Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: appvoid/palmer-x-002
|
| 3 |
+
datasets:
|
| 4 |
+
- appvoid/no-prompt-15k
|
| 5 |
+
inference: false
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
model_creator: appvoid
|
| 10 |
+
model_name: palmer-x-002
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
quantized_by: afrideva
|
| 13 |
+
tags:
|
| 14 |
+
- gguf
|
| 15 |
+
- ggml
|
| 16 |
+
- quantized
|
| 17 |
+
- q2_k
|
| 18 |
+
- q3_k_m
|
| 19 |
+
- q4_k_m
|
| 20 |
+
- q5_k_m
|
| 21 |
+
- q6_k
|
| 22 |
+
- q8_0
|
| 23 |
+
---
|
| 24 |
+
# appvoid/palmer-x-002-GGUF
|
| 25 |
+
|
| 26 |
+
Quantized GGUF model files for [palmer-x-002](https://huggingface.co/appvoid/palmer-x-002) from [appvoid](https://huggingface.co/appvoid)
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
| Name | Quant method | Size |
|
| 30 |
+
| ---- | ---- | ---- |
|
| 31 |
+
| [palmer-x-002.fp16.gguf](https://huggingface.co/afrideva/palmer-x-002-GGUF/resolve/main/palmer-x-002.fp16.gguf) | fp16 | 2.20 GB |
|
| 32 |
+
| [palmer-x-002.q2_k.gguf](https://huggingface.co/afrideva/palmer-x-002-GGUF/resolve/main/palmer-x-002.q2_k.gguf) | q2_k | 483.12 MB |
|
| 33 |
+
| [palmer-x-002.q3_k_m.gguf](https://huggingface.co/afrideva/palmer-x-002-GGUF/resolve/main/palmer-x-002.q3_k_m.gguf) | q3_k_m | 550.82 MB |
|
| 34 |
+
| [palmer-x-002.q4_k_m.gguf](https://huggingface.co/afrideva/palmer-x-002-GGUF/resolve/main/palmer-x-002.q4_k_m.gguf) | q4_k_m | 668.79 MB |
|
| 35 |
+
| [palmer-x-002.q5_k_m.gguf](https://huggingface.co/afrideva/palmer-x-002-GGUF/resolve/main/palmer-x-002.q5_k_m.gguf) | q5_k_m | 783.02 MB |
|
| 36 |
+
| [palmer-x-002.q6_k.gguf](https://huggingface.co/afrideva/palmer-x-002-GGUF/resolve/main/palmer-x-002.q6_k.gguf) | q6_k | 904.39 MB |
|
| 37 |
+
| [palmer-x-002.q8_0.gguf](https://huggingface.co/afrideva/palmer-x-002-GGUF/resolve/main/palmer-x-002.q8_0.gguf) | q8_0 | 1.17 GB |
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
## Original Model Card:
|
| 42 |
+
|
| 43 |
+
# x-002
|
| 44 |
+
This is an incremental model update on `palmer-002` using dpo technique. X means dpo+sft spinoff.
|
| 45 |
+
|
| 46 |
+
### evaluation
|
| 47 |
+
|Model| ARC_C| HellaSwag| PIQA| Winogrande|
|
| 48 |
+
|------|-----|-----------|------|-------------|
|
| 49 |
+
|tinyllama-2t| 0.2807| 0.5463| 0.7067| 0.5683|
|
| 50 |
+
|palmer-001| 0.2807| 0.5524| 0.7106| 0.5896|
|
| 51 |
+
|tinyllama-2.5t|0.3191|0.5896| 0.7307| 0.5872|
|
| 52 |
+
|palmer-002|**0.3242**|**0.5956**|0.7345|0.5888|
|
| 53 |
+
|palmer-x-002|0.3224|0.5941|**0.7383**|**0.5912**|
|
| 54 |
+
|
| 55 |
+
### training
|
| 56 |
+
~500 dpo samples as experimental data to check on improvements. It seems like data is making it better on some benchmarks while also degrading quality on others.
|
| 57 |
+
|
| 58 |
+
### prompt
|
| 59 |
+
```
|
| 60 |
+
no prompt
|
| 61 |
+
```
|
| 62 |
+
|
| 63 |
+
As you can notice, the model actually completes by default questions that are the most-likely to be asked, which is good because most people will use it to answer as a chatbot.
|
| 64 |
+
<a href="https://ko-fi.com/appvoid" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 48px !important;width: 180px !important; filter: invert(70%);" ></a>
|