初始化项目，由ModelHub XC社区提供模型

Model: ThomasBaruzier/Qwen2.5-3B-Instruct-GGUF Source: Original Platform
2026-09-13 04:38:18 +08:00
commit 3564055805
36 changed files with 2839 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,67 @@
+*.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
+Qwen2.5-3B-Instruct-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-3B-Instruct-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Qwen2.5-3B-Instruct-F16.gguf
+++ b/Qwen2.5-3B-Instruct-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25908e409af8c952a17c8fda44b90e699565a90436431574f44c25d140aa5032
+size 6178317216
--- a/Qwen2.5-3B-Instruct-IQ1_M.gguf
+++ b/Qwen2.5-3B-Instruct-IQ1_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de5033270911c8bd2f1d9691d361040473b80cb71d9a5a27af6fd40343bd073
+size 850027648
--- a/Qwen2.5-3B-Instruct-IQ1_S.gguf
+++ b/Qwen2.5-3B-Instruct-IQ1_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483fc79cf22b51a1726d5dd90d9fafa161cc4bb005e432a5020f36359f78f086
+size 791094400
--- a/Qwen2.5-3B-Instruct-IQ2_M.gguf
+++ b/Qwen2.5-3B-Instruct-IQ2_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7040893e04687d722d2d73f0c6ee9509b1aa2e29d21098da05b24691d74b1073
+size 1140515968
--- a/Qwen2.5-3B-Instruct-IQ2_S.gguf
+++ b/Qwen2.5-3B-Instruct-IQ2_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918ce7280dd943f0e8f01e7c0dc6f83089a9e0e2b762cb1ff8003ac6d06ee9f1
+size 1061938304
--- a/Qwen2.5-3B-Instruct-IQ2_XS.gguf
+++ b/Qwen2.5-3B-Instruct-IQ2_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1cc61b3e3a3e1071d496497915c137f84860b9232ebd8661f3a56d393fd54c
+size 1031545984
--- a/Qwen2.5-3B-Instruct-IQ2_XXS.gguf
+++ b/Qwen2.5-3B-Instruct-IQ2_XXS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3699f107a920bd27b30e9ba0f42502dc2da431a2710862922e90390c77f11ee0
+size 948249728
--- a/Qwen2.5-3B-Instruct-IQ3_M.gguf
+++ b/Qwen2.5-3B-Instruct-IQ3_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38e8000dba7cf4182474cdc4ec53e5ad5d6b8afa161722338138d50598bb4f9
+size 1488895104
--- a/Qwen2.5-3B-Instruct-IQ3_S.gguf
+++ b/Qwen2.5-3B-Instruct-IQ3_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f528f38f8fab2808f2ce881faafafb312935ba0bfe6701f32973cc85accce5
+size 1456864384
--- a/Qwen2.5-3B-Instruct-IQ3_XS.gguf
+++ b/Qwen2.5-3B-Instruct-IQ3_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fe93fd43692d1f36485a6e6d58b79664f987dccacb9db3552f932ba1b59ab9
+size 1391836288
--- a/Qwen2.5-3B-Instruct-IQ3_XXS.gguf
+++ b/Qwen2.5-3B-Instruct-IQ3_XXS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe332d17832332828b38e5f7e4ffb6c807271a2cedae9d76f87d4183d5aec1e
+size 1282827392
--- a/Qwen2.5-3B-Instruct-IQ4_NL.gguf
+++ b/Qwen2.5-3B-Instruct-IQ4_NL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715803f2f2b7bf7742103b3cbbb18f2812446aa3554c9e9192ea74ec81c78009
+size 1825209472
--- a/Qwen2.5-3B-Instruct-IQ4_XS.gguf
+++ b/Qwen2.5-3B-Instruct-IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ce4a4bcc99a012f85f017cc7dbdddc66bda8d6e555088ec310e752e46b764b
+size 1739095168
--- a/Qwen2.5-3B-Instruct-Q2_K.gguf
+++ b/Qwen2.5-3B-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2003231bf3852c1ec83b9bdc51ba3efa052361b0a4b0615c1b81ed657ac87c
+size 1274756224
--- a/Qwen2.5-3B-Instruct-Q2_K_S.gguf
+++ b/Qwen2.5-3B-Instruct-Q2_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f5bd70a22aaaaf78e6547bf4beded8934ca1d0f9a6da84606c92b355d3f283
+size 1198128256
--- a/Qwen2.5-3B-Instruct-Q3_K_L.gguf
+++ b/Qwen2.5-3B-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7074ac93fa80c19e8979ec353af382ef30cd0604247bf1da139bde9f584694
+size 1707392128
--- a/Qwen2.5-3B-Instruct-Q3_K_M.gguf
+++ b/Qwen2.5-3B-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6ced6cba53a791c2f88d3d06264cddaca9a89afaf4c9751bdfd2e4de819a59
+size 1590475904
--- a/Qwen2.5-3B-Instruct-Q3_K_S.gguf
+++ b/Qwen2.5-3B-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eed1ecd9039a5ba955648d801478b8ded5e7316c8a2ecdd891c9241e5af265d
+size 1454357632
--- a/Qwen2.5-3B-Instruct-Q4_0.gguf
+++ b/Qwen2.5-3B-Instruct-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5421020d17cb7a027faf466ca2fefbfb61dce360ece3244be7aae2d6407ee7f8
+size 1828486272
--- a/Qwen2.5-3B-Instruct-Q4_0_4_4.gguf
+++ b/Qwen2.5-3B-Instruct-Q4_0_4_4.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c136bd63ce2bc66b9940e18cf263b4d8ba06a3e4f7d9c26b2c99ef180b2d7e8
+size 1822849952
--- a/Qwen2.5-3B-Instruct-Q4_0_4_8.gguf
+++ b/Qwen2.5-3B-Instruct-Q4_0_4_8.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148d087902ef4214b4278b3e917a6065bd61bce3d0fdf1435b77e65807d0b53a
+size 1822849952
--- a/Qwen2.5-3B-Instruct-Q4_0_8_8.gguf
+++ b/Qwen2.5-3B-Instruct-Q4_0_8_8.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbf1280d75e323eb6117264ff87cf794ce431a15d617459fb3a7a40d3005543e
+size 1822849952
--- a/Qwen2.5-3B-Instruct-Q4_1.gguf
+++ b/Qwen2.5-3B-Instruct-Q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae769cb559e8d81b5af1fa402465579f211f8d7755740565c655298b45f95a4
+size 1996258432
--- a/Qwen2.5-3B-Instruct-Q4_K_M.gguf
+++ b/Qwen2.5-3B-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1baf35a45b42ea3f5f7aee28bd98f005a215bc93cea4a6272d774f91bfe6e97c
+size 1929903232
--- a/Qwen2.5-3B-Instruct-Q4_K_S.gguf
+++ b/Qwen2.5-3B-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04175567d06bfa9f36bafbcfa273b2e7b6175c5129339219ccb5b7909c13810
+size 1834384512
--- a/Qwen2.5-3B-Instruct-Q5_0.gguf
+++ b/Qwen2.5-3B-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed64928087ab631d645b0d3823f256f69a432fb2af91594208b88646f257544
+size 2175302784
--- a/Qwen2.5-3B-Instruct-Q5_1.gguf
+++ b/Qwen2.5-3B-Instruct-Q5_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef9c274b56d9d75380c049cc87abaae36408a757e548aba30aa134e80852a19
+size 2343074944
--- a/Qwen2.5-3B-Instruct-Q5_K_M.gguf
+++ b/Qwen2.5-3B-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a87389e978f19da2b1d3c901323e12db2ea03e6659d7d0ecf9dcbb11fcaa71
+size 2224815232
--- a/Qwen2.5-3B-Instruct-Q5_K_S.gguf
+++ b/Qwen2.5-3B-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac6144e74dad8431ac0e9253011600a5bff9259c5b2d9ec0ceeadb4997a355a
+size 2169666688
--- a/Qwen2.5-3B-Instruct-Q6_K.gguf
+++ b/Qwen2.5-3B-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978a3448d884a366bf9a1ab9477649c5f92278e31795914ae1b6769f405e7d43
+size 2538159232
--- a/Qwen2.5-3B-Instruct-Q8_0.gguf
+++ b/Qwen2.5-3B-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5441226e070ec8d961a838a27c5476688fff210a2d5d64566a867d77a4b7d93c
+size 3285476480
--- a/README.md
+++ b/README.md
@@ -0,0 +1,171 @@
+---
+license: other
+license_name: qwen-research
+license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
+language:
+- zho
+- eng
+- fra
+- spa
+- por
+- deu
+- ita
+- rus
+- jpn
+- kor
+- vie
+- tha
+- ara
+pipeline_tag: text-generation
+base_model: Qwen/Qwen2.5-3B
+tags:
+- chat
+---
+
+<hr>
+
+# Llama.cpp imatrix quantizations of Qwen/Qwen2.5-3B-Instruct
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/646410e04bf9122922289dc7/gDUbZOu1ND0j-th4Q6tep.jpeg" alt="qwen" width="60%"/>
+
+Using llama.cpp commit [eca0fab](https://github.com/ggerganov/llama.cpp/commit/eca0fab) for quantization.
+
+Original model: [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
+
+All quants were made using the imatrix option and Bartowski's [calibration file](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8).
+
+<hr>
+
+# Perplexity table (the lower the better)
+
+| Quant   | Size (MB) | PPL      | Size (%) | Accuracy (%) | PPL error rate |
+| ------- | --------- | -------- | -------- | ------------ | -------------- |
+| IQ1_S   | 755       | 112.0612 | 12.81    | 8.02         | 0.97138        |
+| IQ1_M   | 811       | 42.7456  | 13.76    | 21.03        | 0.34718        |
+| IQ2_XXS | 905       | 25.2117  | 15.36    | 35.65        | 0.20222        |
+| IQ2_XS  | 984       | 15.9149  | 16.7     | 56.48        | 0.11965        |
+| IQ2_S   | 1013      | 14.5975  | 17.19    | 61.58        | 0.1082         |
+| IQ2_M   | 1088      | 12.8779  | 18.46    | 69.8         | 0.09436        |
+| Q2_K_S  | 1143      | 13.0878  | 19.4     | 68.68        | 0.09636        |
+| Q2_K    | 1216      | 11.8001  | 20.63    | 76.18        | 0.08674        |
+| IQ3_XXS | 1224      | 10.6049  | 20.77    | 84.76        | 0.07572        |
+| IQ3_XS  | 1328      | 10.0306  | 22.54    | 89.61        | 0.06975        |
+| Q3_K_S  | 1387      | 15.5457  | 23.54    | 57.82        | 0.11941        |
+| IQ3_S   | 1390      | 9.9591   | 23.59    | 90.26        | 0.06984        |
+| IQ3_M   | 1420      | 9.9957   | 24.1     | 89.93        | 0.06962        |
+| Q3_K_M  | 1517      | 14.0989  | 25.74    | 63.76        | 0.10568        |
+| Q3_K_L  | 1629      | 13.8579  | 27.64    | 64.86        | 0.10372        |
+| IQ4_XS  | 1659      | 9.2935   | 28.15    | 96.72        | 0.06517        |
+| IQ4_NL  | 1741      | 9.2824   | 29.54    | 96.84        | 0.06503        |
+| Q4_0    | 1744      | 9.485    | 29.59    | 94.77        | 0.06626        |
+| Q4_K_S  | 1750      | 9.2573   | 29.7     | 97.1         | 0.06485        |
+| Q4_K_M  | 1841      | 9.2305   | 31.24    | 97.38        | 0.06475        |
+| Q4_1    | 1904      | 9.2746   | 32.31    | 96.92        | 0.06512        |
+| Q5_K_S  | 2070      | 9.1338   | 35.13    | 98.41        | 0.06402        |
+| Q5_0    | 2075      | 9.1513   | 35.21    | 98.22        | 0.06413        |
+| Q5_K_M  | 2122      | 9.1339   | 36.01    | 98.41        | 0.06407        |
+| Q5_1    | 2235      | 9.1231   | 37.93    | 98.53        | 0.06386        |
+| Q6_K    | 2421      | 9.069    | 41.08    | 99.12        | 0.06342        |
+| Q8_0    | 3134      | 9.0114   | 53.18    | 99.75        | 0.06285        |
+| F16     | 5893      | 8.9888   | 100      | 100          | 0.06268        |
+
+<hr>
+
+# Qwen2.5-3B-Instruct
+
+## Introduction
+
+Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
+
+- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
+- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
+- **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
+- **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. 
+
+**This repo contains the instruction-tuned 3B Qwen2.5 model**, which has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining & Post-training
+- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
+- Number of Parameters: 3.09B
+- Number of Paramaters (Non-Embedding): 2.77B
+- Number of Layers: 36
+- Number of Attention Heads (GQA): 16 for Q and 2 for KV
+- Context Length: Full 32,768 tokens and generation 8192 tokens
+
+For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+
+## Requirements
+
+The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
+
+With `transformers<4.37.0`, you will encounter the following error:
+```
+KeyError: 'qwen2'
+```
+
+## Quickstart
+
+Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen2.5-3B-Instruct"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```
+
+
+## Evaluation & Performance
+
+Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/).
+
+For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen2.5,
+    title = {Qwen2.5: A Party of Foundation Models},
+    url = {https://qwenlm.github.io/blog/qwen2.5/},
+    author = {Qwen Team},
+    month = {September},
+    year = {2024}
+}
+
+@article{qwen2,
+      title={Qwen2 Technical Report}, 
+      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
+      journal={arXiv preprint arXiv:2407.10671},
+      year={2024}
+}
+```
--- a/calibration_datav3.txt
+++ b/calibration_datav3.txt
--- a/imatrix.dat
+++ b/imatrix.dat
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e68abe89b59ea10b13d7e0a92c160464c46800d717ca79eefcd1edb18ea786
+size 3362981
--- a/perplexity.md
+++ b/perplexity.md
@@ -0,0 +1,23 @@
+
+Qwen2.5-3B-Instruct
+Quant	Size (MB)	PPL	Size (%)	Accuracy (%)	PPL error rate
+IQ1_S	755	112.0612			0.97138
+IQ1_M	811	42.7456			0.34718
+IQ2_XXS	905	25.2117			0.20222
+IQ2_XS	984	15.9149			0.11965
+IQ2_S	1013	14.5975			0.10820
+IQ2_M	1088	12.8779			0.09436
+Q2_K_S	1143	13.0878			0.09636
+Q2_K	1216	11.8001			0.08674
+IQ3_XXS	1224	10.6049			0.07572
+IQ3_XS	1328	10.0306			0.06975
+Q3_K_S	1387	15.5457			0.11941
+IQ3_S	1390	9.9591			0.06984
+IQ3_M	1420	9.9957			0.06962
+Q3_K_M	1517	14.0989			0.10568
+Q3_K_L	1629	13.8579			0.10372
+IQ4_XS	1659	9.2935			0.06517
+IQ4_NL	1741	9.2824			0.06503
+Q4_0	1744	9.4850			0.06626
+Q4_K_S	1750	9.2573			0.06485
+Q4_K_M	1841	9.2305			0.06475