afrideva commited on
Commit
08776a7
1 Parent(s): adc59c5

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +64 -0
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: appvoid/palmer-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-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-002-GGUF
25
+
26
+ Quantized GGUF model files for [palmer-002](https://huggingface.co/appvoid/palmer-002) from [appvoid](https://huggingface.co/appvoid)
27
+
28
+
29
+ | Name | Quant method | Size |
30
+ | ---- | ---- | ---- |
31
+ | [palmer-002.fp16.gguf](https://huggingface.co/afrideva/palmer-002-GGUF/resolve/main/palmer-002.fp16.gguf) | fp16 | 2.20 GB |
32
+ | [palmer-002.q2_k.gguf](https://huggingface.co/afrideva/palmer-002-GGUF/resolve/main/palmer-002.q2_k.gguf) | q2_k | 483.12 MB |
33
+ | [palmer-002.q3_k_m.gguf](https://huggingface.co/afrideva/palmer-002-GGUF/resolve/main/palmer-002.q3_k_m.gguf) | q3_k_m | 550.82 MB |
34
+ | [palmer-002.q4_k_m.gguf](https://huggingface.co/afrideva/palmer-002-GGUF/resolve/main/palmer-002.q4_k_m.gguf) | q4_k_m | 668.79 MB |
35
+ | [palmer-002.q5_k_m.gguf](https://huggingface.co/afrideva/palmer-002-GGUF/resolve/main/palmer-002.q5_k_m.gguf) | q5_k_m | 783.02 MB |
36
+ | [palmer-002.q6_k.gguf](https://huggingface.co/afrideva/palmer-002-GGUF/resolve/main/palmer-002.q6_k.gguf) | q6_k | 904.39 MB |
37
+ | [palmer-002.q8_0.gguf](https://huggingface.co/afrideva/palmer-002-GGUF/resolve/main/palmer-002.q8_0.gguf) | q8_0 | 1.17 GB |
38
+
39
+
40
+
41
+ ## Original Model Card:
42
+ ![palmer](https://huggingface.co/appvoid/palmer-001/resolve/main/palmer.jpeg)
43
+ # palmer
44
+ ### a better base model
45
+ palmer is a series of ~1b parameters language models fine-tuned to be used as base models instead of using custom prompts for tasks. This means that it can be further fine-tuned on more data with custom prompts as usual or be used for downstream tasks as any base model you can get. The model has the best of both worlds: some "bias" to act as an assistant, but also the abillity to predict the next-word from its internet knowledge base. It's a 1.1b llama 2 model so you can use it with your favorite tools/frameworks.
46
+
47
+ ### evaluation
48
+ |Model| ARC_C| HellaSwag| PIQA| Winogrande|
49
+ |------|-----|-----------|------|-------------|
50
+ |tinyllama-2t| 0.2807| 0.5463| 0.7067| 0.5683|
51
+ |palmer-001| 0.2807| 0.5524| 0.7106| **0.5896**|
52
+ |tinyllama-2.5t|0.3191|0.5896| 0.7307| 0.5872|
53
+ |palmer-002|**0.3242**|**0.5956**|**0.7345**|0.5888|
54
+
55
+
56
+ ### training
57
+ Training took ~3.5 P100 gpu hours. It was trained on 15,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.
58
+
59
+
60
+ ### prompt
61
+ ```
62
+ no prompt
63
+ ```
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>