BigDong commited on
Commit
245450f
·
1 Parent(s): e46a12a

update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -27,6 +27,8 @@ MiniCPM4 series are highly efficient large language models (LLMs) designed expli
27
  - [MiniCPM4-0.5B](https://huggingface.co/openbmb/MiniCPM4-0.5B): The small version of MiniCPM4, with 0.5B parameters, trained on 1T tokens.
28
  - [MiniCPM4-8B-Eagle-FRSpec](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-FRSpec): Eagle head for FRSpec, accelerating speculative inference for MiniCPM4-8B.
29
  - [MiniCPM4-8B-Eagle-FRSpec-QAT](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-FRSpec-QAT): Eagle head trained with QAT for FRSpec, efficiently integrate speculation and quantization to achieve ultra acceleration for MiniCPM4-8B.
 
 
30
  - [BitCPM4-0.5B](https://huggingface.co/openbmb/BitCPM4-0.5B): Extreme ternary quantization applied to MiniCPM4-0.5B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
31
  - [BitCPM4-1B](https://huggingface.co/openbmb/BitCPM4-1B): Extreme ternary quantization applied to MiniCPM3-1B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
32
  - [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey): Based on MiniCPM4-8B, accepts users' quiries as input and autonomously generate trustworthy, long-form survey papers.
@@ -46,7 +48,6 @@ As of now, MiniCPM4-MCP supports the following:
46
 
47
  - Cross-tool-calling capability: It can perform single- or multi-step tool calls using different tools that complies with the MCP.
48
 
49
-
50
  ## Evaluation
51
  The detailed evaluation script can be found on the [GitHub](https://github.com/OpenBMB/MiniCPM/tree/minicpm-4/demo/minicpm4/MCP) page. The evaluation results are presented below.
52
 
@@ -71,8 +72,6 @@ The detailed evaluation script can be found on the [GitHub](https://github.com/O
71
  | Whisper | 90.0 | 90.0 | 90.0 | 90.0 | 90.0 | 90.0 | 90.0 | 90.0 | 30.0 |
72
  | **Average** | **80.2** | **70.2** | **49.1** | **83.5** | **67.7** | **43.8** | **88.3** | **76.1** | **51.2** |
73
 
74
-
75
-
76
  ## Statement
77
  - As a language model, MiniCPM generates content by learning from a vast amount of text.
78
  - However, it does not possess the ability to comprehend or express personal opinions or value judgments.
 
27
  - [MiniCPM4-0.5B](https://huggingface.co/openbmb/MiniCPM4-0.5B): The small version of MiniCPM4, with 0.5B parameters, trained on 1T tokens.
28
  - [MiniCPM4-8B-Eagle-FRSpec](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-FRSpec): Eagle head for FRSpec, accelerating speculative inference for MiniCPM4-8B.
29
  - [MiniCPM4-8B-Eagle-FRSpec-QAT](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-FRSpec-QAT): Eagle head trained with QAT for FRSpec, efficiently integrate speculation and quantization to achieve ultra acceleration for MiniCPM4-8B.
30
+ - [MiniCPM4-8B-Eagle-vLLM](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-vLLM): Eagle head in vLLM format, accelerating speculative inference for MiniCPM4-8B.
31
+ - [MiniCPM4-8B-marlin-Eagle-vLLM](https://huggingface.co/openbmb/MiniCPM4-8B-marlin-Eagle-vLLM): Quantized Eagle head for vLLM format, accelerating speculative inference for MiniCPM4-8B.
32
  - [BitCPM4-0.5B](https://huggingface.co/openbmb/BitCPM4-0.5B): Extreme ternary quantization applied to MiniCPM4-0.5B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
33
  - [BitCPM4-1B](https://huggingface.co/openbmb/BitCPM4-1B): Extreme ternary quantization applied to MiniCPM3-1B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
34
  - [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey): Based on MiniCPM4-8B, accepts users' quiries as input and autonomously generate trustworthy, long-form survey papers.
 
48
 
49
  - Cross-tool-calling capability: It can perform single- or multi-step tool calls using different tools that complies with the MCP.
50
 
 
51
  ## Evaluation
52
  The detailed evaluation script can be found on the [GitHub](https://github.com/OpenBMB/MiniCPM/tree/minicpm-4/demo/minicpm4/MCP) page. The evaluation results are presented below.
53
 
 
72
  | Whisper | 90.0 | 90.0 | 90.0 | 90.0 | 90.0 | 90.0 | 90.0 | 90.0 | 30.0 |
73
  | **Average** | **80.2** | **70.2** | **49.1** | **83.5** | **67.7** | **43.8** | **88.3** | **76.1** | **51.2** |
74
 
 
 
75
  ## Statement
76
  - As a language model, MiniCPM generates content by learning from a vast amount of text.
77
  - However, it does not possess the ability to comprehend or express personal opinions or value judgments.