mode 100644 index 0000000..39cf154 --- /dev/null +++ b/llama2-children-stories100M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5099a4f53489d6ac9cde9dc998bc63747be8c2de0957fdc71d144245a2cd2762 +size 7161090560 diff --git a/llama2-children-stories100M.f16.gguf b/llama2-children-stories100M.f16.gguf new file mode 100644 index 0000000..49ae446 --- /dev/null +++ b/llama2-children-stories100M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad3ac6ed24a2458937531791f65d855fcd9c42f96953c03c536f463178b3f218 +size 13478105600