Updated compression_config to quantization_config
Browse files- config.json +22 -22
config.json
CHANGED
@@ -6,7 +6,27 @@
|
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"config_groups": {
|
11 |
"group_0": {
|
12 |
"input_activations": null,
|
@@ -36,25 +56,5 @@
|
|
36 |
"kv_cache_scheme": null,
|
37 |
"quant_method": "compressed-tensors",
|
38 |
"quantization_status": "frozen"
|
39 |
-
}
|
40 |
-
"eos_token_id": 2,
|
41 |
-
"hidden_act": "silu",
|
42 |
-
"hidden_size": 2048,
|
43 |
-
"initializer_range": 0.02,
|
44 |
-
"intermediate_size": 5632,
|
45 |
-
"max_position_embeddings": 2048,
|
46 |
-
"mlp_bias": false,
|
47 |
-
"model_type": "llama",
|
48 |
-
"num_attention_heads": 32,
|
49 |
-
"num_hidden_layers": 22,
|
50 |
-
"num_key_value_heads": 4,
|
51 |
-
"pretraining_tp": 1,
|
52 |
-
"rms_norm_eps": 1e-05,
|
53 |
-
"rope_scaling": null,
|
54 |
-
"rope_theta": 10000.0,
|
55 |
-
"tie_word_embeddings": false,
|
56 |
-
"torch_dtype": "bfloat16",
|
57 |
-
"transformers_version": "4.45.0.dev0",
|
58 |
-
"use_cache": true,
|
59 |
-
"vocab_size": 32000
|
60 |
}
|
|
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 22,
|
19 |
+
"num_key_value_heads": 4,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.45.0.dev0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000,
|
29 |
+
"quantization_config": {
|
30 |
"config_groups": {
|
31 |
"group_0": {
|
32 |
"input_activations": null,
|
|
|
56 |
"kv_cache_scheme": null,
|
57 |
"quant_method": "compressed-tensors",
|
58 |
"quantization_status": "frozen"
|
59 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
}
|