commit bb72abfdc9670de0e1660dcd04345d92a4d15bdf Author: ModelHub XC Date: Thu Apr 16 14:58:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Tele-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37b5406 --- /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-3.2-1B-Tele.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Tele.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Tele.IQ4_XS.gguf b/Llama-3.2-1B-Tele.IQ4_XS.gguf new file mode 100644 index 0000000..e9c8251 --- /dev/null +++ b/Llama-3.2-1B-Tele.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:474e37bf5d1e12f124834cdda6e519db3132aa67ac27694caef1ceb35053e9ac +size 748380928 diff --git a/Llama-3.2-1B-Tele.Q2_K.gguf b/Llama-3.2-1B-Tele.Q2_K.gguf new file mode 100644 index 0000000..b9fc041 --- /dev/null +++ b/Llama-3.2-1B-Tele.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d49c3ea791d27c6750e3f85aaf204a50d5a566d86b994f35c8298d2b11827c0 +size 580870912 diff --git a/Llama-3.2-1B-Tele.Q3_K_L.gguf b/Llama-3.2-1B-Tele.Q3_K_L.gguf new file mode 100644 index 0000000..95cf651 --- /dev/null +++ b/Llama-3.2-1B-Tele.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9afc2cd1e8c792947809c4acbbaae193153c4df6c85d5adf5a13a68c4a804a0d +size 732521216 diff --git a/Llama-3.2-1B-Tele.Q3_K_M.gguf b/Llama-3.2-1B-Tele.Q3_K_M.gguf new file mode 100644 index 0000000..e3654cc --- /dev/null +++ b/Llama-3.2-1B-Tele.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884d783e4019ff7167d09f5f0616acfe1bb5ba489a17acabed7c282434e94215 +size 690840320 diff --git a/Llama-3.2-1B-Tele.Q3_K_S.gguf b/Llama-3.2-1B-Tele.Q3_K_S.gguf new file mode 100644 index 0000000..78d5cac --- /dev/null +++ b/Llama-3.2-1B-Tele.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4fd98d1c969bbd123e317f0ccf2b2ac1661c4322929f711a7fc20773ddfdd70 +size 641688320 diff --git a/Llama-3.2-1B-Tele.Q4_K_M.gguf b/Llama-3.2-1B-Tele.Q4_K_M.gguf new file mode 100644 index 0000000..44fe2f7 --- /dev/null +++ b/Llama-3.2-1B-Tele.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d78502bb41d828194485a2cbf72e2770aa17cbb82509252d694d12a56a39c3e +size 807691008 diff --git a/Llama-3.2-1B-Tele.Q4_K_S.gguf b/Llama-3.2-1B-Tele.Q4_K_S.gguf new file mode 100644 index 0000000..083ec4f --- /dev/null +++ b/Llama-3.2-1B-Tele.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c041874f6a0174c2c2c64578d83269f868137f70fcd83e60698b90bf2f6fbb5 +size 775643904 diff --git a/Llama-3.2-1B-Tele.Q5_K_M.gguf b/Llama-3.2-1B-Tele.Q5_K_M.gguf new file mode 100644 index 0000000..bbfd64d --- /dev/null +++ b/Llama-3.2-1B-Tele.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7fda41b465ccfb0b0a4fc50fbdffe6a2fa8cd9550526377a6977071c8ee36e1 +size 911500032 diff --git a/Llama-3.2-1B-Tele.Q5_K_S.gguf b/Llama-3.2-1B-Tele.Q5_K_S.gguf new file mode 100644 index 0000000..ae94951 --- /dev/null +++ b/Llama-3.2-1B-Tele.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9510916ed3e69fb8a00e321ff92dbf543c9bf3b64cd0834aff115d00cc8546a9 +size 892560128 diff --git a/Llama-3.2-1B-Tele.Q6_K.gguf b/Llama-3.2-1B-Tele.Q6_K.gguf new file mode 100644 index 0000000..d39809f --- /dev/null +++ b/Llama-3.2-1B-Tele.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc9226b4d3a4b901b865e13012fdb1db238aea928abba9da102f26ded4fec1c +size 1021797120 diff --git a/Llama-3.2-1B-Tele.Q8_0.gguf b/Llama-3.2-1B-Tele.Q8_0.gguf new file mode 100644 index 0000000..428b2c0 --- /dev/null +++ b/Llama-3.2-1B-Tele.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded59d38d2828bdba51ca5fc22bc9bf5a0dc40eec119b7b98eac74f56ea5efe1 +size 1321079552 diff --git a/Llama-3.2-1B-Tele.f16.gguf b/Llama-3.2-1B-Tele.f16.gguf new file mode 100644 index 0000000..543b6bd --- /dev/null +++ b/Llama-3.2-1B-Tele.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f994b8d72d799bc92082fec7a747bfb5ff4c282adf1a8790ca4f4148da06b84e +size 2479592192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0f0255 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: AliMaatouk/Llama-3.2-1B-Tele +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nlp +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AliMaatouk/Llama-3.2-1B-Tele + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-Tele-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-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Tele-GGUF/resolve/main/Llama-3.2-1B-Tele.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. + +