quants upload
Browse filesMahou-1.5-mistral-nemo-12B Q4 Q8 quant
- .gitattributes +6 -0
- Mahou-1.5-mistral-nemo-12B-IQ4_NL.gguf +3 -0
- Mahou-1.5-mistral-nemo-12B-Q4_0.gguf +3 -0
- Mahou-1.5-mistral-nemo-12B-Q4_0_4_4.gguf +3 -0
- Mahou-1.5-mistral-nemo-12B-Q4_1.gguf +3 -0
- Mahou-1.5-mistral-nemo-12B-Q8_0.gguf +3 -0
- Mahou-1.5-mistral-nemo-12B.imatrix +3 -0
- README.md +11 -0
- README.org.md +156 -0
.gitattributes
CHANGED
@@ -33,3 +33,9 @@ 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 |
+
Mahou-1.5-mistral-nemo-12B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Mahou-1.5-mistral-nemo-12B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Mahou-1.5-mistral-nemo-12B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Mahou-1.5-mistral-nemo-12B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Mahou-1.5-mistral-nemo-12B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Mahou-1.5-mistral-nemo-12B.imatrix filter=lfs diff=lfs merge=lfs -text
|
Mahou-1.5-mistral-nemo-12B-IQ4_NL.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33629552f38ed6e634d3fe8e45bb5a671e47f83d80322d25d9cdd22dda41dc07
|
3 |
+
size 7097914848
|
Mahou-1.5-mistral-nemo-12B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:366037c5210d9ff0e955744453ca93c55d2c65b5d1179b5adc3d4142da7e886c
|
3 |
+
size 7094638048
|
Mahou-1.5-mistral-nemo-12B-Q4_0_4_4.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1da60e14c9eff2f668565c5e4e555a445a8e6a16985c80e850cb27ae16da0826
|
3 |
+
size 7071700448
|
Mahou-1.5-mistral-nemo-12B-Q4_1.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e23c4b07c3c381f16e0dd03ec96218f99ab21c369b801318859056d0a9847af0
|
3 |
+
size 7795217888
|
Mahou-1.5-mistral-nemo-12B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1a99a0e9589d38dc2e8ac37ba24a90c8c661c251286c56fccfd0eb70656edb7
|
3 |
+
size 13022369248
|
Mahou-1.5-mistral-nemo-12B.imatrix
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd97c48105b0bb255d99bdc35762a54270d24095ed48c18f6a08ba7ce46edb98
|
3 |
+
size 7054410
|
README.md
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: transformers
|
4 |
+
base_model: flammenai/Mahou-1.5-mistral-nemo-12B
|
5 |
+
datasets: flammenai/MahouMix-v1
|
6 |
+
inference: false
|
7 |
+
---
|
8 |
+
|
9 |
+
# Mahou-1.5-mistral-nemo-12B
|
10 |
+
|
11 |
+
Selected GGUF quants of https://huggingface.co/flammenai/Mahou-1.5-mistral-nemo-12B
|
README.org.md
ADDED
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: transformers
|
4 |
+
base_model:
|
5 |
+
- flammenai/Flammades-Mistral-Nemo-12B
|
6 |
+
datasets:
|
7 |
+
- flammenai/MahouMix-v1
|
8 |
+
model-index:
|
9 |
+
- name: Mahou-1.5-mistral-nemo-12B
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: text-generation
|
13 |
+
name: Text Generation
|
14 |
+
dataset:
|
15 |
+
name: IFEval (0-Shot)
|
16 |
+
type: HuggingFaceH4/ifeval
|
17 |
+
args:
|
18 |
+
num_few_shot: 0
|
19 |
+
metrics:
|
20 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
21 |
+
value: 67.51
|
22 |
+
name: strict accuracy
|
23 |
+
source:
|
24 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.5-mistral-nemo-12B
|
25 |
+
name: Open LLM Leaderboard
|
26 |
+
- task:
|
27 |
+
type: text-generation
|
28 |
+
name: Text Generation
|
29 |
+
dataset:
|
30 |
+
name: BBH (3-Shot)
|
31 |
+
type: BBH
|
32 |
+
args:
|
33 |
+
num_few_shot: 3
|
34 |
+
metrics:
|
35 |
+
- type: acc_norm
|
36 |
+
value: 36.26
|
37 |
+
name: normalized accuracy
|
38 |
+
source:
|
39 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.5-mistral-nemo-12B
|
40 |
+
name: Open LLM Leaderboard
|
41 |
+
- task:
|
42 |
+
type: text-generation
|
43 |
+
name: Text Generation
|
44 |
+
dataset:
|
45 |
+
name: MATH Lvl 5 (4-Shot)
|
46 |
+
type: hendrycks/competition_math
|
47 |
+
args:
|
48 |
+
num_few_shot: 4
|
49 |
+
metrics:
|
50 |
+
- type: exact_match
|
51 |
+
value: 5.06
|
52 |
+
name: exact match
|
53 |
+
source:
|
54 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.5-mistral-nemo-12B
|
55 |
+
name: Open LLM Leaderboard
|
56 |
+
- task:
|
57 |
+
type: text-generation
|
58 |
+
name: Text Generation
|
59 |
+
dataset:
|
60 |
+
name: GPQA (0-shot)
|
61 |
+
type: Idavidrein/gpqa
|
62 |
+
args:
|
63 |
+
num_few_shot: 0
|
64 |
+
metrics:
|
65 |
+
- type: acc_norm
|
66 |
+
value: 3.47
|
67 |
+
name: acc_norm
|
68 |
+
source:
|
69 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.5-mistral-nemo-12B
|
70 |
+
name: Open LLM Leaderboard
|
71 |
+
- task:
|
72 |
+
type: text-generation
|
73 |
+
name: Text Generation
|
74 |
+
dataset:
|
75 |
+
name: MuSR (0-shot)
|
76 |
+
type: TAUR-Lab/MuSR
|
77 |
+
args:
|
78 |
+
num_few_shot: 0
|
79 |
+
metrics:
|
80 |
+
- type: acc_norm
|
81 |
+
value: 16.47
|
82 |
+
name: acc_norm
|
83 |
+
source:
|
84 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.5-mistral-nemo-12B
|
85 |
+
name: Open LLM Leaderboard
|
86 |
+
- task:
|
87 |
+
type: text-generation
|
88 |
+
name: Text Generation
|
89 |
+
dataset:
|
90 |
+
name: MMLU-PRO (5-shot)
|
91 |
+
type: TIGER-Lab/MMLU-Pro
|
92 |
+
config: main
|
93 |
+
split: test
|
94 |
+
args:
|
95 |
+
num_few_shot: 5
|
96 |
+
metrics:
|
97 |
+
- type: acc
|
98 |
+
value: 28.91
|
99 |
+
name: accuracy
|
100 |
+
source:
|
101 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Mahou-1.5-mistral-nemo-12B
|
102 |
+
name: Open LLM Leaderboard
|
103 |
+
---
|
104 |
+
![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png)
|
105 |
+
|
106 |
+
# Mahou-1.5-mistral-nemo-12B
|
107 |
+
|
108 |
+
Mahou is designed to provide short messages in a conversational context. It is capable of casual conversation and character roleplay.
|
109 |
+
|
110 |
+
### Chat Format
|
111 |
+
|
112 |
+
This model has been trained to use ChatML format.
|
113 |
+
|
114 |
+
```
|
115 |
+
<|im_start|>system
|
116 |
+
{{system}}<|im_end|>
|
117 |
+
<|im_start|>{{char}}
|
118 |
+
{{message}}<|im_end|>
|
119 |
+
<|im_start|>{{user}}
|
120 |
+
{{message}}<|im_end|>
|
121 |
+
```
|
122 |
+
|
123 |
+
### Roleplay Format
|
124 |
+
|
125 |
+
- Speech without quotes.
|
126 |
+
- Actions in `*asterisks*`
|
127 |
+
|
128 |
+
```
|
129 |
+
*leans against wall cooly* so like, i just casted a super strong spell at magician academy today, not gonna lie, felt badass.
|
130 |
+
```
|
131 |
+
|
132 |
+
### SillyTavern Settings
|
133 |
+
|
134 |
+
1. Use ChatML for the Context Template.
|
135 |
+
2. Enable Instruct Mode.
|
136 |
+
3. Use the [Mahou ChatML Instruct preset](https://huggingface.co/datasets/flammenai/Mahou-ST-ChatML-Instruct/raw/main/Mahou.json).
|
137 |
+
4. Use the [Mahou Sampler preset](https://huggingface.co/datasets/flammenai/Mahou-ST-Sampler-Preset/raw/main/Mahou.json).
|
138 |
+
|
139 |
+
### Method
|
140 |
+
|
141 |
+
[ORPO finetuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 4x H100 for 3 epochs.
|
142 |
+
|
143 |
+
|
144 |
+
### [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
145 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_flammenai__Mahou-1.5-mistral-nemo-12B)
|
146 |
+
|
147 |
+
| Metric |Value|
|
148 |
+
|-------------------|----:|
|
149 |
+
|Avg. |26.28|
|
150 |
+
|IFEval (0-Shot) |67.51|
|
151 |
+
|BBH (3-Shot) |36.26|
|
152 |
+
|MATH Lvl 5 (4-Shot)| 5.06|
|
153 |
+
|GPQA (0-shot) | 3.47|
|
154 |
+
|MuSR (0-shot) |16.47|
|
155 |
+
|MMLU-PRO (5-shot) |28.91|
|
156 |
+
|