HanzoHuang commited on
Commit
3d9ed64
·
verified ·
1 Parent(s): 5b7a302

Document RKLLM artifacts and checksums

Browse files
Files changed (1) hide show
  1. README.md +51 -0
README.md CHANGED
@@ -1,3 +1,54 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: openbmb/MiniCPM3-4B
4
+ pipeline_tag: text-generation
5
+ library_name: rkllm
6
+ tags:
7
+ - rkllm
8
+ - rockchip
9
+ - rk3576
10
+ - rk3588
11
+ - minicpm3
12
  ---
13
+
14
+ # MiniCPM3-4B-RKLLM
15
+
16
+ RKLLM-converted MiniCPM3-4B language-model artifacts for Rockchip RK3576 and RK3588 NPUs.
17
+
18
+ These are hardware-specific `.rkllm` binaries, not Transformers checkpoints. They require a compatible Rockchip RKLLM runtime and cannot be loaded directly with Transformers, llama.cpp, or Ollama.
19
+
20
+ ## Base model
21
+
22
+ - Upstream model: [openbmb/MiniCPM3-4B](https://huggingface.co/openbmb/MiniCPM3-4B)
23
+ - License: Apache-2.0
24
+ - Model type: LLM (text only)
25
+
26
+ ## Conversion and variants
27
+
28
+ Converted with RKLLM Toolkit 1.3.0. Use a file built for the exact target SoC.
29
+
30
+ | Target | Quantization | File | SHA256 |
31
+ | --- | --- | --- | --- |
32
+ | RK3576 | W4A16 (g128) | [MiniCPM3-4B_RK3576_w4a16_g128.rkllm](RK3576/MiniCPM3-4B_RK3576_w4a16_g128.rkllm) | `ec05211d17c4bb05a685588ff335608233b59722f6ecc296976d61dbc88c4128` |
33
+ | RK3576 | W8A8 | [MiniCPM3-4B_RK3576_w8a8.rkllm](RK3576/MiniCPM3-4B_RK3576_w8a8.rkllm) | `3795c6a22e5f12de0c4243fc187da55f516b530de3125734874d340856160aec` |
34
+ | RK3588 | W8A8 | [MiniCPM3-4B_RK3588_w8a8.rkllm](RK3588/MiniCPM3-4B_RK3588_w8a8.rkllm) | `3815a59593df7aebda90f86844caf2fd625d9d0e996e35aa31fd74790d10b130` |
35
+
36
+ The repository also includes `MiniCPM3-4B_data_quant.json`, used as calibration data during conversion.
37
+
38
+ ## Usage
39
+
40
+ ```bash
41
+ hf download HanzoHuang/MiniCPM3-4B-RKLLM \
42
+ RK3576/MiniCPM3-4B_RK3576_w4a16_g128.rkllm \
43
+ --local-dir MiniCPM3-4B-RKLLM
44
+ ```
45
+
46
+ Run the downloaded file with the RKLLM runtime and the upstream MiniCPM3 chat template. For Docker deployment, see [Hanzo-Huang/rkllm-docker](https://github.com/Hanzo-Huang/rkllm-docker).
47
+
48
+ ## Limitations
49
+
50
+ These artifacts are target-specific conversions. Validate quality, memory use, and runtime compatibility on your own hardware.
51
+
52
+ ## Acknowledgements
53
+
54
+ Thanks to OpenBMB, Rockchip, and the RKLLM community.