Hugging Face's logo

RichardErkhov
/
vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
497a719
·
verified ·
1 Parent(s): cc4ff49

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +169 -0
README.md ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ OpenHermes-Qwen1.5-1.8B - GGUF
11
+ - Model creator: https://huggingface.co/vicgalle/
12
+ - Original model: https://huggingface.co/vicgalle/OpenHermes-Qwen1.5-1.8B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [OpenHermes-Qwen1.5-1.8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q2_K.gguf) | Q2_K | 0.79GB |
18
+ | [OpenHermes-Qwen1.5-1.8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.IQ3_XS.gguf) | IQ3_XS | 0.86GB |
19
+ | [OpenHermes-Qwen1.5-1.8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.IQ3_S.gguf) | IQ3_S | 0.89GB |
20
+ | [OpenHermes-Qwen1.5-1.8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q3_K_S.gguf) | Q3_K_S | 0.89GB |
21
+ | [OpenHermes-Qwen1.5-1.8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.IQ3_M.gguf) | IQ3_M | 0.92GB |
22
+ | [OpenHermes-Qwen1.5-1.8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q3_K.gguf) | Q3_K | 0.95GB |
23
+ | [OpenHermes-Qwen1.5-1.8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q3_K_M.gguf) | Q3_K_M | 0.95GB |
24
+ | [OpenHermes-Qwen1.5-1.8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q3_K_L.gguf) | Q3_K_L | 0.98GB |
25
+ | [OpenHermes-Qwen1.5-1.8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.IQ4_XS.gguf) | IQ4_XS | 1.01GB |
26
+ | [OpenHermes-Qwen1.5-1.8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q4_0.gguf) | Q4_0 | 1.04GB |
27
+ | [OpenHermes-Qwen1.5-1.8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.IQ4_NL.gguf) | IQ4_NL | 1.05GB |
28
+ | [OpenHermes-Qwen1.5-1.8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q4_K_S.gguf) | Q4_K_S | 1.08GB |
29
+ | [OpenHermes-Qwen1.5-1.8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q4_K.gguf) | Q4_K | 1.13GB |
30
+ | [OpenHermes-Qwen1.5-1.8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q4_K_M.gguf) | Q4_K_M | 1.13GB |
31
+ | [OpenHermes-Qwen1.5-1.8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q4_1.gguf) | Q4_1 | 1.13GB |
32
+ | [OpenHermes-Qwen1.5-1.8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q5_0.gguf) | Q5_0 | 1.22GB |
33
+ | [OpenHermes-Qwen1.5-1.8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q5_K_S.gguf) | Q5_K_S | 1.24GB |
34
+ | [OpenHermes-Qwen1.5-1.8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q5_K.gguf) | Q5_K | 1.28GB |
35
+ | [OpenHermes-Qwen1.5-1.8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q5_K_M.gguf) | Q5_K_M | 1.28GB |
36
+ | [OpenHermes-Qwen1.5-1.8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q5_1.gguf) | Q5_1 | 1.31GB |
37
+ | [OpenHermes-Qwen1.5-1.8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q6_K.gguf) | Q6_K | 1.47GB |
38
+ | [OpenHermes-Qwen1.5-1.8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_OpenHermes-Qwen1.5-1.8B-gguf/blob/main/OpenHermes-Qwen1.5-1.8B.Q8_0.gguf) | Q8_0 | 1.82GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: apache-2.0
46
+ library_name: transformers
47
+ datasets:
48
+ - vicgalle/OpenHermesPreferences-1k
49
+ model-index:
50
+ - name: OpenHermes-Qwen1.5-1.8B
51
+ results:
52
+ - task:
53
+ type: text-generation
54
+ name: Text Generation
55
+ dataset:
56
+ name: AI2 Reasoning Challenge (25-Shot)
57
+ type: ai2_arc
58
+ config: ARC-Challenge
59
+ split: test
60
+ args:
61
+ num_few_shot: 25
62
+ metrics:
63
+ - type: acc_norm
64
+ value: 37.8
65
+ name: normalized accuracy
66
+ source:
67
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/OpenHermes-Qwen1.5-1.8B
68
+ name: Open LLM Leaderboard
69
+ - task:
70
+ type: text-generation
71
+ name: Text Generation
72
+ dataset:
73
+ name: HellaSwag (10-Shot)
74
+ type: hellaswag
75
+ split: validation
76
+ args:
77
+ num_few_shot: 10
78
+ metrics:
79
+ - type: acc_norm
80
+ value: 59.73
81
+ name: normalized accuracy
82
+ source:
83
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/OpenHermes-Qwen1.5-1.8B
84
+ name: Open LLM Leaderboard
85
+ - task:
86
+ type: text-generation
87
+ name: Text Generation
88
+ dataset:
89
+ name: MMLU (5-Shot)
90
+ type: cais/mmlu
91
+ config: all
92
+ split: test
93
+ args:
94
+ num_few_shot: 5
95
+ metrics:
96
+ - type: acc
97
+ value: 45.8
98
+ name: accuracy
99
+ source:
100
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/OpenHermes-Qwen1.5-1.8B
101
+ name: Open LLM Leaderboard
102
+ - task:
103
+ type: text-generation
104
+ name: Text Generation
105
+ dataset:
106
+ name: TruthfulQA (0-shot)
107
+ type: truthful_qa
108
+ config: multiple_choice
109
+ split: validation
110
+ args:
111
+ num_few_shot: 0
112
+ metrics:
113
+ - type: mc2
114
+ value: 42.28
115
+ source:
116
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/OpenHermes-Qwen1.5-1.8B
117
+ name: Open LLM Leaderboard
118
+ - task:
119
+ type: text-generation
120
+ name: Text Generation
121
+ dataset:
122
+ name: Winogrande (5-shot)
123
+ type: winogrande
124
+ config: winogrande_xl
125
+ split: validation
126
+ args:
127
+ num_few_shot: 5
128
+ metrics:
129
+ - type: acc
130
+ value: 60.22
131
+ name: accuracy
132
+ source:
133
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/OpenHermes-Qwen1.5-1.8B
134
+ name: Open LLM Leaderboard
135
+ - task:
136
+ type: text-generation
137
+ name: Text Generation
138
+ dataset:
139
+ name: GSM8k (5-shot)
140
+ type: gsm8k
141
+ config: main
142
+ split: test
143
+ args:
144
+ num_few_shot: 5
145
+ metrics:
146
+ - type: acc
147
+ value: 23.88
148
+ name: accuracy
149
+ source:
150
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/OpenHermes-Qwen1.5-1.8B
151
+ name: Open LLM Leaderboard
152
+ ---
153
+
154
+
155
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
156
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__OpenHermes-Qwen1.5-1.8B)
157
+
158
+ | Metric |Value|
159
+ |---------------------------------|----:|
160
+ |Avg. |44.95|
161
+ |AI2 Reasoning Challenge (25-Shot)|37.80|
162
+ |HellaSwag (10-Shot) |59.73|
163
+ |MMLU (5-Shot) |45.80|
164
+ |TruthfulQA (0-shot) |42.28|
165
+ |Winogrande (5-shot) |60.22|
166
+ |GSM8k (5-shot) |23.88|
167
+
168
+
169
+