Initial blueprint: untrained 520M dense base
Browse files- config.json +60 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": null,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": null,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 65536,
|
| 40 |
+
"max_window_layers": 20,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"num_attention_heads": 16,
|
| 43 |
+
"num_hidden_layers": 24,
|
| 44 |
+
"num_key_value_heads": 4,
|
| 45 |
+
"pad_token_id": null,
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rope_parameters": {
|
| 48 |
+
"factor": 8.0,
|
| 49 |
+
"original_max_position_embeddings": 8192,
|
| 50 |
+
"rope_theta": 1000000.0,
|
| 51 |
+
"rope_type": "yarn",
|
| 52 |
+
"type": "yarn"
|
| 53 |
+
},
|
| 54 |
+
"sliding_window": 4096,
|
| 55 |
+
"tie_word_embeddings": true,
|
| 56 |
+
"transformers_version": "5.3.0",
|
| 57 |
+
"use_cache": false,
|
| 58 |
+
"use_sliding_window": true,
|
| 59 |
+
"vocab_size": 248044
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_attentions": false,
|
| 4 |
+
"output_hidden_states": false,
|
| 5 |
+
"transformers_version": "5.3.0",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15440a0da86ccafbb90137a000359ac26a11665425aff7f2adbf475e0a4a93ca
|
| 3 |
+
size 1238009856
|