Trained with Unsloth
Browse files- config.json +8 -10
- generation_config.json +11 -7
- pytorch_model-00001-of-00004.bin +2 -2
- pytorch_model-00002-of-00004.bin +2 -2
- pytorch_model-00003-of-00004.bin +2 -2
- pytorch_model-00004-of-00004.bin +1 -1
config.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
-
"bos_token_id":
|
8 |
-
"eos_token_id":
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 3584,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 18944,
|
13 |
-
"max_position_embeddings":
|
14 |
"max_window_layers": 28,
|
15 |
"model_type": "qwen2",
|
16 |
"num_attention_heads": 28,
|
@@ -19,15 +19,13 @@
|
|
19 |
"pad_token_id": 151654,
|
20 |
"rms_norm_eps": 1e-06,
|
21 |
"rope_scaling": null,
|
22 |
-
"rope_theta":
|
23 |
-
"sliding_window":
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float16",
|
26 |
-
"transformers_version": "4.
|
27 |
-
"unsloth_fixed": true,
|
28 |
"unsloth_version": "2025.3.9",
|
29 |
-
"use_cache":
|
30 |
-
"use_mrope": false,
|
31 |
"use_sliding_window": false,
|
32 |
"vocab_size": 152064
|
33 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Mingsmilet/Qwen2.5-7B-R1-SFT",
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
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,
|
|
|
19 |
"pad_token_id": 151654,
|
20 |
"rms_norm_eps": 1e-06,
|
21 |
"rope_scaling": null,
|
22 |
+
"rope_theta": 1000000.0,
|
23 |
+
"sliding_window": 131072,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.49.0",
|
|
|
27 |
"unsloth_version": "2025.3.9",
|
28 |
+
"use_cache": false,
|
|
|
29 |
"use_sliding_window": false,
|
30 |
"vocab_size": 152064
|
31 |
}
|
generation_config.json
CHANGED
@@ -1,11 +1,15 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"bos_token_id": 151646,
|
4 |
"do_sample": true,
|
5 |
-
"eos_token_id":
|
6 |
-
|
|
|
|
|
|
|
7 |
"pad_token_id": 151654,
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token_id": 151643,
|
|
|
3 |
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"max_length": 32768,
|
9 |
"pad_token_id": 151654,
|
10 |
+
"repetition_penalty": 1.05,
|
11 |
+
"temperature": 0.7,
|
12 |
+
"top_k": 20,
|
13 |
+
"top_p": 0.8,
|
14 |
+
"transformers_version": "4.49.0"
|
15 |
}
|
pytorch_model-00001-of-00004.bin
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 sha256:90dd35fc5289bf8c40fc13c20242d152817af0deadc07b45af891924a2e13da2
|
3 |
+
size 4877685654
|
pytorch_model-00002-of-00004.bin
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 sha256:3ac23acd8febfa7062ee7bf6f55b27139d50ed0d97c0508eb866deae24e3fd19
|
3 |
+
size 4932779944
|
pytorch_model-00003-of-00004.bin
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 sha256:978a8674e40ad70b9fd54fc08bd632d0b59257d8045e26d128df3efa93c91603
|
3 |
+
size 4330891098
|
pytorch_model-00004-of-00004.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089996165
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6f1b2ce95ac135390dbf85a0b90e11cee908fae0c8a6aff9628d84f4e835998
|
3 |
size 1089996165
|