Hugging Face's logo

sglucas
/
v3_r64_3e4_constant

Safetensors
Model card Files
xet
 Community
v3_r64_3e4_constant
File size: 7,161 Bytes
690161b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
{
  "alora_invocation_tokens": null,
  "alpha_pattern": {},
  "arrow_config": null,
  "auto_mapping": null,
  "base_model_name_or_path": "/scratch/e0672130/models/qwen3_8b_ar_fast_skeleton",
  "bias": "none",
  "corda_config": null,
  "ensure_weight_tying": false,
  "eva_config": null,
  "exclude_modules": null,
  "fan_in_fan_out": false,
  "inference_mode": true,
  "init_lora_weights": true,
  "layer_replication": null,
  "layers_pattern": null,
  "layers_to_transform": null,
  "loftq_config": {},
  "lora_alpha": 128,
  "lora_bias": false,
  "lora_dropout": 0.05,
  "lora_ga_config": null,
  "megatron_config": null,
  "megatron_core": "megatron.core",
  "modules_to_save": [
    "model.layers.0.self_attn.q_norm",
    "model.layers.0.self_attn.k_norm",
    "model.layers.0.input_layernorm",
    "model.layers.0.post_attention_layernorm",
    "model.layers.1.self_attn.q_norm",
    "model.layers.1.self_attn.k_norm",
    "model.layers.1.input_layernorm",
    "model.layers.1.post_attention_layernorm",
    "model.layers.2.self_attn.q_norm",
    "model.layers.2.self_attn.k_norm",
    "model.layers.2.input_layernorm",
    "model.layers.2.post_attention_layernorm",
    "model.layers.3.self_attn.q_norm",
    "model.layers.3.self_attn.k_norm",
    "model.layers.3.input_layernorm",
    "model.layers.3.post_attention_layernorm",
    "model.layers.4.self_attn.q_norm",
    "model.layers.4.self_attn.k_norm",
    "model.layers.4.input_layernorm",
    "model.layers.4.post_attention_layernorm",
    "model.layers.5.self_attn.q_norm",
    "model.layers.5.self_attn.k_norm",
    "model.layers.5.input_layernorm",
    "model.layers.5.post_attention_layernorm",
    "model.layers.6.self_attn.q_norm",
    "model.layers.6.self_attn.k_norm",
    "model.layers.6.input_layernorm",
    "model.layers.6.post_attention_layernorm",
    "model.layers.7.self_attn.q_norm",
    "model.layers.7.self_attn.k_norm",
    "model.layers.7.input_layernorm",
    "model.layers.7.post_attention_layernorm",
    "model.layers.8.self_attn.q_norm",
    "model.layers.8.self_attn.k_norm",
    "model.layers.8.input_layernorm",
    "model.layers.8.post_attention_layernorm",
    "model.layers.9.self_attn.q_norm",
    "model.layers.9.self_attn.k_norm",
    "model.layers.9.input_layernorm",
    "model.layers.9.post_attention_layernorm",
    "model.layers.10.self_attn.q_norm",
    "model.layers.10.self_attn.k_norm",
    "model.layers.10.input_layernorm",
    "model.layers.10.post_attention_layernorm",
    "model.layers.11.self_attn.q_norm",
    "model.layers.11.self_attn.k_norm",
    "model.layers.11.input_layernorm",
    "model.layers.11.post_attention_layernorm",
    "model.layers.12.self_attn.q_norm",
    "model.layers.12.self_attn.k_norm",
    "model.layers.12.input_layernorm",
    "model.layers.12.post_attention_layernorm",
    "model.layers.13.self_attn.q_norm",
    "model.layers.13.self_attn.k_norm",
    "model.layers.13.input_layernorm",
    "model.layers.13.post_attention_layernorm",
    "model.layers.14.self_attn.q_norm",
    "model.layers.14.self_attn.k_norm",
    "model.layers.14.input_layernorm",
    "model.layers.14.post_attention_layernorm",
    "model.layers.15.self_attn.q_norm",
    "model.layers.15.self_attn.k_norm",
    "model.layers.15.input_layernorm",
    "model.layers.15.post_attention_layernorm",
    "model.layers.16.self_attn.q_norm",
    "model.layers.16.self_attn.k_norm",
    "model.layers.16.input_layernorm",
    "model.layers.16.post_attention_layernorm",
    "model.layers.17.self_attn.q_norm",
    "model.layers.17.self_attn.k_norm",
    "model.layers.17.input_layernorm",
    "model.layers.17.post_attention_layernorm",
    "model.layers.18.self_attn.q_norm",
    "model.layers.18.self_attn.k_norm",
    "model.layers.18.input_layernorm",
    "model.layers.18.post_attention_layernorm",
    "model.layers.19.self_attn.q_norm",
    "model.layers.19.self_attn.k_norm",
    "model.layers.19.input_layernorm",
    "model.layers.19.post_attention_layernorm",
    "model.layers.20.self_attn.q_norm",
    "model.layers.20.self_attn.k_norm",
    "model.layers.20.input_layernorm",
    "model.layers.20.post_attention_layernorm",
    "model.layers.21.self_attn.q_norm",
    "model.layers.21.self_attn.k_norm",
    "model.layers.21.input_layernorm",
    "model.layers.21.post_attention_layernorm",
    "model.layers.22.self_attn.q_norm",
    "model.layers.22.self_attn.k_norm",
    "model.layers.22.input_layernorm",
    "model.layers.22.post_attention_layernorm",
    "model.layers.23.self_attn.q_norm",
    "model.layers.23.self_attn.k_norm",
    "model.layers.23.input_layernorm",
    "model.layers.23.post_attention_layernorm",
    "model.layers.24.self_attn.q_norm",
    "model.layers.24.self_attn.k_norm",
    "model.layers.24.input_layernorm",
    "model.layers.24.post_attention_layernorm",
    "model.layers.25.self_attn.q_norm",
    "model.layers.25.self_attn.k_norm",
    "model.layers.25.input_layernorm",
    "model.layers.25.post_attention_layernorm",
    "model.layers.26.self_attn.q_norm",
    "model.layers.26.self_attn.k_norm",
    "model.layers.26.input_layernorm",
    "model.layers.26.post_attention_layernorm",
    "model.layers.27.self_attn.q_norm",
    "model.layers.27.self_attn.k_norm",
    "model.layers.27.input_layernorm",
    "model.layers.27.post_attention_layernorm",
    "model.layers.28.self_attn.q_norm",
    "model.layers.28.self_attn.k_norm",
    "model.layers.28.input_layernorm",
    "model.layers.28.post_attention_layernorm",
    "model.layers.29.self_attn.q_norm",
    "model.layers.29.self_attn.k_norm",
    "model.layers.29.input_layernorm",
    "model.layers.29.post_attention_layernorm",
    "model.layers.30.self_attn.q_norm",
    "model.layers.30.self_attn.k_norm",
    "model.layers.30.input_layernorm",
    "model.layers.30.post_attention_layernorm",
    "model.layers.31.self_attn.q_norm",
    "model.layers.31.self_attn.k_norm",
    "model.layers.31.input_layernorm",
    "model.layers.31.post_attention_layernorm",
    "model.layers.32.self_attn.q_norm",
    "model.layers.32.self_attn.k_norm",
    "model.layers.32.input_layernorm",
    "model.layers.32.post_attention_layernorm",
    "model.layers.33.self_attn.q_norm",
    "model.layers.33.self_attn.k_norm",
    "model.layers.33.input_layernorm",
    "model.layers.33.post_attention_layernorm",
    "model.layers.34.self_attn.q_norm",
    "model.layers.34.self_attn.k_norm",
    "model.layers.34.input_layernorm",
    "model.layers.34.post_attention_layernorm",
    "model.layers.35.self_attn.q_norm",
    "model.layers.35.self_attn.k_norm",
    "model.layers.35.input_layernorm",
    "model.layers.35.post_attention_layernorm",
    "model.norm"
  ],
  "peft_type": "LORA",
  "peft_version": "0.19.1",
  "qalora_group_size": 16,
  "r": 64,
  "rank_pattern": {},
  "revision": null,
  "target_modules": [
    "gate_proj",
    "q_proj",
    "k_proj",
    "v_proj",
    "up_proj",
    "o_proj",
    "model.embed_tokens",
    "lm_head",
    "down_proj"
  ],
  "target_parameters": null,
  "task_type": "CAUSAL_LM",
  "trainable_token_indices": null,
  "use_bdlora": null,
  "use_dora": false,
  "use_qalora": false,
  "use_rslora": false
}