MaziyarPanahi commited on
Commit
e23cafb
1 Parent(s): 475072c

Update README.md (#3)

Browse files

- Update README.md (5e9b7b799672742bb822a072406230ae8c5c5fb2)

Files changed (1) hide show
  1. README.md +48 -2
README.md CHANGED
@@ -19,9 +19,55 @@ base_model: Qwen/Qwen2-72B-Instruct
19
  model_name: MaziyarPanahi/Qwen2-72B-Instruct-v0.1
20
 
21
  ---
22
- # Qwen2-72B-Instruct-v0.1
23
 
 
 
 
24
 
25
- ## Model Details
26
  This is a fine-tuned version of the `Qwen/Qwen2-72B-Instruct` model. It aims to improve the base model across all benchmarks.
27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  model_name: MaziyarPanahi/Qwen2-72B-Instruct-v0.1
20
 
21
  ---
 
22
 
23
+ <img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
24
+
25
+ # MaziyarPanahi/Qwen2-72B-Instruct-v0.1
26
 
 
27
  This is a fine-tuned version of the `Qwen/Qwen2-72B-Instruct` model. It aims to improve the base model across all benchmarks.
28
 
29
+ # ⚡ Quantized GGUF
30
+
31
+ All GGUF models are available here: [MaziyarPanahi/Qwen2-72B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Qwen2-72B-Instruct-v0.1-GGUF)
32
+
33
+ # 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
34
+
35
+ coming soon!
36
+
37
+
38
+ ```
39
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
40
+ |--------------|------:|------|-----:|------|-----:|---|-----:|
41
+ |truthfulqa_mc2| 2|none | 0|acc |0.6761|± |0.0148|
42
+
43
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
44
+ |----------|------:|------|-----:|------|-----:|---|-----:|
45
+ |winogrande| 1|none | 5|acc |0.8248|± |0.0107|
46
+
47
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
48
+ |-------------|------:|------|-----:|--------|-----:|---|-----:|
49
+ |arc_challenge| 1|none | 25|acc |0.6852|± |0.0136|
50
+ | | |none | 25|acc_norm|0.7184|± |0.0131|
51
+
52
+ |Tasks|Version| Filter |n-shot| Metric |Value | |Stderr|
53
+ |-----|------:|----------------|-----:|-----------|-----:|---|-----:|
54
+ |gsm8k| 3|strict-match | 5|exact_match|0.8582|± |0.0096|
55
+ | | |flexible-extract| 5|exact_match|0.8893|± |0.0086|
56
+ ```
57
+
58
+ # Prompt Template
59
+
60
+ This model uses `ChatML` prompt template:
61
+
62
+ ```
63
+ <|im_start|>system
64
+ {System}
65
+ <|im_end|>
66
+ <|im_start|>user
67
+ {User}
68
+ <|im_end|>
69
+ <|im_start|>assistant
70
+ {Assistant}
71
+ ````
72
+
73
+ # How to use