Upload folder using huggingface_hub
Browse files- config.json +31 -0
- inc_config.json +13 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "GeneZC/MiniChat-2-3B",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"backend": "default",
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 3072,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 8192,
|
15 |
+
"max_position_embeddings": 4096,
|
16 |
+
"model_type": "llama",
|
17 |
+
"noisy_embedding_alpha": 5.0,
|
18 |
+
"num_attention_heads": 24,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"num_key_value_heads": 24,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "int8",
|
28 |
+
"transformers_version": "4.37.0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 49216
|
31 |
+
}
|
inc_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"distillation": {},
|
3 |
+
"neural_compressor_version": "2.4.1",
|
4 |
+
"optimum_version": "1.16.2",
|
5 |
+
"pruning": {},
|
6 |
+
"quantization": {
|
7 |
+
"dataset_num_samples": null,
|
8 |
+
"is_static": false
|
9 |
+
},
|
10 |
+
"save_onnx_model": false,
|
11 |
+
"torch_version": "2.1.0+cu118",
|
12 |
+
"transformers_version": "4.37.0"
|
13 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4f4cd7d8f955ced0e813a2f59a44f26e17fe64f2445d249e6dd4c408eab0eaa
|
3 |
+
size 3034625294
|