Upload ParchmentForCausalLM
Browse files- README.md +4 -4
- config.json +3 -0
- model.safetensors +2 -2
README.md
CHANGED
|
@@ -2,10 +2,10 @@
|
|
| 2 |
language: en
|
| 3 |
license: mit
|
| 4 |
tags:
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
---
|
| 10 |
|
| 11 |
# tiny-edu-166m (ParchmentLM)
|
|
|
|
| 2 |
language: en
|
| 3 |
license: mit
|
| 4 |
tags:
|
| 5 |
+
- pretrained
|
| 6 |
+
- causal-lm
|
| 7 |
+
- fineweb-edu
|
| 8 |
+
- custom-architecture
|
| 9 |
---
|
| 10 |
|
| 11 |
# tiny-edu-166m (ParchmentLM)
|
config.json
CHANGED
|
@@ -7,10 +7,13 @@
|
|
| 7 |
"d_model": 768,
|
| 8 |
"dtype": "float32",
|
| 9 |
"eos_token_id": 100257,
|
|
|
|
| 10 |
"max_seq_len": 1024,
|
| 11 |
"model_type": "parchment",
|
| 12 |
"n_heads": 12,
|
| 13 |
"n_layers": 12,
|
|
|
|
|
|
|
| 14 |
"pad_token_id": 100257,
|
| 15 |
"rms_norm_eps": 1e-06,
|
| 16 |
"rope_base": 10000.0,
|
|
|
|
| 7 |
"d_model": 768,
|
| 8 |
"dtype": "float32",
|
| 9 |
"eos_token_id": 100257,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
"max_seq_len": 1024,
|
| 12 |
"model_type": "parchment",
|
| 13 |
"n_heads": 12,
|
| 14 |
"n_layers": 12,
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
"pad_token_id": 100257,
|
| 18 |
"rms_norm_eps": 1e-06,
|
| 19 |
"rope_base": 10000.0,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a92b4dd4cec11886a1edfade108d27c6feb30d673bea50a1c21c378ad03f659
|
| 3 |
+
size 647880264
|