Upload Qwen2ForCausalLM
Browse files- config.json +3 -32
- generation_config.json +2 -1
- model-00001-of-00002.safetensors +1 -1
- model.safetensors.index.json +0 -1
config.json
CHANGED
|
@@ -1,44 +1,14 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen2ForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
-
"dtype": "float16",
|
| 7 |
"eos_token_id": 151645,
|
| 8 |
"hidden_act": "silu",
|
| 9 |
"hidden_size": 3584,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 18944,
|
| 12 |
-
"layer_types": [
|
| 13 |
-
"full_attention",
|
| 14 |
-
"full_attention",
|
| 15 |
-
"full_attention",
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention"
|
| 41 |
-
],
|
| 42 |
"max_position_embeddings": 32768,
|
| 43 |
"max_window_layers": 28,
|
| 44 |
"model_type": "qwen2",
|
|
@@ -67,7 +37,8 @@
|
|
| 67 |
"rope_theta": 1000000.0,
|
| 68 |
"sliding_window": null,
|
| 69 |
"tie_word_embeddings": false,
|
| 70 |
-
"
|
|
|
|
| 71 |
"use_cache": false,
|
| 72 |
"use_sliding_window": false,
|
| 73 |
"vocab_size": 152064
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Sefika/CRE_tacred_qwen_10_2_task_memory_5_1",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 7 |
"eos_token_id": 151645,
|
| 8 |
"hidden_act": "silu",
|
| 9 |
"hidden_size": 3584,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 18944,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 32768,
|
| 13 |
"max_window_layers": 28,
|
| 14 |
"model_type": "qwen2",
|
|
|
|
| 37 |
"rope_theta": 1000000.0,
|
| 38 |
"sliding_window": null,
|
| 39 |
"tie_word_embeddings": false,
|
| 40 |
+
"torch_dtype": "float16",
|
| 41 |
+
"transformers_version": "4.45.2",
|
| 42 |
"use_cache": false,
|
| 43 |
"use_sliding_window": false,
|
| 44 |
"vocab_size": 152064
|
generation_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"do_sample": true,
|
| 3 |
"eos_token_id": [
|
| 4 |
151645,
|
|
@@ -9,5 +10,5 @@
|
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
-
"transformers_version": "4.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
"do_sample": true,
|
| 4 |
"eos_token_id": [
|
| 5 |
151645,
|
|
|
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.45.2"
|
| 14 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4761275200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e274d8ac1a3a600daa717afb1dbd520ba437d03d7701c8ec2697f25e74edcced
|
| 3 |
size 4761275200
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters": 7615616512,
|
| 4 |
"total_size": 5851159328
|
| 5 |
},
|
| 6 |
"weight_map": {
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
|
|
|
| 3 |
"total_size": 5851159328
|
| 4 |
},
|
| 5 |
"weight_map": {
|