fix `_name_or_path` in config.json
#3
by not-lain - opened
- README.md +6 -0
- config.json +2 -2
- requirements.txt +2 -0
README.md
CHANGED
|
@@ -40,6 +40,12 @@ The training setup was `4xA100's 80GB` and took ~6 hours to pretrain and ~13 hou
|
|
| 40 |
---
|
| 41 |
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
## Training:
|
| 44 |
We will release the training code in some time.
|
| 45 |
|
|
|
|
| 40 |
---
|
| 41 |
|
| 42 |
|
| 43 |
+
## Installing requirements
|
| 44 |
+
```
|
| 45 |
+
pip install -qr https://huggingface.co/Tensoic/Cerule-v0.1/resolve/main/requirements.txt
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
|
| 49 |
## Training:
|
| 50 |
We will release the training code in some time.
|
| 51 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Tensoic/Cerule",
|
| 3 |
"architectures": [
|
| 4 |
"CeruleGemmaForCausalLM"
|
| 5 |
],
|
|
@@ -34,7 +34,7 @@
|
|
| 34 |
"tokenizer_model_max_length": 2048,
|
| 35 |
"tokenizer_padding_side": "right",
|
| 36 |
"torch_dtype": "bfloat16",
|
| 37 |
-
"transformers_version": "4.39.
|
| 38 |
"tune_mm_mlp_adapter": false,
|
| 39 |
"use_cache": true,
|
| 40 |
"use_mm_proj": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Tensoic/Cerule-v0.1",
|
| 3 |
"architectures": [
|
| 4 |
"CeruleGemmaForCausalLM"
|
| 5 |
],
|
|
|
|
| 34 |
"tokenizer_model_max_length": 2048,
|
| 35 |
"tokenizer_padding_side": "right",
|
| 36 |
"torch_dtype": "bfloat16",
|
| 37 |
+
"transformers_version": "4.39.1",
|
| 38 |
"tune_mm_mlp_adapter": false,
|
| 39 |
"use_cache": true,
|
| 40 |
"use_mm_proj": true,
|
requirements.txt
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
transformers>=4.39.1
|
| 2 |
+
flash_attn
|