Update README.md
Browse files
README.md
CHANGED
@@ -3,17 +3,74 @@ license: cc-by-nc-4.0
|
|
3 |
base_model: mlabonne/NeuralMonarch-7B
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
-
- name:
|
8 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
should probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
-
axolotl version: `0.4.0`
|
17 |
```yaml
|
18 |
base_model: mlabonne/NeuralMonarch-7B
|
19 |
model_type: MistralForCausalLM
|
@@ -190,43 +247,6 @@ fsdp_config:
|
|
190 |
special_tokens:
|
191 |
```
|
192 |
|
193 |
-
</details><br>
|
194 |
-
|
195 |
-
# out
|
196 |
-
|
197 |
-
This model is a fine-tuned version of [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B) on an unknown dataset.
|
198 |
-
|
199 |
-
## Model description
|
200 |
-
|
201 |
-
More information needed
|
202 |
-
|
203 |
-
## Intended uses & limitations
|
204 |
-
|
205 |
-
More information needed
|
206 |
-
|
207 |
-
## Training and evaluation data
|
208 |
-
|
209 |
-
More information needed
|
210 |
-
|
211 |
-
## Training procedure
|
212 |
-
|
213 |
-
### Training hyperparameters
|
214 |
-
|
215 |
-
The following hyperparameters were used during training:
|
216 |
-
- learning_rate: 5e-07
|
217 |
-
- train_batch_size: 1
|
218 |
-
- eval_batch_size: 8
|
219 |
-
- seed: 42
|
220 |
-
- gradient_accumulation_steps: 8
|
221 |
-
- total_train_batch_size: 8
|
222 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
223 |
-
- lr_scheduler_type: cosine
|
224 |
-
- lr_scheduler_warmup_steps: 100
|
225 |
-
- training_steps: 1080
|
226 |
-
|
227 |
-
### Training results
|
228 |
-
|
229 |
-
|
230 |
|
231 |
### Framework versions
|
232 |
|
@@ -234,3 +254,6 @@ The following hyperparameters were used during training:
|
|
234 |
- Pytorch 2.1.2+cu118
|
235 |
- Datasets 2.17.0
|
236 |
- Tokenizers 0.15.0
|
|
|
|
|
|
|
|
3 |
base_model: mlabonne/NeuralMonarch-7B
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
- axolotl
|
7 |
+
- mistral
|
8 |
+
- instruct
|
9 |
+
- finetune
|
10 |
+
- chatml
|
11 |
+
- gpt4
|
12 |
+
- synthetic data
|
13 |
+
- distillation
|
14 |
model-index:
|
15 |
+
- name: AlphaMonarch-laser
|
16 |
results: []
|
17 |
+
datasets:
|
18 |
+
- argilla/OpenHermes2.5-dpo-binarized-alpha
|
19 |
+
language:
|
20 |
+
- en
|
21 |
+
library_name: transformers
|
22 |
+
pipeline_tag: text-generation
|
23 |
---
|
24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
should probably proofread and complete it, then remove this comment. -->
|
26 |
|
27 |
+
# AlphaMonarch-laser
|
28 |
+
|
29 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/62S_ExHO6NKCM3NhPDrds.jpeg)
|
30 |
+
|
31 |
+
|
32 |
+
|
33 |
+
</details><br>
|
34 |
+
|
35 |
+
# out
|
36 |
+
|
37 |
+
This model is a fine-tuned version of [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B) on an unknown dataset.
|
38 |
+
|
39 |
+
## Model description
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Intended uses & limitations
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training and evaluation data
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training procedure
|
52 |
+
|
53 |
+
### Training hyperparameters
|
54 |
+
|
55 |
+
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 5e-07
|
57 |
+
- train_batch_size: 1
|
58 |
+
- eval_batch_size: 8
|
59 |
+
- seed: 42
|
60 |
+
- gradient_accumulation_steps: 8
|
61 |
+
- total_train_batch_size: 8
|
62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
+
- lr_scheduler_type: cosine
|
64 |
+
- lr_scheduler_warmup_steps: 100
|
65 |
+
- training_steps: 1080
|
66 |
+
|
67 |
+
|
68 |
+
|
69 |
+
|
70 |
+
|
71 |
+
|
72 |
+
### 📝 Axolotl Configuration
|
73 |
|
|
|
74 |
```yaml
|
75 |
base_model: mlabonne/NeuralMonarch-7B
|
76 |
model_type: MistralForCausalLM
|
|
|
247 |
special_tokens:
|
248 |
```
|
249 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
|
251 |
### Framework versions
|
252 |
|
|
|
254 |
- Pytorch 2.1.2+cu118
|
255 |
- Datasets 2.17.0
|
256 |
- Tokenizers 0.15.0
|
257 |
+
- axolotl: 0.4.0
|
258 |
+
|
259 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|