ArtusDev commited on
Commit
48ac454
·
verified ·
1 Parent(s): 7e2bc71

Upload folder using huggingface_hub

Browse files
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": 128,
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 sha256:672eacceb3ec2c3e9ac9807bb118a0503a650e8116fc5ee4e51c9a10f057f977
3
+ size 4940662176
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b80650b52536e80f340789335a2df246268471b37dcb7ecb5497c30394259cd
3
+ size 4893441948
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:760c8c4a28a06cb9ee94430bd4fe8c6349d57cead638300ad1de3e734df25808
3
+ size 4893442348
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42f70091f939431dceab36daf10f932ac78a1849100cc684cd82f88ecb35bec
3
+ size 4985355860
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16ed26af279f6c37eea0c4c4c2df2b534fbcff5ee64995956b8257612687610
3
+ size 4974538828
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78c26fd2c01c7211b51882ae7cd1398b82a2274009807967c82249d2de8d866
3
+ size 4893421652
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e40ce2fa47282039afb82fd5c77a949b5a1618ffe4955c47e4ffbfe80b9b1c7
3
+ size 4158090956
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3b405673668d9fc3fbac99d011027804a43e0c5e6e8b5444a58738e973a65b
3
+ size 1555824768
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff