Upload config.json
Browse files- config.json +14 -4
config.json
CHANGED
@@ -1,17 +1,21 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "./Hathor_Tahsin-L3-8B-v0.
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
-
"max_position_embeddings":
|
15 |
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 32,
|
@@ -19,7 +23,13 @@
|
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
-
"rope_scaling":
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"rope_theta": 500000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./Hathor_Tahsin-L3-8B-v0.9",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
"hidden_act": "silu",
|
15 |
"hidden_size": 4096,
|
16 |
"initializer_range": 0.02,
|
17 |
"intermediate_size": 14336,
|
18 |
+
"max_position_embeddings": 131072,
|
19 |
"mlp_bias": false,
|
20 |
"model_type": "llama",
|
21 |
"num_attention_heads": 32,
|
|
|
23 |
"num_key_value_heads": 8,
|
24 |
"pretraining_tp": 1,
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
+
"rope_scaling": {
|
27 |
+
"factor": 8.0,
|
28 |
+
"low_freq_factor": 1.0,
|
29 |
+
"high_freq_factor": 4.0,
|
30 |
+
"original_max_position_embeddings": 8192,
|
31 |
+
"rope_type": "llama3"
|
32 |
+
},
|
33 |
"rope_theta": 500000.0,
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "bfloat16",
|