Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,20 @@ 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
+Qwen2.5-7B-Instruct-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.fp16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text

Qwen2.5-7B-Instruct-GGUF_imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5e9fd350dffad96aa5adf82e1643c25407c5772ea537182b1a63e17d072a7c
+size 4536654

Qwen2.5-7B-Instruct.IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43a9a221152c314bb761f2bd5c3605c931ccb8250aa439c02c52758e9824b9f
+size 2042196640

Qwen2.5-7B-Instruct.IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec2dd66c0ee9371ad53977c17449e5c47e5410a48b73e4aa04373c2409c267f
+size 1903667872

Qwen2.5-7B-Instruct.IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4fc6203f1a9eaf8e6e02bec411a9b2f44de4a83a79c8e5d1c50ae4a4194b879
+size 2469022368

Qwen2.5-7B-Instruct.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e85a821d7ecb34315662bbf278eba51aa20570eaf6e043b2fb10b540b651dd
+size 3346256544

Qwen2.5-7B-Instruct.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2810b8d763d3f051ff9917c324fa314ff286edff090db1bddae9fb773f3713
+size 4218473120

Qwen2.5-7B-Instruct.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfdffbe594a22e7627297fba4492dcc9484e1c6e3acf4aabfad98a49e46550c
+size 3015940768

Qwen2.5-7B-Instruct.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d26492f75fd467088a12fa34715948f4c3226f4dbd8c171df0b17bca76f32fd
+size 4088459936

Qwen2.5-7B-Instruct.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1b8e82690ac561353275068f5869c8442ad738c1949b6731754aafb00a2a33
+size 3808391840

Qwen2.5-7B-Instruct.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1d3ff3973717a757f5c809565ab5b67bc163091e6f2b228621d36b1030d6a6
+size 3492369056

Qwen2.5-7B-Instruct.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f80e06be81cc130e2f4881edfa32e10eaa3f93f3370fde579868065186730b6
+size 4683074208

Qwen2.5-7B-Instruct.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344c78661b98c929d2c8ee791e3d8f38095bdf363f91a3b0232edcc7094f6bd9
+size 4457769632

Qwen2.5-7B-Instruct.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22579ae6fbec54cba914b20e0fe19acc4d918b264ed31d91ce465afa9843c9e9
+size 5444831904

Qwen2.5-7B-Instruct.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17af263acd0263fe05d5d88a480e02ac455be1b2f9eac0475b740e83af2495a4
+size 5315177120

Qwen2.5-7B-Instruct.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab42007e998e51a3269ce79b6418fcbbc9ba4999b07b5f4dae242876ab626d5
+size 6254199456

Qwen2.5-7B-Instruct.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e399a7afc6f592ecde409725a1bdc9102a8921eea6e95a8ba7a4f46367a17b
+size 8098525856

Qwen2.5-7B-Instruct.fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e1162ae270859ff9ef2916ef7f1c89233ca191b06efc074576e0340371b787
+size 15237853632

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: Qwen2.5-7B-Instruct-GGUF
+base_model: Qwen/Qwen2.5-7B-Instruct
+inference: false
+model_creator: Qwen
+pipeline_tag: text-generation
+quantized_by: MaziyarPanahi
+---
+# [MaziyarPanahi/Qwen2.5-7B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2.5-7B-Instruct-GGUF)
+- Model creator: [Qwen](https://huggingface.co/Qwen)
+- Original model: [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
+
+## Description
+[MaziyarPanahi/Qwen2.5-7B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2.5-7B-Instruct-GGUF) contains GGUF format model files for [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-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.