Update config.json
Browse files- config.json +28 -39
config.json
CHANGED
@@ -1,40 +1,29 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "neversleep/llama-3-lumimaid-8b-v0.1",
|
3 |
-
"architectures": [
|
4 |
-
"LlamaForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_bias": false,
|
7 |
-
"attention_dropout": 0.0,
|
8 |
-
"bos_token_id": 128000,
|
9 |
-
"eos_token_id": 128001,
|
10 |
-
"hidden_act": "silu",
|
11 |
-
"hidden_size": 4096,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 14336,
|
14 |
-
"max_position_embeddings": 8192,
|
15 |
-
"mlp_bias": false,
|
16 |
-
"model_type": "llama",
|
17 |
-
"num_attention_heads": 32,
|
18 |
-
"num_hidden_layers": 32,
|
19 |
-
"num_key_value_heads": 8,
|
20 |
-
"pretraining_tp": 1,
|
21 |
-
"rms_norm_eps": 1e-05,
|
22 |
-
"rope_scaling": null,
|
23 |
-
"rope_theta": 500000.0,
|
24 |
-
"tie_word_embeddings": false,
|
25 |
-
"torch_dtype": "float16",
|
26 |
-
"transformers_version": "4.41.0.dev0",
|
27 |
-
"use_cache": true,
|
28 |
-
"vocab_size": 128256
|
29 |
-
"quantization_config": {
|
30 |
-
"quant_method": "exl2",
|
31 |
-
"version": "0.0.20",
|
32 |
-
"bits": 6.5,
|
33 |
-
"head_bits": 8,
|
34 |
-
"calibration": {
|
35 |
-
"rows": 100,
|
36 |
-
"length": 2048,
|
37 |
-
"dataset": "(default)"
|
38 |
-
}
|
39 |
-
}
|
40 |
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neversleep/llama-3-lumimaid-8b-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128001,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 500000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.41.0.dev0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 128256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|