stratplans
commited on
Commit
•
fc985db
1
Parent(s):
d874d21
Upload 16 files
Browse files- config.json +32 -0
- generation_config.json +14 -0
- model-00001-of-00029.safetensors +3 -0
- model-00005-of-00029.safetensors +3 -0
- model-00011-of-00029.safetensors +3 -0
- model-00021-of-00029.safetensors +3 -0
- model-00022-of-00029.safetensors +3 -0
- model-00024-of-00029.safetensors +3 -0
- model-00029-of-00029.safetensors +3 -0
- special_tokens_map.json +31 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "GoldSaturn-72B-Instruct",
|
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": 5120,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 27648,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 70,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 40,
|
17 |
+
"num_hidden_layers": 64,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": {
|
21 |
+
"factor": 4.0,
|
22 |
+
"original_max_position_embeddings": 32768,
|
23 |
+
"type": "yarn"
|
24 |
+
},"rope_theta": 1000000.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.46.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"use_sliding_window": false,
|
31 |
+
"vocab_size": 152064
|
32 |
+
}
|
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": 1.05,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.46.2"
|
14 |
+
}
|
model-00001-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36e1b4b1fbdc6f85eb90d097651f235ace6f7e45582f609224c9af942e59ff2e
|
3 |
+
size 4498420872
|
model-00005-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85ebf5c85900fcc01ee29eab0ea04b63c3726d257191c5eaff9e87b0a4af5bbd
|
3 |
+
size 4718804760
|
model-00011-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ae718d40e9a4c63a4ffc6a6d6f2edd116ee5baa083209ae507fea76013e7357
|
3 |
+
size 4718804800
|
model-00021-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d5abe09a1578b7eb1ab57df097208c1cf7c8a3660d7d57bdd589076782d0488
|
3 |
+
size 4467075904
|
model-00022-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e7aad057ec47c2532dd36c693d60464095b5ad0296af0af3d7cadfbf06ddac3
|
3 |
+
size 4467075904
|
model-00024-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4902a14f93a2011779ba7b375edf646f94d1f7b4f4f09b2e4b81310223929ba
|
3 |
+
size 4467075904
|
model-00029-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c334ff2389fd7e08caec2efc5d1680f769c70aa2ea6567a742a2654a2f8dae0
|
3 |
+
size 3680563768
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|