Add model weights and configurations
Browse files- config.json +32 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- training.log +0 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/DeepSpeedExamples/applications/DeepSpeed-Chat/training/step1_supervised_finetuning/deepspeed-chat_step1_output",
|
| 3 |
+
"_remove_final_layer_norm": false,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"OPTForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 2,
|
| 11 |
+
"do_layer_norm_before": true,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"enable_bias": true,
|
| 14 |
+
"end_token_id": 50260,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"ffn_dim": 8192,
|
| 17 |
+
"hidden_size": 2048,
|
| 18 |
+
"init_std": 0.02,
|
| 19 |
+
"layer_norm_elementwise_affine": true,
|
| 20 |
+
"layerdrop": 0.0,
|
| 21 |
+
"max_position_embeddings": 2048,
|
| 22 |
+
"model_type": "opt",
|
| 23 |
+
"num_attention_heads": 32,
|
| 24 |
+
"num_hidden_layers": 24,
|
| 25 |
+
"pad_token_id": 2,
|
| 26 |
+
"prefix": "</s>",
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"transformers_version": "4.29.0.dev0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50272,
|
| 31 |
+
"word_embed_proj_dim": 2048
|
| 32 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f051d540e349d0848de628c50099514f3460fba6dd990143994612d3d409b9
|
| 3 |
+
size 3235870087
|
training.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|