Upload folder using huggingface_hub
Browse files- config.json +50 -0
- generation_config.json +13 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.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": 4,
|
29 |
+
"optimize": true,
|
30 |
+
"round_zero": true,
|
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-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41459606ef1dab4845c97acabe71481ce547852e31d53f58f7245d377d3671c7
|
3 |
+
size 4974301316
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a842f6934403b1cdf233369caac4927919a07cbf1d915b442d58b1c18086efde
|
3 |
+
size 4937480480
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f212fbce81a51536e6412385e17d00e6d44bfda18f0d640b0db25912d610a13d
|
3 |
+
size 4937480480
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6087a5339a200b630ced23b77e18bb9a71c5fac0d1f33d04f0bc7320a6df8df8
|
3 |
+
size 4262058164
|
model-00005-of-00005.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
|
|