ba83bdc722c7dc54870980329bd94c5f9f90dc8e4ffa15554cdade8369734ead

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* 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
+SmolLM2-360M-Instruct-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- quantized
+- 2-bit
+- 3-bit
+- 4-bit
+- 5-bit
+- 6-bit
+- 8-bit
+- GGUF
+- text-generation
+- text-generation
+model_name: SmolLM2-360M-Instruct-GGUF
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+inference: false
+model_creator: HuggingFaceTB
+pipeline_tag: text-generation
+quantized_by: MaziyarPanahi
+---
+# [MaziyarPanahi/SmolLM2-360M-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/SmolLM2-360M-Instruct-GGUF)
+- Model creator: [HuggingFaceTB](https://huggingface.co/HuggingFaceTB)
+- Original model: [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct)
+
+## Description
+[MaziyarPanahi/SmolLM2-360M-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/SmolLM2-360M-Instruct-GGUF) contains GGUF format model files for [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct).
+
+### About GGUF
+
+GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
+
+Here is an incomplete list of clients and libraries that are known to support GGUF:
+
+* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
+* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
+* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
+* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
+* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
+* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
+* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
+* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
+* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
+* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
+
+## Special thanks
+
+🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.

SmolLM2-360M-Instruct-GGUF_imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea8a3504e3bd6ce5cb8396dbe6ff8af18e4581243c937e308ced822faf1fbbc
+size 1072370

SmolLM2-360M-Instruct.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a892b7e1b2770477b73392267d3b7f4312eac69502b53871fb9611d540b8c6
+size 218674016

SmolLM2-360M-Instruct.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b61974ac4b9170d4666322bdc45dd3a978b9a360fc1fe5498d2091956a0db4
+size 246322016

SmolLM2-360M-Instruct.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88d930cb91a5321d6bc7e9e55071c05d288b86215db5896ab2dff93b06ab801
+size 234686816

SmolLM2-360M-Instruct.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc399bade07e8b71f91ce0a5b51ee25a462e8223cf6ef9129fbba9171b371b9b
+size 270590816

SmolLM2-360M-Instruct.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcfb794d26c9b978415f27b07d046aa3a25e7830e7ce558db83d910c84a5e80
+size 259915616

SmolLM2-360M-Instruct.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a5c4d1a8196cb66de455d5ed359cf6ee1d0ddc03b6eeaa452fe7a06ec2617d
+size 289944416

SmolLM2-360M-Instruct.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27c0038abbba589f2cbde5c02a8f6aae0234a61de3608584f1e00fc8dc031d4
+size 283186016