Hugging Face's logo

c01zaut
/
Qwen2.5-14B-Instruct-rk3588-1.1.1

Text Generation
Transformers
Safetensors
English
qwen2
chat
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
c01zaut commited on
Commit
377b34d
•
1 Parent(s): 0844ac7

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. .gitattributes +0 -18
  2. Qwen2.5-14B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-0.0.rkllm +1 -1
  3. Qwen2.5-14B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-0.5.rkllm +1 -1
  4. Qwen2.5-14B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-1.0.rkllm +1 -1
  5. Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.0.rkllm +1 -1
  6. Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.5.rkllm +1 -1
  7. Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-1.0.rkllm +1 -1
  8. README.md +1 -2
.gitattributes CHANGED
@@ -39,21 +39,3 @@ Qwen2.5-14B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-1.0.rkllm filter=lfs diff=lf
39
  Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
40
  Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
41
  Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
42
- Qwen2.5-14B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
43
- Qwen2.5-14B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
44
- Qwen2.5-14B-Instruct-rk3588-w8a8_g128-opt-0-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
45
- Qwen2.5-14B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
46
- Qwen2.5-14B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
47
- Qwen2.5-14B-Instruct-rk3588-w8a8_g128-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
48
- Qwen2.5-14B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
49
- Qwen2.5-14B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
50
- Qwen2.5-14B-Instruct-rk3588-w8a8_g256-opt-0-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
51
- Qwen2.5-14B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
52
- Qwen2.5-14B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
53
- Qwen2.5-14B-Instruct-rk3588-w8a8_g256-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
54
- Qwen2.5-14B-Instruct-rk3588-w8a8_g512-opt-0-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
55
- Qwen2.5-14B-Instruct-rk3588-w8a8_g512-opt-0-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
56
- Qwen2.5-14B-Instruct-rk3588-w8a8_g512-opt-0-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
57
- Qwen2.5-14B-Instruct-rk3588-w8a8_g512-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
58
- Qwen2.5-14B-Instruct-rk3588-w8a8_g512-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
59
- Qwen2.5-14B-Instruct-rk3588-w8a8_g512-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
 
39
  Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text
40
  Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.5.rkllm filter=lfs diff=lfs merge=lfs -text
41
  Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-14B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-0.0.rkllm CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09ee1a116b554500797c37fa5e256562e5e60ee82a85ed7938cd2c08eef615d2
3
  size 15595364468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253aa1494fb8a4e6ac90d441bb4c09eee0da129368a4d84759bad6bb67adf9bb
3
  size 15595364468
Qwen2.5-14B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-0.5.rkllm CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09ee1a116b554500797c37fa5e256562e5e60ee82a85ed7938cd2c08eef615d2
3
  size 15595364468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253aa1494fb8a4e6ac90d441bb4c09eee0da129368a4d84759bad6bb67adf9bb
3
  size 15595364468
Qwen2.5-14B-Instruct-rk3588-w8a8-opt-0-hybrid-ratio-1.0.rkllm CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09ee1a116b554500797c37fa5e256562e5e60ee82a85ed7938cd2c08eef615d2
3
  size 15595364468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253aa1494fb8a4e6ac90d441bb4c09eee0da129368a4d84759bad6bb67adf9bb
3
  size 15595364468
Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.0.rkllm CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a56e4f963d754030eca5681081ed2aace6b1cd2d3c9d5ee9c8ed2a17c59bd038
3
  size 15595364468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6627394521a3b1fc2cc43ebc0bdc270608b162a7bd246e683aed6264223b31bc
3
  size 15595364468
Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-0.5.rkllm CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a56e4f963d754030eca5681081ed2aace6b1cd2d3c9d5ee9c8ed2a17c59bd038
3
  size 15595364468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6627394521a3b1fc2cc43ebc0bdc270608b162a7bd246e683aed6264223b31bc
3
  size 15595364468
Qwen2.5-14B-Instruct-rk3588-w8a8-opt-1-hybrid-ratio-1.0.rkllm CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a56e4f963d754030eca5681081ed2aace6b1cd2d3c9d5ee9c8ed2a17c59bd038
3
  size 15595364468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6627394521a3b1fc2cc43ebc0bdc270608b162a7bd246e683aed6264223b31bc
3
  size 15595364468
README.md CHANGED
@@ -11,8 +11,7 @@ tags:
11
  ---
12
  # Qwen2.5-14B-Instruct-RK3588-1.1.1
13
 
14
- This version of Qwen2.5-14B-Instruct has been converted to run on the RK3588 NPU using ['w8a8', 'w8a8_g128', 'w8a8_g256', 'w8a8_g512'] quantization.
15
-
16
  This model has been optimized with the following LoRA:
17
 
18
  Compatible with RKLLM version: 1.1.1
 
11
  ---
12
  # Qwen2.5-14B-Instruct-RK3588-1.1.1
13
 
14
+ This version of Qwen2.5-14B-Instruct has been converted to run on the RK3588 NPU using ['w8a8'] quantization.
 
15
  This model has been optimized with the following LoRA:
16
 
17
  Compatible with RKLLM version: 1.1.1