zhaicunqi commited on
Commit
0afe74a
1 Parent(s): d97ef8e

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "ZhinaoForCausalLM"
4
  ],
@@ -6,8 +7,8 @@
6
  "AutoConfig": "configuration_zhinao.ZhinaoConfig",
7
  "AutoModelForCausalLM": "modeling_zhinao.ZhinaoForCausalLM"
8
  },
9
- "bf16": true,
10
- "fp16": false,
11
  "hidden_act": "silu",
12
  "hidden_size": 4096,
13
  "initializer_range": 0.01,
@@ -19,25 +20,35 @@
19
  "num_hidden_layers": 32,
20
  "num_key_value_heads": 32,
21
  "quantization_config": {
 
22
  "bits": 4,
23
- "checkpoint_format": "gptq",
24
- "damp_percent": 0.01,
 
25
  "desc_act": false,
 
 
 
26
  "group_size": 128,
27
- "model_file_base_name": "gptq_model-4bit-128g",
28
- "model_name_or_path": "360Zhinao-7B-Chat-4K-Int4",
 
 
 
29
  "quant_method": "gptq",
30
- "static_groups": false,
31
  "sym": true,
32
- "true_sequential": true
 
 
 
33
  },
34
  "rms_norm_eps": 1e-05,
35
  "rope_scaling": null,
36
  "rope_theta": 10000.0,
37
  "tie_word_embeddings": false,
38
  "torch_dtype": "float16",
39
- "transformers_version": "4.38.2",
40
  "use_cache": false,
41
- "use_flash_attn": "auto",
42
  "vocab_size": 158464
43
  }
 
1
  {
2
+ "_name_or_path": "360Zhinao-7B-Chat-4K",
3
  "architectures": [
4
  "ZhinaoForCausalLM"
5
  ],
 
7
  "AutoConfig": "configuration_zhinao.ZhinaoConfig",
8
  "AutoModelForCausalLM": "modeling_zhinao.ZhinaoForCausalLM"
9
  },
10
+ "bf16": false,
11
+ "fp16": true,
12
  "hidden_act": "silu",
13
  "hidden_size": 4096,
14
  "initializer_range": 0.01,
 
20
  "num_hidden_layers": 32,
21
  "num_key_value_heads": 32,
22
  "quantization_config": {
23
+ "batch_size": 1,
24
  "bits": 4,
25
+ "block_name_to_quantize": null,
26
+ "cache_block_outputs": true,
27
+ "damp_percent": 0.1,
28
  "desc_act": false,
29
+ "exllama_config": {
30
+ "version": 1
31
+ },
32
  "group_size": 128,
33
+ "max_input_length": null,
34
+ "model_seqlen": null,
35
+ "module_name_preceding_first_block": null,
36
+ "modules_in_block_to_quantize": null,
37
+ "pad_token_id": null,
38
  "quant_method": "gptq",
 
39
  "sym": true,
40
+ "tokenizer": null,
41
+ "true_sequential": true,
42
+ "use_cuda_fp16": false,
43
+ "use_exllama": true
44
  },
45
  "rms_norm_eps": 1e-05,
46
  "rope_scaling": null,
47
  "rope_theta": 10000.0,
48
  "tie_word_embeddings": false,
49
  "torch_dtype": "float16",
50
+ "transformers_version": "4.38.1",
51
  "use_cache": false,
52
+ "use_flash_attn": true,
53
  "vocab_size": 158464
54
  }
generation_config.json CHANGED
@@ -1,12 +1,14 @@
1
  {
2
- "do_sample": true,
3
- "top_k": 0,
4
- "top_p": 0.8,
5
- "temperature": 1.0,
6
- "repetition_penalty": 1.0,
7
- "pad_token_id": 158326,
8
- "eos_token_id": [158326, 158332, 158333],
9
- "max_new_tokens": 1024,
10
- "_from_model_config": true,
11
- "transformers_version": "4.38.2"
12
- }
 
 
 
1
  {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 158326,
6
+ 158332,
7
+ 158333
8
+ ],
9
+ "max_new_tokens": 1024,
10
+ "pad_token_id": 158326,
11
+ "top_k": 0,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.38.1"
14
+ }
generation_utils.py CHANGED
@@ -1,3 +1,4 @@
 
1
  import torch
2
  import numpy as np
3
  from queue import Queue
@@ -76,14 +77,75 @@ def make_context(model, tokenizer,
76
  return torch.LongTensor([input_tokens]).to(model.device)
77
 
78
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
  class TextIterStreamer:
80
- def __init__(self, tokenizer, skip_prompt=False, skip_special_tokens=False):
81
  self.tokenizer = tokenizer
82
  self.skip_prompt = skip_prompt
83
  self.skip_special_tokens = skip_special_tokens
84
  self.tokens = []
85
  self.text_queue = Queue()
86
  self.next_tokens_are_prompt = True
 
87
 
88
  def put(self, value):
89
  if self.skip_prompt and self.next_tokens_are_prompt:
@@ -92,8 +154,10 @@ class TextIterStreamer:
92
  if len(value.shape) > 1:
93
  value = value[0]
94
  self.tokens.extend(value.tolist())
95
- self.text_queue.put(
96
- self.tokenizer.decode(self.tokens, skip_special_tokens=self.skip_special_tokens, errors='ignore'))
 
 
97
 
98
  def end(self):
99
  self.text_queue.put(None)
 
1
+ import re
2
  import torch
3
  import numpy as np
4
  from queue import Queue
 
77
  return torch.LongTensor([input_tokens]).to(model.device)
78
 
79
 
80
+ def parse_pot_no_stream(inputs):
81
+ try:
82
+ s = re.findall(r'<<(.*?)>>', inputs, re.DOTALL)
83
+ if not s:
84
+ #print("err inputs: ", origin_inputs, flush=True)
85
+ return inputs
86
+
87
+ index = 0
88
+ for k in s:
89
+ try:
90
+ if "func" in k:
91
+ var = k.split("=", 1)
92
+ try:
93
+ var[1] = var[1].strip(" ")
94
+ exec(var[1], globals())
95
+ ans = func()
96
+ except:
97
+ if 'sympy' in var[1]:
98
+ var[1] = var[1].replace('res[x]', 'res[0][0]').replace('res[y]', 'res[0][1]')
99
+ exec(var[1], globals())
100
+ ans = func()
101
+ pass
102
+ var_list = [c.strip(" ") for c in var[0].split(",")]
103
+ if len(var_list) == 1:
104
+ ans = [ans]
105
+
106
+ for i in range(len(ans)):
107
+ try:
108
+ ans[i] = float(ans[i])
109
+ if abs(ans[i] - int(ans[i])) < 1e-10:
110
+ ans[i] = str(int(ans[i]))
111
+ except:
112
+ pass
113
+
114
+ inputs = inputs.replace("<<"+k+">>", "")
115
+ for i in range(len(var_list)):
116
+ inputs = inputs.replace(var_list[i], str(ans[i]))
117
+ index += 1
118
+ for c in range(index, len(s)):
119
+ for i in range(len(var_list)):
120
+ s[c] = s[c].replace(var_list[i], str(ans[i]))
121
+ else:
122
+ var = k.replace(" ", "").split("=")
123
+ var[1] = var[1].replace("eval", "")
124
+ ans = round(eval(var[1]), 10)
125
+ ans = float(ans)
126
+ if abs(ans - int(ans)) < 1e-10:
127
+ ans = str(int(ans))
128
+ inputs = inputs.replace("<<"+k+">>", "").replace(var[0], str(ans))
129
+ index += 1
130
+ for c in range(index, len(s)):
131
+ s[c] = s[c].replace(var[0], str(ans))
132
+ except:
133
+ return inputs
134
+ except Exception as e:
135
+ return inputs
136
+
137
+ return inputs
138
+
139
+
140
  class TextIterStreamer:
141
+ def __init__(self, tokenizer, skip_prompt=False, skip_special_tokens=False, use_pot=True):
142
  self.tokenizer = tokenizer
143
  self.skip_prompt = skip_prompt
144
  self.skip_special_tokens = skip_special_tokens
145
  self.tokens = []
146
  self.text_queue = Queue()
147
  self.next_tokens_are_prompt = True
148
+ self.use_pot = use_pot
149
 
150
  def put(self, value):
151
  if self.skip_prompt and self.next_tokens_are_prompt:
 
154
  if len(value.shape) > 1:
155
  value = value[0]
156
  self.tokens.extend(value.tolist())
157
+ tokens_str = self.tokenizer.decode(self.tokens, skip_special_tokens=self.skip_special_tokens, errors='ignore')
158
+ if self.use_pot:
159
+ tokens_str = parse_pot_no_stream(tokens_str)
160
+ self.text_queue.put(tokens_str)
161
 
162
  def end(self):
163
  self.text_queue.put(None)
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7079127c6289afd8b7a833aa4bcd176bfeb5a8b13f32e59855210f4678e8e65c
3
+ size 1988671752
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22fbddd73e83020a997071abbdd360ea1581682fdd3646b41e74db24deb0b995
3
+ size 1978251896
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451893ddd5179856a2e04a7ef5da1bfebdc7bb0b8e67e33e9349a94319e4dc95
3
+ size 702555592
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8196e15dfae1e3f34813ba2269fbbb348c802d998524d412481a37927b9c8e
3
+ size 1298137216
model.safetensors.index.json ADDED
@@ -0,0 +1,874 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5967519744
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
21
+ "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
22
+ "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
23
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
24
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
27
+ "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
28
+ "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
29
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
30
+ "model.layers.0.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.0.self_attn.qkv_proj.g_idx": "model-00001-of-00004.safetensors",
32
+ "model.layers.0.self_attn.qkv_proj.qweight": "model-00001-of-00004.safetensors",
33
+ "model.layers.0.self_attn.qkv_proj.qzeros": "model-00001-of-00004.safetensors",
34
+ "model.layers.0.self_attn.qkv_proj.scales": "model-00001-of-00004.safetensors",
35
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
36
+ "model.layers.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
37
+ "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
38
+ "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
39
+ "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
40
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
41
+ "model.layers.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
42
+ "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
43
+ "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
44
+ "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
45
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
46
+ "model.layers.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
47
+ "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
48
+ "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
49
+ "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
50
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
51
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
52
+ "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00004.safetensors",
53
+ "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
54
+ "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
55
+ "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
56
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
57
+ "model.layers.1.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
58
+ "model.layers.1.self_attn.qkv_proj.g_idx": "model-00001-of-00004.safetensors",
59
+ "model.layers.1.self_attn.qkv_proj.qweight": "model-00001-of-00004.safetensors",
60
+ "model.layers.1.self_attn.qkv_proj.qzeros": "model-00001-of-00004.safetensors",
61
+ "model.layers.1.self_attn.qkv_proj.scales": "model-00001-of-00004.safetensors",
62
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.10.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
64
+ "model.layers.10.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
65
+ "model.layers.10.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
66
+ "model.layers.10.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
67
+ "model.layers.10.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
68
+ "model.layers.10.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
69
+ "model.layers.10.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
70
+ "model.layers.10.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
71
+ "model.layers.10.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
72
+ "model.layers.10.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
73
+ "model.layers.10.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.10.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
75
+ "model.layers.10.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
76
+ "model.layers.10.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
77
+ "model.layers.10.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
78
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.10.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.10.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
81
+ "model.layers.10.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
82
+ "model.layers.10.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
83
+ "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
84
+ "model.layers.10.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
85
+ "model.layers.10.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
86
+ "model.layers.10.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
87
+ "model.layers.10.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
88
+ "model.layers.10.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
89
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.11.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.11.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
92
+ "model.layers.11.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
93
+ "model.layers.11.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
94
+ "model.layers.11.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
95
+ "model.layers.11.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
96
+ "model.layers.11.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
97
+ "model.layers.11.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
98
+ "model.layers.11.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
99
+ "model.layers.11.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
100
+ "model.layers.11.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.11.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
102
+ "model.layers.11.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
103
+ "model.layers.11.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
104
+ "model.layers.11.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
105
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.11.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
107
+ "model.layers.11.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
108
+ "model.layers.11.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
109
+ "model.layers.11.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
110
+ "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
111
+ "model.layers.11.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
112
+ "model.layers.11.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
113
+ "model.layers.11.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
114
+ "model.layers.11.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
115
+ "model.layers.11.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
116
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.12.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
118
+ "model.layers.12.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
119
+ "model.layers.12.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
120
+ "model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
121
+ "model.layers.12.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
122
+ "model.layers.12.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
123
+ "model.layers.12.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
124
+ "model.layers.12.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
125
+ "model.layers.12.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
126
+ "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
127
+ "model.layers.12.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
128
+ "model.layers.12.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
129
+ "model.layers.12.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
130
+ "model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
131
+ "model.layers.12.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
132
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.12.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.12.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
135
+ "model.layers.12.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
136
+ "model.layers.12.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
137
+ "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
138
+ "model.layers.12.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.12.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
140
+ "model.layers.12.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
141
+ "model.layers.12.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
142
+ "model.layers.12.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
143
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
144
+ "model.layers.13.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
145
+ "model.layers.13.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
146
+ "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
147
+ "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
148
+ "model.layers.13.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
149
+ "model.layers.13.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
150
+ "model.layers.13.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
151
+ "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
152
+ "model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
153
+ "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
154
+ "model.layers.13.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
155
+ "model.layers.13.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
156
+ "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
157
+ "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
158
+ "model.layers.13.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
159
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.13.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
161
+ "model.layers.13.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
162
+ "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
163
+ "model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
164
+ "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
165
+ "model.layers.13.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
166
+ "model.layers.13.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
167
+ "model.layers.13.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
168
+ "model.layers.13.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
169
+ "model.layers.13.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
170
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
171
+ "model.layers.14.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
172
+ "model.layers.14.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
173
+ "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
174
+ "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
175
+ "model.layers.14.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
176
+ "model.layers.14.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
177
+ "model.layers.14.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
178
+ "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
179
+ "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
180
+ "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
181
+ "model.layers.14.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
182
+ "model.layers.14.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
183
+ "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
184
+ "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
185
+ "model.layers.14.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
186
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
187
+ "model.layers.14.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
188
+ "model.layers.14.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
189
+ "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
190
+ "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
191
+ "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
192
+ "model.layers.14.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
193
+ "model.layers.14.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
194
+ "model.layers.14.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
195
+ "model.layers.14.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
196
+ "model.layers.14.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
197
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
198
+ "model.layers.15.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
199
+ "model.layers.15.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
200
+ "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
201
+ "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
202
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
203
+ "model.layers.15.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
204
+ "model.layers.15.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
205
+ "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
206
+ "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
207
+ "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
208
+ "model.layers.15.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
209
+ "model.layers.15.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
210
+ "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
211
+ "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
212
+ "model.layers.15.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
213
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
214
+ "model.layers.15.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
215
+ "model.layers.15.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
216
+ "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
217
+ "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
218
+ "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
219
+ "model.layers.15.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
220
+ "model.layers.15.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
221
+ "model.layers.15.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
222
+ "model.layers.15.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
223
+ "model.layers.15.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
224
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
225
+ "model.layers.16.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
226
+ "model.layers.16.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
227
+ "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
228
+ "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
229
+ "model.layers.16.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
230
+ "model.layers.16.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
231
+ "model.layers.16.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
232
+ "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
233
+ "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
234
+ "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
235
+ "model.layers.16.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
236
+ "model.layers.16.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
237
+ "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
238
+ "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
239
+ "model.layers.16.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
240
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
241
+ "model.layers.16.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
242
+ "model.layers.16.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
243
+ "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
244
+ "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
245
+ "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
246
+ "model.layers.16.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
247
+ "model.layers.16.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
248
+ "model.layers.16.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
249
+ "model.layers.16.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
250
+ "model.layers.16.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
251
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.17.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
253
+ "model.layers.17.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
254
+ "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
255
+ "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
256
+ "model.layers.17.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
257
+ "model.layers.17.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
258
+ "model.layers.17.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
259
+ "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
260
+ "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
261
+ "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
262
+ "model.layers.17.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
263
+ "model.layers.17.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
264
+ "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
265
+ "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
266
+ "model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
267
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
268
+ "model.layers.17.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
269
+ "model.layers.17.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
270
+ "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
271
+ "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
272
+ "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
273
+ "model.layers.17.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
274
+ "model.layers.17.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
275
+ "model.layers.17.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
276
+ "model.layers.17.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
277
+ "model.layers.17.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
278
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
279
+ "model.layers.18.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
280
+ "model.layers.18.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
281
+ "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
282
+ "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
283
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
284
+ "model.layers.18.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
285
+ "model.layers.18.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
286
+ "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
287
+ "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
288
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
289
+ "model.layers.18.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
290
+ "model.layers.18.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
291
+ "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
292
+ "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
293
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
294
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.18.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
296
+ "model.layers.18.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
297
+ "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
298
+ "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
299
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
300
+ "model.layers.18.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
301
+ "model.layers.18.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
302
+ "model.layers.18.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
303
+ "model.layers.18.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
304
+ "model.layers.18.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
305
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
306
+ "model.layers.19.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.layers.19.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
308
+ "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
309
+ "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
310
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
311
+ "model.layers.19.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
312
+ "model.layers.19.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
313
+ "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
314
+ "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
315
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
316
+ "model.layers.19.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
317
+ "model.layers.19.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
318
+ "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
319
+ "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
320
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
321
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.19.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
323
+ "model.layers.19.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
324
+ "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
325
+ "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
326
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
327
+ "model.layers.19.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
328
+ "model.layers.19.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
329
+ "model.layers.19.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
330
+ "model.layers.19.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
331
+ "model.layers.19.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
332
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
333
+ "model.layers.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
334
+ "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
335
+ "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
336
+ "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
337
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
338
+ "model.layers.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
339
+ "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
340
+ "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
341
+ "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
342
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
343
+ "model.layers.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
344
+ "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
345
+ "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
346
+ "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
347
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
348
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
349
+ "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00004.safetensors",
350
+ "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
351
+ "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
352
+ "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
353
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
354
+ "model.layers.2.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
355
+ "model.layers.2.self_attn.qkv_proj.g_idx": "model-00001-of-00004.safetensors",
356
+ "model.layers.2.self_attn.qkv_proj.qweight": "model-00001-of-00004.safetensors",
357
+ "model.layers.2.self_attn.qkv_proj.qzeros": "model-00001-of-00004.safetensors",
358
+ "model.layers.2.self_attn.qkv_proj.scales": "model-00001-of-00004.safetensors",
359
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
360
+ "model.layers.20.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
361
+ "model.layers.20.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
362
+ "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
363
+ "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
364
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
365
+ "model.layers.20.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
366
+ "model.layers.20.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
367
+ "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
368
+ "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
369
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
370
+ "model.layers.20.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
371
+ "model.layers.20.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
372
+ "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
373
+ "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
374
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
375
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
376
+ "model.layers.20.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
377
+ "model.layers.20.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
378
+ "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
379
+ "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
380
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
381
+ "model.layers.20.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
382
+ "model.layers.20.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
383
+ "model.layers.20.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
384
+ "model.layers.20.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
385
+ "model.layers.20.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
386
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
387
+ "model.layers.21.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
388
+ "model.layers.21.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
389
+ "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
390
+ "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
391
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
392
+ "model.layers.21.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
393
+ "model.layers.21.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
394
+ "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
395
+ "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
396
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
397
+ "model.layers.21.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
398
+ "model.layers.21.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
399
+ "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
400
+ "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
401
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
402
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
403
+ "model.layers.21.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
404
+ "model.layers.21.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
405
+ "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
406
+ "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
407
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
408
+ "model.layers.21.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
409
+ "model.layers.21.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
410
+ "model.layers.21.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
411
+ "model.layers.21.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
412
+ "model.layers.21.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
413
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
414
+ "model.layers.22.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
415
+ "model.layers.22.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
416
+ "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
417
+ "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
418
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
419
+ "model.layers.22.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
420
+ "model.layers.22.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
421
+ "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
422
+ "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
423
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
424
+ "model.layers.22.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
425
+ "model.layers.22.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
426
+ "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
427
+ "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
428
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
429
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
430
+ "model.layers.22.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
431
+ "model.layers.22.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
432
+ "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
433
+ "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
434
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
435
+ "model.layers.22.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
436
+ "model.layers.22.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
437
+ "model.layers.22.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
438
+ "model.layers.22.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
439
+ "model.layers.22.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
440
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
441
+ "model.layers.23.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
442
+ "model.layers.23.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
443
+ "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
444
+ "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
445
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
446
+ "model.layers.23.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
447
+ "model.layers.23.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
448
+ "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
449
+ "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
450
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
451
+ "model.layers.23.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
452
+ "model.layers.23.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
453
+ "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
454
+ "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
455
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
456
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
457
+ "model.layers.23.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
458
+ "model.layers.23.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
459
+ "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
460
+ "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
461
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
462
+ "model.layers.23.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
463
+ "model.layers.23.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
464
+ "model.layers.23.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
465
+ "model.layers.23.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
466
+ "model.layers.23.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
467
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
468
+ "model.layers.24.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
469
+ "model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
470
+ "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
471
+ "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
472
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
473
+ "model.layers.24.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
474
+ "model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
475
+ "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
476
+ "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
477
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
478
+ "model.layers.24.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
479
+ "model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
480
+ "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
481
+ "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
482
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
483
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
484
+ "model.layers.24.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
485
+ "model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
486
+ "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
487
+ "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
488
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
489
+ "model.layers.24.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
490
+ "model.layers.24.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
491
+ "model.layers.24.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
492
+ "model.layers.24.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
493
+ "model.layers.24.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
494
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
495
+ "model.layers.25.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
496
+ "model.layers.25.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
497
+ "model.layers.25.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
498
+ "model.layers.25.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
499
+ "model.layers.25.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
500
+ "model.layers.25.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
501
+ "model.layers.25.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
502
+ "model.layers.25.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
503
+ "model.layers.25.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
504
+ "model.layers.25.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
505
+ "model.layers.25.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
506
+ "model.layers.25.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
507
+ "model.layers.25.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
508
+ "model.layers.25.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
509
+ "model.layers.25.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
510
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
511
+ "model.layers.25.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
512
+ "model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
513
+ "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
514
+ "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
515
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
516
+ "model.layers.25.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
517
+ "model.layers.25.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
518
+ "model.layers.25.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
519
+ "model.layers.25.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
520
+ "model.layers.25.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
521
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
522
+ "model.layers.26.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
523
+ "model.layers.26.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
524
+ "model.layers.26.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
525
+ "model.layers.26.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
526
+ "model.layers.26.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
527
+ "model.layers.26.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
528
+ "model.layers.26.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
529
+ "model.layers.26.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
530
+ "model.layers.26.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
531
+ "model.layers.26.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
532
+ "model.layers.26.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
533
+ "model.layers.26.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
534
+ "model.layers.26.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
535
+ "model.layers.26.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
536
+ "model.layers.26.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
537
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
538
+ "model.layers.26.self_attn.o_proj.bias": "model-00003-of-00004.safetensors",
539
+ "model.layers.26.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
540
+ "model.layers.26.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
541
+ "model.layers.26.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
542
+ "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
543
+ "model.layers.26.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
544
+ "model.layers.26.self_attn.qkv_proj.g_idx": "model-00003-of-00004.safetensors",
545
+ "model.layers.26.self_attn.qkv_proj.qweight": "model-00003-of-00004.safetensors",
546
+ "model.layers.26.self_attn.qkv_proj.qzeros": "model-00003-of-00004.safetensors",
547
+ "model.layers.26.self_attn.qkv_proj.scales": "model-00003-of-00004.safetensors",
548
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
549
+ "model.layers.27.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
550
+ "model.layers.27.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
551
+ "model.layers.27.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
552
+ "model.layers.27.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
553
+ "model.layers.27.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
554
+ "model.layers.27.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
555
+ "model.layers.27.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
556
+ "model.layers.27.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
557
+ "model.layers.27.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
558
+ "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
559
+ "model.layers.27.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
560
+ "model.layers.27.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
561
+ "model.layers.27.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
562
+ "model.layers.27.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
563
+ "model.layers.27.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
564
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
565
+ "model.layers.27.self_attn.o_proj.bias": "model-00003-of-00004.safetensors",
566
+ "model.layers.27.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
567
+ "model.layers.27.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
568
+ "model.layers.27.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
569
+ "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
570
+ "model.layers.27.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
571
+ "model.layers.27.self_attn.qkv_proj.g_idx": "model-00003-of-00004.safetensors",
572
+ "model.layers.27.self_attn.qkv_proj.qweight": "model-00003-of-00004.safetensors",
573
+ "model.layers.27.self_attn.qkv_proj.qzeros": "model-00003-of-00004.safetensors",
574
+ "model.layers.27.self_attn.qkv_proj.scales": "model-00003-of-00004.safetensors",
575
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
576
+ "model.layers.28.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
577
+ "model.layers.28.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
578
+ "model.layers.28.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
579
+ "model.layers.28.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
580
+ "model.layers.28.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
581
+ "model.layers.28.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
582
+ "model.layers.28.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
583
+ "model.layers.28.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
584
+ "model.layers.28.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
585
+ "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
586
+ "model.layers.28.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
587
+ "model.layers.28.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
588
+ "model.layers.28.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
589
+ "model.layers.28.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
590
+ "model.layers.28.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
591
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
592
+ "model.layers.28.self_attn.o_proj.bias": "model-00003-of-00004.safetensors",
593
+ "model.layers.28.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
594
+ "model.layers.28.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
595
+ "model.layers.28.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
596
+ "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
597
+ "model.layers.28.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
598
+ "model.layers.28.self_attn.qkv_proj.g_idx": "model-00003-of-00004.safetensors",
599
+ "model.layers.28.self_attn.qkv_proj.qweight": "model-00003-of-00004.safetensors",
600
+ "model.layers.28.self_attn.qkv_proj.qzeros": "model-00003-of-00004.safetensors",
601
+ "model.layers.28.self_attn.qkv_proj.scales": "model-00003-of-00004.safetensors",
602
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
603
+ "model.layers.29.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
604
+ "model.layers.29.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
605
+ "model.layers.29.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
606
+ "model.layers.29.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
607
+ "model.layers.29.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
608
+ "model.layers.29.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
609
+ "model.layers.29.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
610
+ "model.layers.29.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
611
+ "model.layers.29.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
612
+ "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
613
+ "model.layers.29.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
614
+ "model.layers.29.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
615
+ "model.layers.29.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
616
+ "model.layers.29.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
617
+ "model.layers.29.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
618
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
619
+ "model.layers.29.self_attn.o_proj.bias": "model-00003-of-00004.safetensors",
620
+ "model.layers.29.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
621
+ "model.layers.29.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
622
+ "model.layers.29.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
623
+ "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
624
+ "model.layers.29.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
625
+ "model.layers.29.self_attn.qkv_proj.g_idx": "model-00003-of-00004.safetensors",
626
+ "model.layers.29.self_attn.qkv_proj.qweight": "model-00003-of-00004.safetensors",
627
+ "model.layers.29.self_attn.qkv_proj.qzeros": "model-00003-of-00004.safetensors",
628
+ "model.layers.29.self_attn.qkv_proj.scales": "model-00003-of-00004.safetensors",
629
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
630
+ "model.layers.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
631
+ "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
632
+ "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
633
+ "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
634
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
635
+ "model.layers.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
636
+ "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
637
+ "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
638
+ "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
639
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
640
+ "model.layers.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
641
+ "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
642
+ "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
643
+ "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
644
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
645
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
646
+ "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00004.safetensors",
647
+ "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
648
+ "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
649
+ "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
650
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
651
+ "model.layers.3.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
652
+ "model.layers.3.self_attn.qkv_proj.g_idx": "model-00001-of-00004.safetensors",
653
+ "model.layers.3.self_attn.qkv_proj.qweight": "model-00001-of-00004.safetensors",
654
+ "model.layers.3.self_attn.qkv_proj.qzeros": "model-00001-of-00004.safetensors",
655
+ "model.layers.3.self_attn.qkv_proj.scales": "model-00001-of-00004.safetensors",
656
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
657
+ "model.layers.30.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
658
+ "model.layers.30.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
659
+ "model.layers.30.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
660
+ "model.layers.30.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
661
+ "model.layers.30.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
662
+ "model.layers.30.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
663
+ "model.layers.30.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
664
+ "model.layers.30.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
665
+ "model.layers.30.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
666
+ "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
667
+ "model.layers.30.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
668
+ "model.layers.30.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
669
+ "model.layers.30.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
670
+ "model.layers.30.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
671
+ "model.layers.30.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
672
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
673
+ "model.layers.30.self_attn.o_proj.bias": "model-00003-of-00004.safetensors",
674
+ "model.layers.30.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
675
+ "model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
676
+ "model.layers.30.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
677
+ "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
678
+ "model.layers.30.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
679
+ "model.layers.30.self_attn.qkv_proj.g_idx": "model-00003-of-00004.safetensors",
680
+ "model.layers.30.self_attn.qkv_proj.qweight": "model-00003-of-00004.safetensors",
681
+ "model.layers.30.self_attn.qkv_proj.qzeros": "model-00003-of-00004.safetensors",
682
+ "model.layers.30.self_attn.qkv_proj.scales": "model-00003-of-00004.safetensors",
683
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
684
+ "model.layers.31.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
685
+ "model.layers.31.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors",
686
+ "model.layers.31.mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
687
+ "model.layers.31.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors",
688
+ "model.layers.31.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
689
+ "model.layers.31.mlp.gate_proj.bias": "model-00003-of-00004.safetensors",
690
+ "model.layers.31.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors",
691
+ "model.layers.31.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
692
+ "model.layers.31.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors",
693
+ "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
694
+ "model.layers.31.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
695
+ "model.layers.31.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors",
696
+ "model.layers.31.mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
697
+ "model.layers.31.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors",
698
+ "model.layers.31.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
699
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
700
+ "model.layers.31.self_attn.o_proj.bias": "model-00003-of-00004.safetensors",
701
+ "model.layers.31.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors",
702
+ "model.layers.31.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
703
+ "model.layers.31.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors",
704
+ "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
705
+ "model.layers.31.self_attn.qkv_proj.bias": "model-00003-of-00004.safetensors",
706
+ "model.layers.31.self_attn.qkv_proj.g_idx": "model-00003-of-00004.safetensors",
707
+ "model.layers.31.self_attn.qkv_proj.qweight": "model-00003-of-00004.safetensors",
708
+ "model.layers.31.self_attn.qkv_proj.qzeros": "model-00003-of-00004.safetensors",
709
+ "model.layers.31.self_attn.qkv_proj.scales": "model-00003-of-00004.safetensors",
710
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
711
+ "model.layers.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
712
+ "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
713
+ "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
714
+ "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
715
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
716
+ "model.layers.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
717
+ "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
718
+ "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
719
+ "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
720
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
721
+ "model.layers.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
722
+ "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
723
+ "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
724
+ "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
725
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
726
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
727
+ "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00004.safetensors",
728
+ "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
729
+ "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
730
+ "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
731
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
732
+ "model.layers.4.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
733
+ "model.layers.4.self_attn.qkv_proj.g_idx": "model-00001-of-00004.safetensors",
734
+ "model.layers.4.self_attn.qkv_proj.qweight": "model-00001-of-00004.safetensors",
735
+ "model.layers.4.self_attn.qkv_proj.qzeros": "model-00001-of-00004.safetensors",
736
+ "model.layers.4.self_attn.qkv_proj.scales": "model-00001-of-00004.safetensors",
737
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
738
+ "model.layers.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
739
+ "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
740
+ "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
741
+ "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
742
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
743
+ "model.layers.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
744
+ "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors",
745
+ "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
746
+ "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors",
747
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
748
+ "model.layers.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
749
+ "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors",
750
+ "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
751
+ "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors",
752
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
753
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
754
+ "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00004.safetensors",
755
+ "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
756
+ "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
757
+ "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
758
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
759
+ "model.layers.5.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
760
+ "model.layers.5.self_attn.qkv_proj.g_idx": "model-00001-of-00004.safetensors",
761
+ "model.layers.5.self_attn.qkv_proj.qweight": "model-00001-of-00004.safetensors",
762
+ "model.layers.5.self_attn.qkv_proj.qzeros": "model-00001-of-00004.safetensors",
763
+ "model.layers.5.self_attn.qkv_proj.scales": "model-00001-of-00004.safetensors",
764
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
765
+ "model.layers.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
766
+ "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors",
767
+ "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
768
+ "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors",
769
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
770
+ "model.layers.6.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
771
+ "model.layers.6.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
772
+ "model.layers.6.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
773
+ "model.layers.6.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
774
+ "model.layers.6.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
775
+ "model.layers.6.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
776
+ "model.layers.6.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
777
+ "model.layers.6.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
778
+ "model.layers.6.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
779
+ "model.layers.6.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
780
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
781
+ "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00004.safetensors",
782
+ "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors",
783
+ "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
784
+ "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors",
785
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
786
+ "model.layers.6.self_attn.qkv_proj.bias": "model-00001-of-00004.safetensors",
787
+ "model.layers.6.self_attn.qkv_proj.g_idx": "model-00001-of-00004.safetensors",
788
+ "model.layers.6.self_attn.qkv_proj.qweight": "model-00001-of-00004.safetensors",
789
+ "model.layers.6.self_attn.qkv_proj.qzeros": "model-00001-of-00004.safetensors",
790
+ "model.layers.6.self_attn.qkv_proj.scales": "model-00001-of-00004.safetensors",
791
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
792
+ "model.layers.7.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
793
+ "model.layers.7.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
794
+ "model.layers.7.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
795
+ "model.layers.7.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
796
+ "model.layers.7.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
797
+ "model.layers.7.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
798
+ "model.layers.7.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
799
+ "model.layers.7.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
800
+ "model.layers.7.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
801
+ "model.layers.7.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
802
+ "model.layers.7.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
803
+ "model.layers.7.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
804
+ "model.layers.7.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
805
+ "model.layers.7.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
806
+ "model.layers.7.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
807
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
808
+ "model.layers.7.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
809
+ "model.layers.7.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
810
+ "model.layers.7.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
811
+ "model.layers.7.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
812
+ "model.layers.7.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
813
+ "model.layers.7.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
814
+ "model.layers.7.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
815
+ "model.layers.7.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
816
+ "model.layers.7.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
817
+ "model.layers.7.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
818
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
819
+ "model.layers.8.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
820
+ "model.layers.8.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
821
+ "model.layers.8.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
822
+ "model.layers.8.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
823
+ "model.layers.8.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
824
+ "model.layers.8.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
825
+ "model.layers.8.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
826
+ "model.layers.8.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
827
+ "model.layers.8.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
828
+ "model.layers.8.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
829
+ "model.layers.8.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
830
+ "model.layers.8.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
831
+ "model.layers.8.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
832
+ "model.layers.8.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
833
+ "model.layers.8.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
834
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
835
+ "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
836
+ "model.layers.8.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
837
+ "model.layers.8.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
838
+ "model.layers.8.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
839
+ "model.layers.8.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
840
+ "model.layers.8.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
841
+ "model.layers.8.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
842
+ "model.layers.8.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
843
+ "model.layers.8.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
844
+ "model.layers.8.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
845
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
846
+ "model.layers.9.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
847
+ "model.layers.9.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors",
848
+ "model.layers.9.mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
849
+ "model.layers.9.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors",
850
+ "model.layers.9.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
851
+ "model.layers.9.mlp.gate_proj.bias": "model-00002-of-00004.safetensors",
852
+ "model.layers.9.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors",
853
+ "model.layers.9.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
854
+ "model.layers.9.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors",
855
+ "model.layers.9.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
856
+ "model.layers.9.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
857
+ "model.layers.9.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors",
858
+ "model.layers.9.mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
859
+ "model.layers.9.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors",
860
+ "model.layers.9.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
861
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
862
+ "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00004.safetensors",
863
+ "model.layers.9.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors",
864
+ "model.layers.9.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
865
+ "model.layers.9.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors",
866
+ "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
867
+ "model.layers.9.self_attn.qkv_proj.bias": "model-00002-of-00004.safetensors",
868
+ "model.layers.9.self_attn.qkv_proj.g_idx": "model-00002-of-00004.safetensors",
869
+ "model.layers.9.self_attn.qkv_proj.qweight": "model-00002-of-00004.safetensors",
870
+ "model.layers.9.self_attn.qkv_proj.qzeros": "model-00002-of-00004.safetensors",
871
+ "model.layers.9.self_attn.qkv_proj.scales": "model-00002-of-00004.safetensors",
872
+ "model.norm.weight": "model-00003-of-00004.safetensors"
873
+ }
874
+ }
modeling_zhinao.py CHANGED
@@ -19,7 +19,7 @@ from transformers.utils import logging
19
  from transformers.generation.utils import GenerationConfig
20
  from transformers.generation.logits_process import LogitsProcessorList
21
  from .configuration_zhinao import ZhinaoConfig
22
- from .generation_utils import TextIterStreamer, make_context, OutputRepetitionPenaltyLogitsProcessor
23
 
24
 
25
  try:
@@ -932,6 +932,7 @@ class ZhinaoForCausalLM(ZhinaoPreTrainedModel):
932
  messages: List[dict],
933
  system: str = "You are a helpful assistant.",
934
  stream=False,
 
935
  generation_config: Optional[GenerationConfig]=None):
936
 
937
  generation_config = generation_config or self.generation_config
@@ -941,7 +942,7 @@ class ZhinaoForCausalLM(ZhinaoPreTrainedModel):
941
  )
942
 
943
  if stream:
944
- streamer = TextIterStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
945
  Thread(target=self.generate, kwargs=dict(
946
  inputs=input_ids, streamer=streamer,
947
  generation_config=generation_config,
@@ -950,8 +951,9 @@ class ZhinaoForCausalLM(ZhinaoPreTrainedModel):
950
  else:
951
  outputs = self.generate(input_ids, generation_config=generation_config)
952
  response = tokenizer.decode(outputs[0][len(input_ids[0]):], skip_special_tokens=True)
953
-
954
- return response
 
955
 
956
 
957
  class ZhinaoForSequenceClassification(ZhinaoPreTrainedModel):
 
19
  from transformers.generation.utils import GenerationConfig
20
  from transformers.generation.logits_process import LogitsProcessorList
21
  from .configuration_zhinao import ZhinaoConfig
22
+ from .generation_utils import TextIterStreamer, make_context, OutputRepetitionPenaltyLogitsProcessor, parse_pot_no_stream
23
 
24
 
25
  try:
 
932
  messages: List[dict],
933
  system: str = "You are a helpful assistant.",
934
  stream=False,
935
+ use_pot=True,
936
  generation_config: Optional[GenerationConfig]=None):
937
 
938
  generation_config = generation_config or self.generation_config
 
942
  )
943
 
944
  if stream:
945
+ streamer = TextIterStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True, use_pot=use_pot)
946
  Thread(target=self.generate, kwargs=dict(
947
  inputs=input_ids, streamer=streamer,
948
  generation_config=generation_config,
 
951
  else:
952
  outputs = self.generate(input_ids, generation_config=generation_config)
953
  response = tokenizer.decode(outputs[0][len(input_ids[0]):], skip_special_tokens=True)
954
+ if use_pot:
955
+ response = parse_pot_no_stream(response)
956
+ return response
957
 
958
 
959
  class ZhinaoForSequenceClassification(ZhinaoPreTrainedModel):
quantize_config.json CHANGED
@@ -1,13 +1,23 @@
1
  {
 
2
  "bits": 4,
3
- "group_size": 128,
4
- "damp_percent": 0.01,
 
5
  "desc_act": false,
6
- "static_groups": false,
 
 
 
 
 
 
 
 
 
7
  "sym": true,
 
8
  "true_sequential": true,
9
- "model_name_or_path": "360Zhinao-7B-Chat-4K-Int4",
10
- "model_file_base_name": "gptq_model-4bit-128g",
11
- "quant_method": "gptq",
12
- "checkpoint_format": "gptq"
13
  }
 
1
  {
2
+ "batch_size": 1,
3
  "bits": 4,
4
+ "block_name_to_quantize": null,
5
+ "cache_block_outputs": true,
6
+ "damp_percent": 0.1,
7
  "desc_act": false,
8
+ "exllama_config": {
9
+ "version": 1
10
+ },
11
+ "group_size": 128,
12
+ "max_input_length": null,
13
+ "model_seqlen": null,
14
+ "module_name_preceding_first_block": null,
15
+ "modules_in_block_to_quantize": null,
16
+ "pad_token_id": null,
17
+ "quant_method": "gptq",
18
  "sym": true,
19
+ "tokenizer": null,
20
  "true_sequential": true,
21
+ "use_cuda_fp16": false,
22
+ "use_exllama": true
 
 
23
  }
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "pad_token": "<pad>"
3
+ }
tokenization_zhinao.py CHANGED
@@ -212,6 +212,10 @@ class ZhinaoTokenizer(PreTrainedTokenizer):
212
  @property
213
  def vocab_size(self):
214
  return self.tokenizer.num_tokens
 
 
 
 
215
 
216
  def get_vocab(self):
217
  """ Returns vocab as a dict """
 
212
  @property
213
  def vocab_size(self):
214
  return self.tokenizer.num_tokens
215
+
216
+ @property
217
+ def vocab(self):
218
+ return self.get_vocab()
219
 
220
  def get_vocab(self):
221
  """ Returns vocab as a dict """
tokenizer_config.json CHANGED
@@ -6,6 +6,16 @@
6
  null
7
  ]
8
  },
 
 
 
 
 
 
 
 
 
 
9
  "clean_up_tokenization_spaces": false,
10
  "do_lower_case": false,
11
  "eos_token": "<eod>",
@@ -15,4 +25,4 @@
15
  "remove_space": false,
16
  "tokenizer_class": "ZhinaoTokenizer",
17
  "unk_token": "<unk>"
18
- }
 
6
  null
7
  ]
8
  },
9
+ "stop_token_ids": [
10
+ 158326,
11
+ 158332,
12
+ 158333
13
+ ],
14
+ "stop": [
15
+ "<eod>",
16
+ "<|im_start|>",
17
+ "<|im_end|>"
18
+ ],
19
  "clean_up_tokenization_spaces": false,
20
  "do_lower_case": false,
21
  "eos_token": "<eod>",
 
25
  "remove_space": false,
26
  "tokenizer_class": "ZhinaoTokenizer",
27
  "unk_token": "<unk>"
28
+ }