Training in progress, epoch 0
Browse files- config.json +9 -9
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- trainer_log.jsonl +0 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Qwen/Qwen2.5-
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
|
@@ -7,23 +7,23 @@
|
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
-
"hidden_size":
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size":
|
| 13 |
"max_position_embeddings": 32768,
|
| 14 |
-
"max_window_layers":
|
| 15 |
"model_type": "qwen2",
|
| 16 |
-
"num_attention_heads":
|
| 17 |
-
"num_hidden_layers":
|
| 18 |
-
"num_key_value_heads":
|
| 19 |
"rms_norm_eps": 1e-06,
|
| 20 |
"rope_scaling": null,
|
| 21 |
"rope_theta": 1000000.0,
|
| 22 |
"sliding_window": null,
|
| 23 |
-
"tie_word_embeddings":
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.46.1",
|
| 26 |
"use_cache": false,
|
| 27 |
"use_sliding_window": false,
|
| 28 |
-
"vocab_size":
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
|
|
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 18944,
|
| 13 |
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 28,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
"rms_norm_eps": 1e-06,
|
| 20 |
"rope_scaling": null,
|
| 21 |
"rope_theta": 1000000.0,
|
| 22 |
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.46.1",
|
| 26 |
"use_cache": false,
|
| 27 |
"use_sliding_window": false,
|
| 28 |
+
"vocab_size": 152064
|
| 29 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76304d214fae0a740bb4fbc3c23abb9300610273f5b3d5ca132dcce44092b64f
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:079bfb3f0ed47587461c74f3be997fcc232d133f9476971ec76d71f7a98e25ea
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73745049d80771cf6f864bceb36015477879a88a966bc6b47906479f79b34525
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a8d94aa13d1614a7b4523b345cde3fcce160cd5190a9d5deb809a3a69d7557c
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d5f0e0df88dd6b6ab5eff60b853a170062518dc475660ba7b8aa73216d36b48
|
| 3 |
size 7480
|