Add files using upload-large-folder tool
Browse files- checkpoint-10000/config.json +28 -0
- checkpoint-10000/generation_config.json +14 -0
- checkpoint-10000/model.safetensors +3 -0
- checkpoint-10000/rng_state_0.pth +3 -0
- checkpoint-10000/rng_state_1.pth +3 -0
- checkpoint-10000/rng_state_2.pth +3 -0
- checkpoint-10000/rng_state_3.pth +3 -0
- checkpoint-10000/rng_state_4.pth +3 -0
- checkpoint-10000/rng_state_5.pth +3 -0
- checkpoint-10000/rng_state_6.pth +3 -0
- checkpoint-10000/rng_state_7.pth +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/trainer_state.json +0 -0
- checkpoint-13516/config.json +28 -0
- checkpoint-13516/generation_config.json +14 -0
- checkpoint-13516/model.safetensors +3 -0
- checkpoint-13516/rng_state_0.pth +3 -0
- checkpoint-13516/rng_state_1.pth +3 -0
- checkpoint-13516/rng_state_2.pth +3 -0
- checkpoint-13516/rng_state_3.pth +3 -0
- checkpoint-13516/rng_state_4.pth +3 -0
- checkpoint-13516/rng_state_5.pth +3 -0
- checkpoint-13516/rng_state_6.pth +3 -0
- checkpoint-13516/rng_state_7.pth +3 -0
- checkpoint-13516/scheduler.pt +3 -0
- checkpoint-13516/trainer_state.json +0 -0
checkpoint-10000/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 896,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4864,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 21,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 14,
|
16 |
+
"num_hidden_layers": 24,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": 32768,
|
22 |
+
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.51.3",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 180348
|
28 |
+
}
|
checkpoint-10000/generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.51.3"
|
14 |
+
}
|
checkpoint-10000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e24df4e047aeff5b9e5031d60f3f11a296c99573c60283318b44a975b6ff1a3f
|
3 |
+
size 2724359584
|
checkpoint-10000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:955b895101e13c81ba510512313a06782795770a0bf998c90f718166d25f1664
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:096e351ace65ff91008be171a45173ed6369cc639fce73a288f671041e24b0ec
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21c61b1a7e793bbdec183de3b52da90042305234bc7e5887986655cd3fc2192
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:348742498d81780506d9760c655a7a7555185b5fbd70a7ae296d88fd9aeecd84
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:399c4700dab9ae7b754110ce307fb7e26e22cb49b5bb233c435f0f12b77c202f
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:864ea2379cc907eb4189c52706cb978150d9c26e18abf74679590729a8f0c8e8
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25755ba07299ee6ff45936dd04df329596319c9f8095af71e6f3a219e7543e26
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:908f018cd701ed629c41299726da4a25f202f20a1d4bc2075a2266ed4013db3a
|
3 |
+
size 15984
|
checkpoint-10000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cd6a170ab3bb5cec7506f1e8e912eeab4dceeec5970413ee59b2c75e6838b1d
|
3 |
+
size 1064
|
checkpoint-10000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-13516/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 896,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4864,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 21,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 14,
|
16 |
+
"num_hidden_layers": 24,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": 32768,
|
22 |
+
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.51.3",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 180348
|
28 |
+
}
|
checkpoint-13516/generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.51.3"
|
14 |
+
}
|
checkpoint-13516/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d46ae7f9d0b29be5ecb706640bb202801c6e342190260d50a9e7a67dd225ca4a
|
3 |
+
size 2724359584
|
checkpoint-13516/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:955b895101e13c81ba510512313a06782795770a0bf998c90f718166d25f1664
|
3 |
+
size 15984
|
checkpoint-13516/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:096e351ace65ff91008be171a45173ed6369cc639fce73a288f671041e24b0ec
|
3 |
+
size 15984
|
checkpoint-13516/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21c61b1a7e793bbdec183de3b52da90042305234bc7e5887986655cd3fc2192
|
3 |
+
size 15984
|
checkpoint-13516/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:348742498d81780506d9760c655a7a7555185b5fbd70a7ae296d88fd9aeecd84
|
3 |
+
size 15984
|
checkpoint-13516/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:399c4700dab9ae7b754110ce307fb7e26e22cb49b5bb233c435f0f12b77c202f
|
3 |
+
size 15984
|
checkpoint-13516/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:864ea2379cc907eb4189c52706cb978150d9c26e18abf74679590729a8f0c8e8
|
3 |
+
size 15984
|
checkpoint-13516/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25755ba07299ee6ff45936dd04df329596319c9f8095af71e6f3a219e7543e26
|
3 |
+
size 15984
|
checkpoint-13516/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:908f018cd701ed629c41299726da4a25f202f20a1d4bc2075a2266ed4013db3a
|
3 |
+
size 15984
|
checkpoint-13516/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37440d9bb368c855c839ef6bd46a9e59708a7980e219c093a9ca6c3e2e721de2
|
3 |
+
size 1064
|
checkpoint-13516/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|