Upload folder using huggingface_hub
#1
by
MaziyarPanahi
- opened
- .gitattributes +17 -0
- Qwen2.5-3B-Instruct-GGUF_imatrix.dat +3 -0
- Qwen2.5-3B-Instruct.IQ1_M.gguf +3 -0
- Qwen2.5-3B-Instruct.IQ1_S.gguf +3 -0
- Qwen2.5-3B-Instruct.IQ2_XS.gguf +3 -0
- Qwen2.5-3B-Instruct.IQ3_XS.gguf +3 -0
- Qwen2.5-3B-Instruct.IQ4_XS.gguf +3 -0
- Qwen2.5-3B-Instruct.Q2_K.gguf +3 -0
- Qwen2.5-3B-Instruct.Q3_K_L.gguf +3 -0
- Qwen2.5-3B-Instruct.Q3_K_M.gguf +3 -0
- Qwen2.5-3B-Instruct.Q3_K_S.gguf +3 -0
- Qwen2.5-3B-Instruct.Q4_K_M.gguf +3 -0
- Qwen2.5-3B-Instruct.Q4_K_S.gguf +3 -0
- Qwen2.5-3B-Instruct.Q5_K_M.gguf +3 -0
- Qwen2.5-3B-Instruct.Q5_K_S.gguf +3 -0
- Qwen2.5-3B-Instruct.Q6_K.gguf +3 -0
- Qwen2.5-3B-Instruct.Q8_0.gguf +3 -0
- Qwen2.5-3B-Instruct.fp16.gguf +3 -0
- README.md +46 -0
.gitattributes
CHANGED
@@ -33,3 +33,20 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
Qwen2.5-3B-Instruct-GGUF_imatrix.dat filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen2.5-3B-Instruct.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen2.5-3B-Instruct.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen2.5-3B-Instruct.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen2.5-3B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen2.5-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen2.5-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen2.5-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen2.5-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen2.5-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen2.5-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen2.5-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
Qwen2.5-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
49 |
+
Qwen2.5-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
50 |
+
Qwen2.5-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
51 |
+
Qwen2.5-3B-Instruct.fp16.gguf filter=lfs diff=lfs merge=lfs -text
|
52 |
+
Qwen2.5-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen2.5-3B-Instruct-GGUF_imatrix.dat
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:851bf69b555f19410689c76946d363a204150e1515f5a7cd0743dd11e74e588e
|
3 |
+
size 3362966
|
Qwen2.5-3B-Instruct.IQ1_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10034eff57f7da53a1bfe974b891d78a39ba8f57925cd318128d953f71d8452b
|
3 |
+
size 850027680
|
Qwen2.5-3B-Instruct.IQ1_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94b24084e8f8004d080c9b3dba8fde810cbd7982a4492719145b3df1b51400e2
|
3 |
+
size 791094432
|
Qwen2.5-3B-Instruct.IQ2_XS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92a82f01fd63d42570792d2bbb41088117aa0bee6ade11ad441881914444457a
|
3 |
+
size 1031546016
|
Qwen2.5-3B-Instruct.IQ3_XS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3699e8a2b62c378645fc1afde06e2f147d7afc8669ccf82ce6b9c57202250b6b
|
3 |
+
size 1391836320
|
Qwen2.5-3B-Instruct.IQ4_XS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e794ef49d36842e3d1702ab2d1adbfb8026631a82f46315c61534da55f8c6f3a
|
3 |
+
size 1739095200
|
Qwen2.5-3B-Instruct.Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b67ab712f7c83149769ff9f402e1bf4d95f8498fe0bcec546bd0127eff1ce4f7
|
3 |
+
size 1274756256
|
Qwen2.5-3B-Instruct.Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85f72eb3dcd0332512371c349d52ce987df11f70f02380a513bf53d0fa2c99d2
|
3 |
+
size 1707392160
|
Qwen2.5-3B-Instruct.Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec3aabd22f21016aef2de3f8ce9aa1e207cf498463a5ef292061f08993482559
|
3 |
+
size 1590475936
|
Qwen2.5-3B-Instruct.Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40dac85d0f2136abfbda6608223bcabe1624289b4bf72f6414ae6a3687734369
|
3 |
+
size 1454357664
|
Qwen2.5-3B-Instruct.Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7230acd716226852ed1bafad0b51137903a8924c798322e8dfb679315d78eae
|
3 |
+
size 1929903264
|
Qwen2.5-3B-Instruct.Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b08ed008a55a94c66fe84baedf635c1e2bc26d72a8894ad37455e3949e3bccd
|
3 |
+
size 1834384544
|
Qwen2.5-3B-Instruct.Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d11dde20bd2c8bc4ea46baa69adaa0312f31df296e9ed13f37de04c5556bd6fa
|
3 |
+
size 2224815264
|
Qwen2.5-3B-Instruct.Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08df1bbffe78834acc2aad543d70314df8ed8fdb0595804074830a646d2d8725
|
3 |
+
size 2169666720
|
Qwen2.5-3B-Instruct.Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:195299941ed34cbfa658c84bb28e233ffd43ce62fb9b5c29304ba1ef39faad9f
|
3 |
+
size 2538159264
|
Qwen2.5-3B-Instruct.Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33ed602236a167de033bc81c06f3cb5c7058e92b5900fbdd32efb6aa468c2709
|
3 |
+
size 3285476512
|
Qwen2.5-3B-Instruct.fp16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d5747748a796081d1284aedcc40ab6948d32deead23314ef06a5b77f2cb564c
|
3 |
+
size 6178317248
|
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- quantized
|
4 |
+
- 2-bit
|
5 |
+
- 3-bit
|
6 |
+
- 4-bit
|
7 |
+
- 5-bit
|
8 |
+
- 6-bit
|
9 |
+
- 8-bit
|
10 |
+
- GGUF
|
11 |
+
- text-generation
|
12 |
+
- text-generation
|
13 |
+
model_name: Qwen2.5-3B-Instruct-GGUF
|
14 |
+
base_model: Qwen/Qwen2.5-3B-Instruct
|
15 |
+
inference: false
|
16 |
+
model_creator: Qwen
|
17 |
+
pipeline_tag: text-generation
|
18 |
+
quantized_by: MaziyarPanahi
|
19 |
+
---
|
20 |
+
# [MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF)
|
21 |
+
- Model creator: [Qwen](https://huggingface.co/Qwen)
|
22 |
+
- Original model: [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
|
23 |
+
|
24 |
+
## Description
|
25 |
+
[MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2.5-3B-Instruct-GGUF) contains GGUF format model files for [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
|
26 |
+
|
27 |
+
### About GGUF
|
28 |
+
|
29 |
+
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.
|
30 |
+
|
31 |
+
Here is an incomplete list of clients and libraries that are known to support GGUF:
|
32 |
+
|
33 |
+
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
|
34 |
+
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
|
35 |
+
* [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.
|
36 |
+
* [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.
|
37 |
+
* [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.
|
38 |
+
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
|
39 |
+
* [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.
|
40 |
+
* [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.
|
41 |
+
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
|
42 |
+
* [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.
|
43 |
+
|
44 |
+
## Special thanks
|
45 |
+
|
46 |
+
🙏 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.
|