Upload LlamaForCausalLM
Browse files- config.json +18 -30
- generation_config.json +2 -2
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,37 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/Pretraining-Testing/pretraining/local-models/training/2024-01-
|
| 3 |
-
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
-
"
|
| 8 |
-
"bos_token_id":
|
| 9 |
-
"
|
| 10 |
-
"
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"scale_attn_weights": true,
|
| 24 |
-
"summary_activation": null,
|
| 25 |
-
"summary_first_dropout": 0.0,
|
| 26 |
-
"summary_proj_to_labels": true,
|
| 27 |
-
"summary_type": "cls_index",
|
| 28 |
-
"summary_use_proj": true,
|
| 29 |
-
"task_specific_params": {
|
| 30 |
-
"text-generation": {
|
| 31 |
-
"do_sample": true,
|
| 32 |
-
"max_length": 50
|
| 33 |
-
}
|
| 34 |
-
},
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
"transformers_version": "4.34.1",
|
| 37 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/Pretraining-Testing/pretraining/local-models/training/2024-01-19_07-31-02",
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 2000,
|
| 13 |
+
"max_position_embeddings": 1024,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"num_key_value_heads": 12,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"torch_dtype": "float32",
|
| 24 |
"transformers_version": "4.34.1",
|
| 25 |
"use_cache": true,
|
generation_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
-
"eos_token_id":
|
| 5 |
"transformers_version": "4.34.1"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
"transformers_version": "4.34.1"
|
| 6 |
}
|
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 sha256:781985fa89f711b781ab2c66c6f6756bc2a52c9d007951d587f439f9e12702cc
|
| 3 |
+
size 488908744
|