初始化项目，由ModelHub XC社区提供模型

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

.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
+Llama-SmolTalk-3.2-1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-SmolTalk-3.2-1B-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8ee070b7a1eb0cc52436762e66d1daf10368f46d4ba0f8620cbb26c6cb0478
+size 748385888

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81064bae631d72fb5380b8f3f92dae7b3ab8a74c6eaf0a64665f1c971580f164
+size 580875872

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da9a437a4a34831e2341fca1820725fa54a442e2d46a6512df74145224210052
+size 732526176

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6486372d9abe247b4b7bd6b8204d1e398c3bf38396798fe319aa3d23d16c04
+size 690845280

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841d63cd5ec706455555b17f3aa94ab2373c369fc79228edee5fda8b472352d9
+size 641693280

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4bfc729b01587836553eabd7f1f2cec661908d798b1b17107c3f873dde883f5
+size 770930272

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d8d05e3821f4caa65defa82baaff658484d4405b66546431528153ceef4d9e
+size 807695968

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1449362aa29143816765395c40ad49e478a5a707932fe9003b3b87fb350e4e9
+size 775648864

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b062eff627487e6b5213b9358fbe245da411f30a95915f7a4dcf021160c758
+size 911504992

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b90b6dbb0d44eb1e7b93bd27eb6b30138d0b6a69bf9ebe04612485d2c207810
+size 892565088

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3dfb6c977044e3e80487a72b712be71f344f44d48a594b0cd4480ffd9009e7
+size 1021802080

Llama-SmolTalk-3.2-1B-Instruct.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025f2a7edf4b6528dd15264d20b44df1405e952b283d532daf3d6f34121cfe16
+size 1321084512

Llama-SmolTalk-3.2-1B-Instruct.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7c34874af7d43898494c88fadbc2b25c4af14f0a9efadb60e06e849efb2b49
+size 2479597152

README.md

@@ -0,0 +1,73 @@
+---
+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 -->
+static quants of https://huggingface.co/prithivMLmods/Llama-SmolTalk-3.2-1B-Instruct
+
+<!-- provided-files -->
+weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-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/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q2_K.gguf) | Q2_K | 0.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.9 | fast on arm, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-SmolTalk-3.2-1B-Instruct-GGUF/resolve/main/Llama-SmolTalk-3.2-1B-Instruct.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. 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 -->