rashmi commited on
Commit
a453482
1 Parent(s): b5fc670
app.py CHANGED
@@ -167,8 +167,6 @@ def do_inference(full_text):
167
  model_paths = [
168
  'model_finetuned/HuggingFaceH4-zephyr-7b-beta_fold0_best.pth']
169
 
170
- # config_path = ("/home/rashmi/Documents/kaggle/h2oai_predict_llm/src/models_exp56/config.pth")
171
-
172
  def prepare_input(cfg, text):
173
  inputs = cfg.tokenizer.encode_plus(
174
  text,
@@ -182,7 +180,6 @@ def do_inference(full_text):
182
  inputs[k] = torch.tensor(v, dtype=torch.long)
183
  return inputs
184
 
185
- # model = CustomModel()
186
  state = torch.load(model_paths[0], map_location=torch.device("cpu"))
187
  model.load_state_dict(state["model"] ,strict=False)
188
  model.eval()
@@ -236,8 +233,6 @@ with gr.Blocks(title=title) as demo: # theme=theme
236
  example_list = sample_examples[['Question','Response','target']].sample(2).values.tolist()
237
  gr.Markdown(f"## {title}")
238
  with gr.Row():
239
- # with gr.Column(scale=1):
240
- # gr.Markdown("### Question and LLM Response")
241
  question_text = gr.Textbox(lines=2, placeholder="Question:", label="")
242
  response_text = gr.Textbox(lines=2, placeholder="Response:", label="")
243
  target_text = gr.Textbox(lines=1, placeholder="Target:", label="", interactive=False , visible=False)
@@ -250,7 +245,6 @@ with gr.Blocks(title=title) as demo: # theme=theme
250
  gr.Examples(
251
  example_list,
252
  [question_text,response_text,target_text],
253
- # cache_examples=True,
254
  )
255
 
256
  demo.launch(greet)
 
167
  model_paths = [
168
  'model_finetuned/HuggingFaceH4-zephyr-7b-beta_fold0_best.pth']
169
 
 
 
170
  def prepare_input(cfg, text):
171
  inputs = cfg.tokenizer.encode_plus(
172
  text,
 
180
  inputs[k] = torch.tensor(v, dtype=torch.long)
181
  return inputs
182
 
 
183
  state = torch.load(model_paths[0], map_location=torch.device("cpu"))
184
  model.load_state_dict(state["model"] ,strict=False)
185
  model.eval()
 
233
  example_list = sample_examples[['Question','Response','target']].sample(2).values.tolist()
234
  gr.Markdown(f"## {title}")
235
  with gr.Row():
 
 
236
  question_text = gr.Textbox(lines=2, placeholder="Question:", label="")
237
  response_text = gr.Textbox(lines=2, placeholder="Response:", label="")
238
  target_text = gr.Textbox(lines=1, placeholder="Target:", label="", interactive=False , visible=False)
 
245
  gr.Examples(
246
  example_list,
247
  [question_text,response_text,target_text],
 
248
  )
249
 
250
  demo.launch(greet)
save_pretrained_model/zephyr-7b-beta/config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
3
- "architectures": [
4
- "MistralForCausalLM"
5
- ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
8
- "hidden_act": "silu",
9
- "hidden_size": 4096,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 14336,
12
- "max_position_embeddings": 32768,
13
- "model_type": "mistral",
14
- "num_attention_heads": 32,
15
- "num_hidden_layers": 32,
16
- "num_key_value_heads": 8,
17
- "pad_token_id": 2,
18
- "rms_norm_eps": 1e-05,
19
- "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
- "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.36.0.dev0",
24
- "use_cache": true,
25
- "vocab_size": 32000
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
save_pretrained_model/zephyr-7b-beta/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.36.0.dev0"
6
- }
 
 
 
 
 
 
 
save_pretrained_model/zephyr-7b-beta/model-00001-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2023a2a717ff20e941c21d68bc48916354e976800a8393ba11df59060584ac3a
3
- size 4987196936
 
 
 
 
save_pretrained_model/zephyr-7b-beta/model-00002-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:89d0d703099ade2eb1e06019d8fc176598a599a92a5c70b55e8a5cb77215b421
3
- size 4899116440
 
 
 
 
save_pretrained_model/zephyr-7b-beta/model-00003-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:448db92c8f5e610971f050d84dd16607e0e895b34d07cf0cd3e21b88c3131aeb
3
- size 4999813120
 
 
 
 
save_pretrained_model/zephyr-7b-beta/model-00004-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e49c54167036eee8493ccfa313edec808f8b6c508ef747c7a84e7abe2b01c3a
3
- size 4999813128
 
 
 
 
save_pretrained_model/zephyr-7b-beta/model-00005-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0edab06947c8702d3a61fab57f84e052d46fbbd77e8e3e206bc7d0802879022
3
- size 4832007496
 
 
 
 
save_pretrained_model/zephyr-7b-beta/model-00006-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2caf0970ab661caf158ca08992d814798689d101e70b19a7fd2e4b7b45eff73
3
- size 4249014896
 
 
 
 
save_pretrained_model/zephyr-7b-beta/model.safetensors.index.json DELETED
@@ -1,298 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 28966928384
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00006-of-00006.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
296
- "model.norm.weight": "model-00006-of-00006.safetensors"
297
- }
298
- }