Hugging Face's logo

lesserfield
/
fiona-7B-v0.2

Text Generation
Transformers
Safetensors
English
mistral
text-generation-inference
unsloth
trl
sft
conversational
Eval Results
Inference Endpoints
Model card Files Community
1
Nizam commited on
Commit
9079920
·
verified ·
1 Parent(s): 337d5d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -1
README.md CHANGED
@@ -10,6 +10,57 @@ tags:
10
  - trl
11
  - sft
12
  base_model: BarraHome/Mistroll-7B-v2.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
 
15
  # Uploaded model
@@ -20,4 +71,4 @@ base_model: BarraHome/Mistroll-7B-v2.2
20
 
21
  This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
22
 
23
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
10
  - trl
11
  - sft
12
  base_model: BarraHome/Mistroll-7B-v2.2
13
+ model-index:
14
+ - name: fiona-7B-v0.2
15
+ results:
16
+ - task:
17
+ type: text-generation
18
+ metrics:
19
+ - name: AI2 Reasoning Challenge
20
+ type: AI2 Reasoning Challenge
21
+ value: 65.1
22
+ source:
23
+ name: Open LLM Leaderboard
24
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
25
+ - task:
26
+ type: text-generation
27
+ metrics:
28
+ - name: HellaSwag
29
+ type: HellaSwag
30
+ value: 85.49
31
+ source:
32
+ name: Open LLM Leaderboard
33
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
34
+ - task:
35
+ type: text-generation
36
+ metrics:
37
+ - name: MMLU
38
+ type: MMLU
39
+ value: 62.78
40
+ source:
41
+ name: Open LLM Leaderboard
42
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
43
+ - task:
44
+ type: text-generation
45
+ metrics:
46
+ - name: TruthfulQA
47
+ type: TruthfulQA
48
+ value: 56.53
49
+ - task:
50
+ type: text-generation
51
+ metrics:
52
+ - name: Winogrande
53
+ type: Winogrande
54
+ value: 78.77
55
+ - task:
56
+ type: text-generation
57
+ metrics:
58
+ - name: GSM8K
59
+ type: GSM8K
60
+ value: 68.31
61
+ source:
62
+ name: Open LLM Leaderboard
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
64
  ---
65
 
66
  # Uploaded model
 
71
 
72
  This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
73
 
74
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)