Upload folder using huggingface_hub
Browse files- config.json +50 -0
- generation_config.json +13 -0
- model-00001-of-00008.safetensors +3 -0
- model-00002-of-00008.safetensors +3 -0
- model-00003-of-00008.safetensors +3 -0
- model-00004-of-00008.safetensors +3 -0
- model-00005-of-00008.safetensors +3 -0
- model-00006-of-00008.safetensors +3 -0
- model-00007-of-00008.safetensors +3 -0
- model-00008-of-00008.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen3ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 25600,
|
14 |
+
"max_position_embeddings": 40960,
|
15 |
+
"max_window_layers": 64,
|
16 |
+
"model_type": "qwen3",
|
17 |
+
"num_attention_heads": 64,
|
18 |
+
"num_hidden_layers": 64,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"quantization_config": {
|
21 |
+
"quant_config": {
|
22 |
+
"offload_meta": false,
|
23 |
+
"scale_quant_params": null,
|
24 |
+
"weight_quant_params": {
|
25 |
+
"axis": 1,
|
26 |
+
"channel_wise": true,
|
27 |
+
"group_size": 64,
|
28 |
+
"nbits": 8,
|
29 |
+
"optimize": true,
|
30 |
+
"round_zero": false,
|
31 |
+
"view_as_float": false
|
32 |
+
},
|
33 |
+
"zero_quant_params": null
|
34 |
+
},
|
35 |
+
"quant_method": "hqq",
|
36 |
+
"skip_modules": [
|
37 |
+
"lm_head"
|
38 |
+
]
|
39 |
+
},
|
40 |
+
"rms_norm_eps": 1e-06,
|
41 |
+
"rope_scaling": null,
|
42 |
+
"rope_theta": 1000000,
|
43 |
+
"sliding_window": null,
|
44 |
+
"tie_word_embeddings": false,
|
45 |
+
"torch_dtype": "float16",
|
46 |
+
"transformers_version": "4.51.3",
|
47 |
+
"use_cache": true,
|
48 |
+
"use_sliding_window": false,
|
49 |
+
"vocab_size": 151936
|
50 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"temperature": 0.6,
|
10 |
+
"top_k": 20,
|
11 |
+
"top_p": 0.95,
|
12 |
+
"transformers_version": "4.51.3"
|
13 |
+
}
|
model-00001-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4ac05c872ae77a05055b3784bdee673a8fbf0dca1129893b7518749e24819ba
|
3 |
+
size 4903959916
|
model-00002-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a49b3adee0429b9ad347c1fa79b1c11d7b226ba1fbaefbc245f002ac6f205636
|
3 |
+
size 4997149816
|
model-00003-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:347be83f9decca5dd9cb4181273bcead24a832e668601ea816344b29ce3d0417
|
3 |
+
size 4985984920
|
model-00004-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8320977427fa060c35c1de7c81f4ef59291a93eaf33a2e29cbf60e97d6f1290c
|
3 |
+
size 4902451560
|
model-00005-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45953ca0381075e7e0353faa4e8ddf2b0b24a9a49342cba56ad4bd54620bcc87
|
3 |
+
size 4941417588
|
model-00006-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d4ed3b831f8c99dc6b86a878b2669b1c792bbe53e0edd174c3f8f336fd40a43
|
3 |
+
size 4902451560
|
model-00007-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76250d6ef2949c09159167edc23a6a26db8b82f81bc2df56bd8df477c2989ea8
|
3 |
+
size 4941417588
|
model-00008-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bbe217bf73bff5ec6a4e9cfe49e325c117d9d6d0fa3ecd101f6e29fdfdb9aa7
|
3 |
+
size 1695121900
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|