Instructions to use VextLabsinc/gem-ruby with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use VextLabsinc/gem-ruby with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("VextLabsinc/juwel-beryl") model = PeftModel.from_pretrained(base_model, "VextLabsinc/gem-ruby") - Notebooks
- Google Colab
- Kaggle
weights: adapter_config.json
Browse files- adapter_config.json +130 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "/models/theron/base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": [
|
| 18 |
+
0,
|
| 19 |
+
1,
|
| 20 |
+
2,
|
| 21 |
+
3,
|
| 22 |
+
4,
|
| 23 |
+
5,
|
| 24 |
+
6,
|
| 25 |
+
7,
|
| 26 |
+
8,
|
| 27 |
+
9,
|
| 28 |
+
10,
|
| 29 |
+
11,
|
| 30 |
+
12,
|
| 31 |
+
13,
|
| 32 |
+
14,
|
| 33 |
+
15,
|
| 34 |
+
16,
|
| 35 |
+
17,
|
| 36 |
+
18,
|
| 37 |
+
19,
|
| 38 |
+
20,
|
| 39 |
+
21,
|
| 40 |
+
22,
|
| 41 |
+
23,
|
| 42 |
+
24,
|
| 43 |
+
25,
|
| 44 |
+
26,
|
| 45 |
+
27,
|
| 46 |
+
28,
|
| 47 |
+
29,
|
| 48 |
+
30,
|
| 49 |
+
31,
|
| 50 |
+
32,
|
| 51 |
+
33,
|
| 52 |
+
34,
|
| 53 |
+
35,
|
| 54 |
+
36,
|
| 55 |
+
37,
|
| 56 |
+
38,
|
| 57 |
+
39,
|
| 58 |
+
40,
|
| 59 |
+
41,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
47,
|
| 66 |
+
48,
|
| 67 |
+
49,
|
| 68 |
+
50,
|
| 69 |
+
51,
|
| 70 |
+
52,
|
| 71 |
+
53,
|
| 72 |
+
54,
|
| 73 |
+
55,
|
| 74 |
+
56,
|
| 75 |
+
57,
|
| 76 |
+
58,
|
| 77 |
+
59,
|
| 78 |
+
60,
|
| 79 |
+
61,
|
| 80 |
+
62,
|
| 81 |
+
63,
|
| 82 |
+
64,
|
| 83 |
+
65,
|
| 84 |
+
66,
|
| 85 |
+
67,
|
| 86 |
+
68,
|
| 87 |
+
69,
|
| 88 |
+
70,
|
| 89 |
+
71,
|
| 90 |
+
72,
|
| 91 |
+
73,
|
| 92 |
+
74,
|
| 93 |
+
75,
|
| 94 |
+
76,
|
| 95 |
+
77,
|
| 96 |
+
78,
|
| 97 |
+
79
|
| 98 |
+
],
|
| 99 |
+
"loftq_config": {},
|
| 100 |
+
"lora_alpha": 128,
|
| 101 |
+
"lora_bias": false,
|
| 102 |
+
"lora_dropout": 0.05,
|
| 103 |
+
"lora_ga_config": null,
|
| 104 |
+
"megatron_config": null,
|
| 105 |
+
"megatron_core": "megatron.core",
|
| 106 |
+
"modules_to_save": null,
|
| 107 |
+
"peft_type": "LORA",
|
| 108 |
+
"peft_version": "0.19.1",
|
| 109 |
+
"qalora_group_size": 16,
|
| 110 |
+
"r": 64,
|
| 111 |
+
"rank_pattern": {},
|
| 112 |
+
"revision": null,
|
| 113 |
+
"target_modules": [
|
| 114 |
+
"k_proj",
|
| 115 |
+
"down_proj",
|
| 116 |
+
"gate_proj",
|
| 117 |
+
"v_proj",
|
| 118 |
+
"up_proj",
|
| 119 |
+
"q_proj",
|
| 120 |
+
"o_proj"
|
| 121 |
+
],
|
| 122 |
+
"target_parameters": null,
|
| 123 |
+
"task_type": "CAUSAL_LM",
|
| 124 |
+
"trainable_token_indices": null,
|
| 125 |
+
"use_bdlora": null,
|
| 126 |
+
"use_dora": false,
|
| 127 |
+
"use_qalora": false,
|
| 128 |
+
"use_rslora": false,
|
| 129 |
+
"_padded_from_v9": true
|
| 130 |
+
}
|