Hugging Face's logo

RichardErkhov
/
Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
1
RichardErkhov commited on
Commit
7317e6e
•
1 Parent(s): 77b0708

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +172 -0
README.md ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ Replete-LLM-V2.5-Qwen-14b - GGUF
11
+ - Model creator: https://huggingface.co/Replete-AI/
12
+ - Original model: https://huggingface.co/Replete-AI/Replete-LLM-V2.5-Qwen-14b/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Replete-LLM-V2.5-Qwen-14b.Q2_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q2_K.gguf) | Q2_K | 5.37GB |
18
+ | [Replete-LLM-V2.5-Qwen-14b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ3_XS.gguf) | IQ3_XS | 5.94GB |
19
+ | [Replete-LLM-V2.5-Qwen-14b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ3_S.gguf) | IQ3_S | 6.23GB |
20
+ | [Replete-LLM-V2.5-Qwen-14b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q3_K_S.gguf) | Q3_K_S | 6.2GB |
21
+ | [Replete-LLM-V2.5-Qwen-14b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ3_M.gguf) | IQ3_M | 6.44GB |
22
+ | [Replete-LLM-V2.5-Qwen-14b.Q3_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q3_K.gguf) | Q3_K | 6.84GB |
23
+ | [Replete-LLM-V2.5-Qwen-14b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q3_K_M.gguf) | Q3_K_M | 6.84GB |
24
+ | [Replete-LLM-V2.5-Qwen-14b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q3_K_L.gguf) | Q3_K_L | 7.38GB |
25
+ | [Replete-LLM-V2.5-Qwen-14b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ4_XS.gguf) | IQ4_XS | 7.62GB |
26
+ | [Replete-LLM-V2.5-Qwen-14b.Q4_0.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_0.gguf) | Q4_0 | 7.93GB |
27
+ | [Replete-LLM-V2.5-Qwen-14b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.IQ4_NL.gguf) | IQ4_NL | 8.01GB |
28
+ | [Replete-LLM-V2.5-Qwen-14b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_K_S.gguf) | Q4_K_S | 7.98GB |
29
+ | [Replete-LLM-V2.5-Qwen-14b.Q4_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_K.gguf) | Q4_K | 8.37GB |
30
+ | [Replete-LLM-V2.5-Qwen-14b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_K_M.gguf) | Q4_K_M | 8.37GB |
31
+ | [Replete-LLM-V2.5-Qwen-14b.Q4_1.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q4_1.gguf) | Q4_1 | 8.75GB |
32
+ | [Replete-LLM-V2.5-Qwen-14b.Q5_0.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_0.gguf) | Q5_0 | 9.56GB |
33
+ | [Replete-LLM-V2.5-Qwen-14b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_K_S.gguf) | Q5_K_S | 9.56GB |
34
+ | [Replete-LLM-V2.5-Qwen-14b.Q5_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_K.gguf) | Q5_K | 9.79GB |
35
+ | [Replete-LLM-V2.5-Qwen-14b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_K_M.gguf) | Q5_K_M | 9.79GB |
36
+ | [Replete-LLM-V2.5-Qwen-14b.Q5_1.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q5_1.gguf) | Q5_1 | 10.38GB |
37
+ | [Replete-LLM-V2.5-Qwen-14b.Q6_K.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q6_K.gguf) | Q6_K | 11.29GB |
38
+ | [Replete-LLM-V2.5-Qwen-14b.Q8_0.gguf](https://huggingface.co/RichardErkhov/Replete-AI_-_Replete-LLM-V2.5-Qwen-14b-gguf/blob/main/Replete-LLM-V2.5-Qwen-14b.Q8_0.gguf) | Q8_0 | 14.62GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: apache-2.0
46
+ library_name: transformers
47
+ base_model:
48
+ - Qwen/Qwen2.5-14B-Instruct
49
+ model-index:
50
+ - name: Replete-LLM-V2.5-Qwen-14b
51
+ results:
52
+ - task:
53
+ type: text-generation
54
+ name: Text Generation
55
+ dataset:
56
+ name: IFEval (0-Shot)
57
+ type: HuggingFaceH4/ifeval
58
+ args:
59
+ num_few_shot: 0
60
+ metrics:
61
+ - type: inst_level_strict_acc and prompt_level_strict_acc
62
+ value: 58.4
63
+ name: strict accuracy
64
+ source:
65
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
66
+ name: Open LLM Leaderboard
67
+ - task:
68
+ type: text-generation
69
+ name: Text Generation
70
+ dataset:
71
+ name: BBH (3-Shot)
72
+ type: BBH
73
+ args:
74
+ num_few_shot: 3
75
+ metrics:
76
+ - type: acc_norm
77
+ value: 49.39
78
+ name: normalized accuracy
79
+ source:
80
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
81
+ name: Open LLM Leaderboard
82
+ - task:
83
+ type: text-generation
84
+ name: Text Generation
85
+ dataset:
86
+ name: MATH Lvl 5 (4-Shot)
87
+ type: hendrycks/competition_math
88
+ args:
89
+ num_few_shot: 4
90
+ metrics:
91
+ - type: exact_match
92
+ value: 15.63
93
+ name: exact match
94
+ source:
95
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
96
+ name: Open LLM Leaderboard
97
+ - task:
98
+ type: text-generation
99
+ name: Text Generation
100
+ dataset:
101
+ name: GPQA (0-shot)
102
+ type: Idavidrein/gpqa
103
+ args:
104
+ num_few_shot: 0
105
+ metrics:
106
+ - type: acc_norm
107
+ value: 16.22
108
+ name: acc_norm
109
+ source:
110
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
111
+ name: Open LLM Leaderboard
112
+ - task:
113
+ type: text-generation
114
+ name: Text Generation
115
+ dataset:
116
+ name: MuSR (0-shot)
117
+ type: TAUR-Lab/MuSR
118
+ args:
119
+ num_few_shot: 0
120
+ metrics:
121
+ - type: acc_norm
122
+ value: 18.83
123
+ name: acc_norm
124
+ source:
125
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
126
+ name: Open LLM Leaderboard
127
+ - task:
128
+ type: text-generation
129
+ name: Text Generation
130
+ dataset:
131
+ name: MMLU-PRO (5-shot)
132
+ type: TIGER-Lab/MMLU-Pro
133
+ config: main
134
+ split: test
135
+ args:
136
+ num_few_shot: 5
137
+ metrics:
138
+ - type: acc
139
+ value: 48.62
140
+ name: accuracy
141
+ source:
142
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Replete-AI/Replete-LLM-V2.5-Qwen-14b
143
+ name: Open LLM Leaderboard
144
+ ---
145
+ # Replete-LLM-V2.5-Qwen-14b
146
+
147
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/ihnWXDEgV-ZKN_B036U1J.png)
148
+
149
+ Replete-LLM-V2.5-Qwen-14b is a continues finetuned version of Qwen2.5-14B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the *Ties* merge method
150
+
151
+ This version of the model shows higher performance than the original instruct and base models.
152
+
153
+ Quants:
154
+
155
+ GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-14b-GGUF
156
+
157
+ Benchmarks:
158
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
159
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Replete-AI__Replete-LLM-V2.5-Qwen-14b)
160
+
161
+ | Metric |Value|
162
+ |-------------------|----:|
163
+ |Avg. |34.52|
164
+ |IFEval (0-Shot) |58.40|
165
+ |BBH (3-Shot) |49.39|
166
+ |MATH Lvl 5 (4-Shot)|15.63|
167
+ |GPQA (0-shot) |16.22|
168
+ |MuSR (0-shot) |18.83|
169
+ |MMLU-PRO (5-shot) |48.62|
170
+
171
+
172
+