Upload GPTOptim
Browse files- config.json +2 -6
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,14 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "distributed/optimized-gpt2-250m",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPTOptim"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.1,
|
| 8 |
-
"auto_map": {
|
| 9 |
-
"AutoConfig": "distributed/optimized-gpt2-250m--configuration_gpt_optimized.GPTOptimConfig",
|
| 10 |
-
"AutoModelForCausalLM": "distributed/optimized-gpt2-250m--modeling_gpt_optimized.GPTOptim"
|
| 11 |
-
},
|
| 12 |
"block_size": 1024,
|
| 13 |
"bos_token_id": 50256,
|
| 14 |
"embd_pdrop": 0.1,
|
|
@@ -17,6 +12,7 @@
|
|
| 17 |
"layer_norm_epsilon": 1e-05,
|
| 18 |
"model_type": "gpt_optimized",
|
| 19 |
"n_embd": 1024,
|
|
|
|
| 20 |
"n_head": 16,
|
| 21 |
"n_inner": null,
|
| 22 |
"n_layer": 16,
|
|
@@ -33,5 +29,5 @@
|
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"transformers_version": "4.39.3",
|
| 35 |
"use_cache": true,
|
| 36 |
-
"vocab_size":
|
| 37 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
"GPTOptim"
|
| 5 |
],
|
| 6 |
"attn_pdrop": 0.1,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"block_size": 1024,
|
| 8 |
"bos_token_id": 50256,
|
| 9 |
"embd_pdrop": 0.1,
|
|
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt_optimized",
|
| 14 |
"n_embd": 1024,
|
| 15 |
+
"n_embed": 1024,
|
| 16 |
"n_head": 16,
|
| 17 |
"n_inner": null,
|
| 18 |
"n_layer": 16,
|
|
|
|
| 29 |
"torch_dtype": "float32",
|
| 30 |
"transformers_version": "4.39.3",
|
| 31 |
"use_cache": true,
|
| 32 |
+
"vocab_size": 50304
|
| 33 |
}
|
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:c7a1f56f7821b6d0fe92785d04037cc2733baa54415cbf8ee8da97335f019806
|
| 3 |
+
size 1016427344
|