Smokeweaver
commited on
Commit
•
6aa30cf
1
Parent(s):
3eb9801
Update model tags
Browse files
README.md
CHANGED
@@ -1,3 +1,147 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- mistral
|
7 |
+
- instruct
|
8 |
+
- finetune
|
9 |
+
- chatml
|
10 |
+
- gpt4
|
11 |
+
- synthetic data
|
12 |
+
- distillation
|
13 |
+
- dpo
|
14 |
+
- rlhf
|
15 |
+
- laser
|
16 |
+
- quantized
|
17 |
+
- 4-bit
|
18 |
+
- AWQ
|
19 |
+
- text-generation
|
20 |
+
- autotrain_compatible
|
21 |
+
- endpoints_compatible
|
22 |
+
datasets:
|
23 |
+
- mlabonne/chatml_dpo_pairs
|
24 |
+
base_model: teknium/OpenHermes-2.5-Mistral-7B
|
25 |
+
model-index:
|
26 |
+
- name: NeuralHermes-2.5-Mistral-7B-laser
|
27 |
+
results:
|
28 |
+
- task:
|
29 |
+
type: text-generation
|
30 |
+
name: Text Generation
|
31 |
+
dataset:
|
32 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
33 |
+
type: ai2_arc
|
34 |
+
config: ARC-Challenge
|
35 |
+
split: test
|
36 |
+
args:
|
37 |
+
num_few_shot: 25
|
38 |
+
metrics:
|
39 |
+
- type: acc_norm
|
40 |
+
value: 66.38
|
41 |
+
name: normalized accuracy
|
42 |
+
source:
|
43 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
44 |
+
name: Open LLM Leaderboard
|
45 |
+
- task:
|
46 |
+
type: text-generation
|
47 |
+
name: Text Generation
|
48 |
+
dataset:
|
49 |
+
name: HellaSwag (10-Shot)
|
50 |
+
type: hellaswag
|
51 |
+
split: validation
|
52 |
+
args:
|
53 |
+
num_few_shot: 10
|
54 |
+
metrics:
|
55 |
+
- type: acc_norm
|
56 |
+
value: 85.09
|
57 |
+
name: normalized accuracy
|
58 |
+
source:
|
59 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
60 |
+
name: Open LLM Leaderboard
|
61 |
+
- task:
|
62 |
+
type: text-generation
|
63 |
+
name: Text Generation
|
64 |
+
dataset:
|
65 |
+
name: MMLU (5-Shot)
|
66 |
+
type: cais/mmlu
|
67 |
+
config: all
|
68 |
+
split: test
|
69 |
+
args:
|
70 |
+
num_few_shot: 5
|
71 |
+
metrics:
|
72 |
+
- type: acc
|
73 |
+
value: 63.43
|
74 |
+
name: accuracy
|
75 |
+
source:
|
76 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
77 |
+
name: Open LLM Leaderboard
|
78 |
+
- task:
|
79 |
+
type: text-generation
|
80 |
+
name: Text Generation
|
81 |
+
dataset:
|
82 |
+
name: TruthfulQA (0-shot)
|
83 |
+
type: truthful_qa
|
84 |
+
config: multiple_choice
|
85 |
+
split: validation
|
86 |
+
args:
|
87 |
+
num_few_shot: 0
|
88 |
+
metrics:
|
89 |
+
- type: mc2
|
90 |
+
value: 54.95
|
91 |
+
source:
|
92 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
93 |
+
name: Open LLM Leaderboard
|
94 |
+
- task:
|
95 |
+
type: text-generation
|
96 |
+
name: Text Generation
|
97 |
+
dataset:
|
98 |
+
name: Winogrande (5-shot)
|
99 |
+
type: winogrande
|
100 |
+
config: winogrande_xl
|
101 |
+
split: validation
|
102 |
+
args:
|
103 |
+
num_few_shot: 5
|
104 |
+
metrics:
|
105 |
+
- type: acc
|
106 |
+
value: 78.14
|
107 |
+
name: accuracy
|
108 |
+
source:
|
109 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
110 |
+
name: Open LLM Leaderboard
|
111 |
+
- task:
|
112 |
+
type: text-generation
|
113 |
+
name: Text Generation
|
114 |
+
dataset:
|
115 |
+
name: GSM8k (5-shot)
|
116 |
+
type: gsm8k
|
117 |
+
config: main
|
118 |
+
split: test
|
119 |
+
args:
|
120 |
+
num_few_shot: 5
|
121 |
+
metrics:
|
122 |
+
- type: acc
|
123 |
+
value: 55.72
|
124 |
+
name: accuracy
|
125 |
+
source:
|
126 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B-laser
|
127 |
+
name: Open LLM Leaderboard
|
128 |
+
library_name: transformers
|
129 |
+
model_creator: mlabonne
|
130 |
+
model_name: Darewin-7B
|
131 |
+
model_type: mistral
|
132 |
+
pipeline_tag: text-generation
|
133 |
+
inference: false
|
134 |
+
prompt_template: '<|im_start|>system
|
135 |
+
|
136 |
+
{system_message}<|im_end|>
|
137 |
+
|
138 |
+
<|im_start|>user
|
139 |
+
|
140 |
+
{prompt}<|im_end|>
|
141 |
+
|
142 |
+
<|im_start|>assistant
|
143 |
+
|
144 |
+
'
|
145 |
+
quantized_by: Suparious
|
146 |
---
|
147 |
+
# mlabonne/NeuralHermes-2.5-Mistral-7B-laser AWQ
|