Hugging Face's logo

MediaTek-Research
/
Breeze-7B-Base-v0_1

Text Generation
Transformers
Safetensors
Chinese
English
mistral
Inference Endpoints
text-generation-inference
Model card Files Community
1
YC-Chen commited on
Commit
5f65b85
•
1 Parent(s): e4ed3d4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -45
README.md CHANGED
@@ -25,51 +25,23 @@ and is comparable with Mistral-7B-v0.1 on MMLU and MT-Bench in English.
25
  - **Model type:** Causal decoder-only transformer language model
26
  - **Language:** English and Traditional Chinese (zh-tw)
27
 
28
- ## Performance
29
-
30
- | **[Traditional Chinese Benchmarks]** | TMMLU+ 5-shot (ACC) | DRCD 5-shot (EM) | MT-Bench-tw (Score) |
31
- |-----------------------------------------------------|---------------------|------------------|---------------------|
32
- | MediaTek-Research/Breeze-7B-Base-v0.1 | | | - |
33
- | MediaTek-Research/Breeze-7B-Instruct-v0.1 | | | |
34
- | mistralai/Mistral-7B-v0.1 | | | - |
35
- | mistralai/Mistral-7B-Instruct-v0.1 | | | |
36
- | yentinglin/Taiwan-LLM-7B-v2.1-base | | | - |
37
- | yentinglin/Taiwan-LLM-7B-v2.1-chat | | | |
38
- | yentinglin/Taiwan-LLM-13B-v2.0-base | | | - |
39
- | yentinglin/Taiwan-LLM-13B-v2.0-chat | | | |
40
- | 01-ai/Yi-6B-Base | | | - |
41
- | 01-ai/Yi-6B-Chat | | | |
42
- | 01-ai/Yi-34B-Base | | | - |
43
- | 01-ai/Yi-34B-Chat | | | |
44
- | Qwen/Qwen-7B | | | - |
45
- | Qwen/Qwen-7B-Chat | | | |
46
- | Qwen/Qwen-14B | | | - |
47
- | Qwen/Qwen-14B-Chat | | | |
48
- | gpt-3.5-turbo-0613 | | | |
49
-
50
-
51
- | **[English Benchmarks]** | MMLU 5-shot (ACC) | MT-Bench (Score) |
52
- |-----------------------------------------------------|---------------------|------------------|
53
- | MediaTek-Research/Breeze-7B-Base-v0.1 | | - |
54
- | MediaTek-Research/Breeze-7B-Instruct-v0.1 | | |
55
- | mistralai/Mistral-7B-v0.1 | | - |
56
- | mistralai/Mistral-7B-Instruct-v0.1 | | |
57
- | yentinglin/Taiwan-LLM-7B-v2.1-base | | - |
58
- | yentinglin/Taiwan-LLM-7B-v2.1-chat | | |
59
- | yentinglin/Taiwan-LLM-13B-v2.0-base | | - |
60
- | yentinglin/Taiwan-LLM-13B-v2.0-chat | | - |
61
- | 01-ai/Yi-6B-Base | | - |
62
- | 01-ai/Yi-6B-Chat | | |
63
- | 01-ai/Yi-34B-Base | | - |
64
- | 01-ai/Yi-34B-Chat | | |
65
- | Qwen/Qwen-7B | | - |
66
- | Qwen/Qwen-7B-Chat | | |
67
- | Qwen/Qwen-14B | | - |
68
- | Qwen/Qwen-14B-Chat | | |
69
- | gpt-3.5-turbo-0613 | | |
70
-
71
-
72
- | **[Inference Metrics on Traditional Chinese]** | Speed (char/sec) | Compression Ratio | Max Character Size |
73
  |--------------------------------------------------------------------|-------------------|-------------------|--------------------|
74
  | MediaTek-Research/Breeze-7B-Base-v0.1 | | | | |
75
  | mistralai/Mistral-7B-v0.1 | | | |
@@ -80,6 +52,22 @@ and is comparable with Mistral-7B-v0.1 on MMLU and MT-Bench in English.
80
  | Qwen/Qwen-7B | | | |
81
  | Qwen/Qwen-14B | | | |
82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
 
84
  ## Use in Transformers
85
 
 
25
  - **Model type:** Causal decoder-only transformer language model
26
  - **Language:** English and Traditional Chinese (zh-tw)
27
 
28
+ ## Base Model Performance
29
+
30
+ | Models | TMMLU+ (ACC) | DRCD (EM) | MMLU (ACC) |
31
+ |-----------------------------------------------------|--------------|-----------|------------|
32
+ | | 5 shot | 3 shot | 5 shot |
33
+ | MediaTek-Research/Breeze-7B-Base-v0.1 | | | |
34
+ | mistralai/Mistral-7B-v0.1 | | | |
35
+ | yentinglin/Taiwan-LLM-7B-v2.1-base | | | |
36
+ | yentinglin/Taiwan-LLM-13B-v2.0-base | | | |
37
+ | 01-ai/Yi-6B | | | |
38
+ | 01-ai/Yi-34B | | | |
39
+ | Qwen/Qwen-7B | | | |
40
+ | Qwen/Qwen-14B | | | |
41
+
42
+ ## Inference Performance
43
+
44
+ | Models | Speed (char/sec) | Compression Ratio | Max Character Size |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  |--------------------------------------------------------------------|-------------------|-------------------|--------------------|
46
  | MediaTek-Research/Breeze-7B-Base-v0.1 | | | | |
47
  | mistralai/Mistral-7B-v0.1 | | | |
 
52
  | Qwen/Qwen-7B | | | |
53
  | Qwen/Qwen-14B | | | |
54
 
55
+ ## Chat Model Performance
56
+
57
+ | Models | TMMLU+ (ACC) | DRCD (EM) | MT-Bench-tw (Score) | MMLU (ACC) | MT-Bench (Score) |
58
+ |-----------------------------------------------------|--------------|-----------|---------------------|------------|------------------|
59
+ | | 5 shot | 3 shot | 0 shot | 5 shot | 0 shot |
60
+ | MediaTek-Research/Breeze-7B-Instruct-v0.1 | | | | | |
61
+ | mistralai/Mistral-7B-Instruct-v0.1 | | | | | |
62
+ | yentinglin/Taiwan-LLM-7B-v2.1-chat | | | | | |
63
+ | yentinglin/Taiwan-LLM-13B-v2.0-chat | | | | | |
64
+ | 01-ai/Yi-6B-Chat | | | | | |
65
+ | 01-ai/Yi-34B-Chat | | | | | |
66
+ | Qwen/Qwen-7B-Chat | | | | | |
67
+ | Qwen/Qwen-14B-Chat | | | | | |
68
+ | gpt-3.5-turbo-0613 | | 76.30 | | | |
69
+
70
+
71
 
72
  ## Use in Transformers
73