Hugging Face's logo

bartowski
/
mistral-orpo-beta-GGUF

Text Generation
GGUF
English
Eval Results
Inference Endpoints
conversational
Model card Files Community
bartowski commited on
Commit
292c872
•
1 Parent(s): fb669e4

Llamacpp quants

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +186 -0
  3. mistral-orpo-beta-Q2_K.gguf +3 -0
  4. mistral-orpo-beta-Q3_K_L.gguf +3 -0
  5. mistral-orpo-beta-Q3_K_M.gguf +3 -0
  6. mistral-orpo-beta-Q3_K_S.gguf +3 -0
  7. mistral-orpo-beta-Q4_0.gguf +3 -0
  8. mistral-orpo-beta-Q4_K_M.gguf +3 -0
  9. mistral-orpo-beta-Q4_K_S.gguf +3 -0
  10. mistral-orpo-beta-Q5_0.gguf +3 -0
  11. mistral-orpo-beta-Q5_K_M.gguf +3 -0
  12. mistral-orpo-beta-Q5_K_S.gguf +3 -0
  13. mistral-orpo-beta-Q6_K.gguf +3 -0
  14. mistral-orpo-beta-Q8_0.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ mistral-orpo-beta-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ mistral-orpo-beta-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ mistral-orpo-beta-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ mistral-orpo-beta-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ mistral-orpo-beta-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ mistral-orpo-beta-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ mistral-orpo-beta-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ mistral-orpo-beta-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ mistral-orpo-beta-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ mistral-orpo-beta-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ mistral-orpo-beta-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ mistral-orpo-beta-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: mit
5
+ base_model:
6
+ - mistralai/Mistral-7B-v0.1
7
+ datasets:
8
+ - argilla/ultrafeedback-binarized-preferences-cleaned
9
+ pipeline_tag: text-generation
10
+ model-index:
11
+ - name: Mistral-ORPO-β
12
+ results:
13
+ # AI2 Reasoning Challenge (25-Shot)
14
+ - task:
15
+ type: text-generation
16
+ name: Text Generation
17
+ dataset:
18
+ name: AI2 Reasoning Challenge (25-Shot)
19
+ type: ai2_arc
20
+ config: ARC-Challenge
21
+ split: test
22
+ args:
23
+ num_few_shot: 25
24
+ metrics:
25
+ - type: acc_norm
26
+ name: normalized accuracy
27
+ value: 61.18
28
+ source:
29
+ name: Open LLM Leaderboard
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta
31
+
32
+ # HellaSwag (10-shot)
33
+ - task:
34
+ type: text-generation
35
+ name: Text Generation
36
+ dataset:
37
+ name: HellaSwag (10-Shot)
38
+ type: hellaswag
39
+ split: validation
40
+ args:
41
+ num_few_shot: 10
42
+ metrics:
43
+ - type: acc_norm
44
+ name: normalized accuracy
45
+ value: 84.03
46
+ source:
47
+ name: Open LLM Leaderboard
48
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta
49
+
50
+ # TruthfulQA (0-shot)
51
+ - task:
52
+ type: text-generation
53
+ name: Text Generation
54
+ dataset:
55
+ name: TruthfulQA (0-shot)
56
+ type: truthful_qa
57
+ config: multiple_choice
58
+ split: validation
59
+ args:
60
+ num_few_shot: 0
61
+ metrics:
62
+ - type: mc2
63
+ value: 47.69
64
+ source:
65
+ name: Open LLM Leaderboard
66
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta
67
+
68
+ # GSM8k (5-shot)
69
+ - task:
70
+ type: text-generation
71
+ name: Text Generation
72
+ dataset:
73
+ name: GSM8k (5-shot)
74
+ type: gsm8k
75
+ config: main
76
+ split: test
77
+ args:
78
+ num_few_shot: 5
79
+ metrics:
80
+ - type: acc
81
+ name: accuracy
82
+ value: 39.8
83
+ source:
84
+ name: Open LLM Leaderboard
85
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta
86
+
87
+ # MMLU (5-Shot)
88
+ - task:
89
+ type: text-generation
90
+ name: Text Generation
91
+ dataset:
92
+ name: MMLU (5-Shot)
93
+ type: cais/mmlu
94
+ config: all
95
+ split: test
96
+ args:
97
+ num_few_shot: 5
98
+ metrics:
99
+ - type: acc
100
+ name: accuracy
101
+ value: 63.26
102
+ source:
103
+ name: Open LLM Leaderboard
104
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta
105
+
106
+ # Winogrande (5-shot)
107
+ - task:
108
+ type: text-generation
109
+ name: Text Generation
110
+ dataset:
111
+ name: Winogrande (5-shot)
112
+ type: winogrande
113
+ config: winogrande_xl
114
+ split: validation
115
+ args:
116
+ num_few_shot: 5
117
+ metrics:
118
+ - type: acc
119
+ name: accuracy
120
+ value: 79.24
121
+ source:
122
+ name: Open LLM Leaderboard
123
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta
124
+ - task:
125
+ type: text-generation
126
+ dataset:
127
+ name: AlpacaEval 1
128
+ type: AlpacaEval
129
+ metrics:
130
+ - type: AlpacaEval 1.0
131
+ value: 91.16%
132
+ name: Win Rate
133
+ source:
134
+ url: https://tatsu-lab.github.io/alpaca_eval/
135
+ name: Leaderboard
136
+ - task:
137
+ type: text-generation
138
+ dataset:
139
+ name: AlpacaEval 2
140
+ type: AlpacaEval
141
+ metrics:
142
+ - type: AlpacaEval 2.0
143
+ value: 12.57%
144
+ name: Win Rate
145
+ source:
146
+ url: https://tatsu-lab.github.io/alpaca_eval/
147
+ name: Leaderboard
148
+ - task:
149
+ type: text-generation
150
+ dataset:
151
+ name: MT-Bench
152
+ type: MT-Bench
153
+ metrics:
154
+ - type: MT-Bench
155
+ value: 7.322
156
+ name: Score
157
+ source:
158
+ url: https://github.com/lm-sys/FastChat/blob/main/fastchat/llm_judge/
159
+ name: self-reported
160
+ quantized_by: bartowski
161
+ ---
162
+
163
+ ## Llamacpp Quantizations of mistral-orpo-beta
164
+
165
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.
166
+
167
+ Original model: https://huggingface.co/kaist-ai/mistral-orpo-beta
168
+
169
+ Download a file (not the whole branch) from below:
170
+
171
+ | Filename | Quant type | File Size | Description |
172
+ | -------- | ---------- | --------- | ----------- |
173
+ | [mistral-orpo-beta-Q8_0.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
174
+ | [mistral-orpo-beta-Q6_K.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
175
+ | [mistral-orpo-beta-Q5_K_M.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
176
+ | [mistral-orpo-beta-Q5_K_S.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
177
+ | [mistral-orpo-beta-Q5_0.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
178
+ | [mistral-orpo-beta-Q4_K_M.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
179
+ | [mistral-orpo-beta-Q4_K_S.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
180
+ | [mistral-orpo-beta-Q4_0.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
181
+ | [mistral-orpo-beta-Q3_K_L.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
182
+ | [mistral-orpo-beta-Q3_K_M.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
183
+ | [mistral-orpo-beta-Q3_K_S.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
184
+ | [mistral-orpo-beta-Q2_K.gguf](https://huggingface.co/bartowski/mistral-orpo-beta-GGUF/blob/main/mistral-orpo-beta-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
185
+
186
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
mistral-orpo-beta-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c12f93fd84eb691b2a63d60191f3f22a8cab57d4f93c1cba20b22c9cef3182
3
+ size 2719242400
mistral-orpo-beta-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4667c6d3d73dddae9b018243ab60af29a69e9c421160395750979d79320395e
3
+ size 3822024864
mistral-orpo-beta-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f58c5e9bc18d4387fe56c50de4c03260f2693181debb76f206f80421e9ef964
3
+ size 3518986400
mistral-orpo-beta-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b1c5f998a369f223ac282b3b4050af12944f0323599a644e3b7824549e97a2e
3
+ size 3164567712
mistral-orpo-beta-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b08feb26fa331ffc791e3672938c50073d8dae71fdcb0d4cd359853851131fa9
3
+ size 4108916896
mistral-orpo-beta-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7d19ee4db1d630574901d9d5230d647c133db7fb9127b39a5ed7a6f9693208
3
+ size 4368439456
mistral-orpo-beta-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae112597b39543fda925572acd09c5145d9f19625469ccc59ee08e53f02a169b
3
+ size 4140374176
mistral-orpo-beta-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d11c538f92ee01268a270002b769a0356e77140d70e293423e9eb2ff5473cf3
3
+ size 4997716128
mistral-orpo-beta-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c8f4b7d1a8876b7b0db7ed0d6327054f35cf01d2fadfe3efa98e6623e20e14
3
+ size 5131409568
mistral-orpo-beta-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d8f9d6379ff202fe99d0648c4e103501f99986da49d5c3677ea0416530abbe
3
+ size 4997716128
mistral-orpo-beta-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a749bc6e7a064281dc82179c2f9db6d8673dc9e2c760e0373b6fab358c4d1a2
3
+ size 5942065312
mistral-orpo-beta-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2e7405e11da18fb21d82f45f180751a1e35e0761692dda826ccf939210f48c
3
+ size 7695857824