Upload 4 files
Browse files- config.json +34 -0
- generation_config.json +4 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"head_dim": 64,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 1024,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention"
|
| 18 |
+
],
|
| 19 |
+
"max_position_embeddings": 1024,
|
| 20 |
+
"max_window_layers": 28,
|
| 21 |
+
"model_type": "qwen3",
|
| 22 |
+
"num_attention_heads": 4,
|
| 23 |
+
"num_hidden_layers": 4,
|
| 24 |
+
"num_key_value_heads": 4,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 100000.0,
|
| 28 |
+
"sliding_window": null,
|
| 29 |
+
"tie_word_embeddings": true,
|
| 30 |
+
"transformers_version": "4.57.4",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"use_sliding_window": false,
|
| 33 |
+
"vocab_size": 2052
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.57.4"
|
| 4 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03e6dfb67b603e297363156d805d412cf5832e8d3662ec6d8121d19d169c947d
|
| 3 |
+
size 18894672
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|