初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,60 @@
+*.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
+imatrix.dat filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25165067e2892a5744173e60bcb78a6fdca6e0a5406e7cee16afc99d9305cd10
+size 413607776

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9147b97b99b8cd7a086badf7d1ae9bb380a02b3f825af89f043625e31a02b64b
+size 393553760

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca2558ab9bf26182027f575e34b536ca142e5be6a97edd9d1533ed597a6b06d
+size 515450720

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c20a60fbdbe97ee0316f39c9cf21074378301011bb72cb105e83ea953c09436
+size 488712032

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a3fcd9aad31196f67ab19dabf1df0517a4d847540855764d28ab161e7c5020
+size 475866976

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed09cc267934926c2a30fcbdfe48460d5bcf103e88671993230dfd940c165e66
+size 447031136

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53fa33248eea0cda97fd1b30c2036bd557e7f1f4bd2ad84c7987d6e8a00d8d85
+size 657291104

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972545bb1b13938af07aa03276c06a31bd88746bd76c29012bf90a6b29fbb890
+size 643921760

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f8b1c6995d349f11458ebe6861427c4e64888db6e0c08e8745a361bc07da83
+size 621115232

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb568666dedbd50e7285e601c2ab001a672e0560def0242df09db2e6bd711a2
+size 562112352

Llama-SmolTalk-3.2-1B-Instruct.i1-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2997d3631bb2e6d3890f52b204f06f7bb1d3ca0c9c2b24ff7b7d0ea711e1a783
+size 743143264

Llama-SmolTalk-3.2-1B-Instruct.i1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6a4c82a4838201111e7e0f224f41b96df0e0aa2ffeae560743865f08ba642a
+size 580876128

Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e0bf1ad509c1518f5a84c2fa78085b1af294cee0aed66e6a32a2a6bf841e64
+size 732526432

Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986c3c98d6b5e067fef576b45bef1a8dc7266bb02cde3ab00aa21973bc22051d
+size 690845536

Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078bb7c9beb2ac419379bd65e62270347b9c6c335ef0f98fac01bae1b0b1c1b1
+size 641693536

Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013b661201264f6bda4e7493dbe4332db3b1bfbe2941a08c10214317b3ac0a1f
+size 773027680

Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_4_4.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f60912e81c1ec929c1ea25fae987352ff2bd34b2c5e636a3040c6e01b44ee3e
+size 770930528

Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_4_8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146e1175ad62207a7951289fcbb37995b8a7499648b843c9a6d9651912a6a687
+size 770930528

Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_8_8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686368fb359ce5af06ec6c0b3932879331f6770cf17b95503ee89eec8e831b5f
+size 770930528

Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8710cbdcec94932ddb50c455c8c560cdab635627cafb18a23decea0c26d6a5eb
+size 807696224

Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a42aee6cd370494880dbd942a9671a303bf58f9e7ef053c6e1b99d67c7a2faf
+size 775649120

Llama-SmolTalk-3.2-1B-Instruct.i1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4363e4ccf437ffed5538ad87fd049525c2733a414c259b08d5b5a4bf698c7c5e
+size 911505248

Llama-SmolTalk-3.2-1B-Instruct.i1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94f1e7476fc95d69c49a442e1afef9239de5438e63235fa1506253e55a5622b
+size 892565344

Llama-SmolTalk-3.2-1B-Instruct.i1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bedd948e9ef101199b151bd9a0fdb541810c602199b86ca185d785a6fa34ef
+size 1021802336

README.md

@@ -0,0 +1,84 @@
+---
+base_model: prithivMLmods/Llama-SmolTalk-3.2-1B-Instruct
+datasets:
+- HuggingFaceTB/smoltalk
+language:
+- en
+library_name: transformers
+license: creativeml-openrail-m
+quantized_by: mradermacher
+tags:
+- Llama
+- Llama-CPP
+- SmolTalk
+- ollama
+- bin
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags: nicoboss -->
+weighted/imatrix quants of https://huggingface.co/prithivMLmods/Llama-SmolTalk-3.2-1B-Instruct
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-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/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.8 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 0.9 | fast on arm, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 0.9 | fast on arm+i8mm, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 0.9 | fast on arm+sve, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.9 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-i1-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 1.1 | practically like static Q6_K |
+
+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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
+
+<!-- end -->

imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee38fa4eb8a7bb9e88c9a930cd64bb1945dc0ab02f22bf56731d568466bdaf19
+size 1314413