nm-autobot
commited on
Commit
•
560c270
1
Parent(s):
46bacf1
Upload LlamaForCausalLM
Browse files- config.json +15 -15
config.json
CHANGED
@@ -6,7 +6,20 @@
|
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"config_groups": {
|
11 |
"group_0": {
|
12 |
"input_activations": {
|
@@ -47,21 +60,8 @@
|
|
47 |
"kv_cache_scheme": null,
|
48 |
"quant_method": "compressed-tensors",
|
49 |
"quantization_status": "compressed",
|
50 |
-
"version": "0.6.0.
|
51 |
},
|
52 |
-
"eos_token_id": 2,
|
53 |
-
"head_dim": 64,
|
54 |
-
"hidden_act": "silu",
|
55 |
-
"hidden_size": 2048,
|
56 |
-
"initializer_range": 0.02,
|
57 |
-
"intermediate_size": 5632,
|
58 |
-
"max_position_embeddings": 2048,
|
59 |
-
"mlp_bias": false,
|
60 |
-
"model_type": "llama",
|
61 |
-
"num_attention_heads": 32,
|
62 |
-
"num_hidden_layers": 22,
|
63 |
-
"num_key_value_heads": 4,
|
64 |
-
"pretraining_tp": 1,
|
65 |
"rms_norm_eps": 1e-05,
|
66 |
"rope_scaling": null,
|
67 |
"rope_theta": 10000.0,
|
|
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"head_dim": 64,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 2048,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5632,
|
15 |
+
"max_position_embeddings": 2048,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 32,
|
19 |
+
"num_hidden_layers": 22,
|
20 |
+
"num_key_value_heads": 4,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"quantization_config": {
|
23 |
"config_groups": {
|
24 |
"group_0": {
|
25 |
"input_activations": {
|
|
|
60 |
"kv_cache_scheme": null,
|
61 |
"quant_method": "compressed-tensors",
|
62 |
"quantization_status": "compressed",
|
63 |
+
"version": "0.6.0.20240928"
|
64 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
"rms_norm_eps": 1e-05,
|
66 |
"rope_scaling": null,
|
67 |
"rope_theta": 10000.0,
|