Training in progress, step 2
Browse files- config.json +20 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"gLM2ForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_glm2.gLM2Config",
|
| 7 |
+
"AutoModel": "modeling_glm2.gLM2Model",
|
| 8 |
+
"AutoModelForMaskedLM": "modeling_glm2.gLM2ForMaskedLM"
|
| 9 |
+
},
|
| 10 |
+
"depth": 33,
|
| 11 |
+
"dim": 1280,
|
| 12 |
+
"ffn_dim_multiplier": null,
|
| 13 |
+
"heads": 20,
|
| 14 |
+
"model_type": "gLM2",
|
| 15 |
+
"norm_eps": 1e-05,
|
| 16 |
+
"swiglu_multiple_of": 256,
|
| 17 |
+
"torch_dtype": "float32",
|
| 18 |
+
"transformers_version": "4.51.3",
|
| 19 |
+
"vocab_size": 37
|
| 20 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bcb3207c1b01dc2880944453572668148e5f8fc975413aa894c677c232baa49
|
| 3 |
+
size 2682482800
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c80afb2a9dcafc071bc8903f12da8ed8115f7be6f0128b08513fde1e722cae1
|
| 3 |
+
size 5777
|