shangeth commited on
Commit
053eb5b
1 Parent(s): 676b75c

Upload model

Browse files
config.json CHANGED
@@ -1,13 +1,18 @@
1
  {
 
 
 
2
  "audio_enc_dim": 1280,
3
  "audio_encoder_name": "facebook/hubert-xlarge-ll60k",
4
  "audio_processor_name": "facebook/hubert-large-ls960-ft",
5
  "auto_map": {
6
- "AutoConfig": "config.SpeechLLMModelConfig"
 
7
  },
8
  "llm_dim": 2048,
9
  "llm_model_checkpoint": "hf_repo/llm_model_checkpoint",
10
  "llm_model_name": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
11
  "model_type": "custom_model",
 
12
  "transformers_version": "4.38.2"
13
  }
 
1
  {
2
+ "architectures": [
3
+ "SpeechLLMModel"
4
+ ],
5
  "audio_enc_dim": 1280,
6
  "audio_encoder_name": "facebook/hubert-xlarge-ll60k",
7
  "audio_processor_name": "facebook/hubert-large-ls960-ft",
8
  "auto_map": {
9
+ "AutoConfig": "config.SpeechLLMModelConfig",
10
+ "AutoModel": "model.SpeechLLMModel"
11
  },
12
  "llm_dim": 2048,
13
  "llm_model_checkpoint": "hf_repo/llm_model_checkpoint",
14
  "llm_model_name": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
15
  "model_type": "custom_model",
16
+ "torch_dtype": "float32",
17
  "transformers_version": "4.38.2"
18
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:778179f27c443457a4ac527afe4c58d25902f410bdc492e7f4e09ffd23dfc6c7
3
- size 4975727392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18785830f9c696dfb288148f64e92b017789e290fbfdbffa4f8c03e903ed65b2
3
+ size 4973217960
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ad7d5e98460221a543bba83cb187111a948f22a34be26ab16fda691f2d83bc2
3
- size 3405770712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc74aa8e2666342b54594419847adfa6279238c9416dda34a09202d00dd638f
3
+ size 3395612080
model.py CHANGED
@@ -6,12 +6,9 @@ from .config import SpeechLLMModelConfig
6
  from peft import LoraConfig, get_peft_model
7
 
8
  class HubertXCNNEnoder(nn.Module):
9
- def __init__(self, audio_enc_dim, llm_dim):
10
  super().__init__()
11
- self.encoder = HubertModel.from_pretrained('facebook/hubert-xlarge-ll60k')
12
- for param in self.encoder.parameters():
13
- param.requires_grad = False
14
-
15
  self.cnn = nn.Sequential(
16
  nn.ReLU(),
17
  nn.Conv1d(audio_enc_dim, llm_dim // 2, kernel_size=5, stride=1, padding=0),
@@ -25,32 +22,40 @@ class HubertXCNNEnoder(nn.Module):
25
  x = self.encoder(x).last_hidden_state
26
  x = self.cnn(x.transpose(1, 2)).transpose(1, 2)
27
  return x
 
 
 
28
 
29
  class SpeechLLMModel(PreTrainedModel):
30
  config_class = SpeechLLMModelConfig
31
 
32
  def __init__(self, config):
33
  super().__init__(config)
34
- self.audio_processor = AutoProcessor.from_pretrained("facebook/hubert-large-ls960-ft")
35
- self.audio_encoder = HubertXCNNEnoder(config.audio_enc_dim, config.llm_dim)
36
- self.llm_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
37
- self.llm_tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
38
-
39
- peft_config = LoraConfig(
40
- r=4,
41
- lora_alpha=8,
42
- target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'up_proj', 'down_proj', 'gate_proj'],
43
- lora_dropout=0.05,
44
- task_type="CAUSAL_LM",
45
- )
46
- self.llm_model = get_peft_model(self.llm_model, peft_config)
 
 
 
 
 
47
 
48
  def encode(self, mel, pre_tokenized_ids, post_tokenized_ids, output_tokenized_ids):
49
  batch_size = mel.shape[0]
50
 
51
  with torch.no_grad():
52
  speech_embeds = self.audio_encoder(mel)
53
- embedder = self.llm_model.model.model.embed_tokens
54
  pre_prompt_embeds = embedder(pre_tokenized_ids)
55
  post_prompt_embeds = embedder(post_tokenized_ids)
56
  output_prompt_embeds = embedder(output_tokenized_ids)
@@ -71,6 +76,7 @@ class SpeechLLMModel(PreTrainedModel):
71
  return outputs
72
 
73
  def generate_meta(self, audio_path, instruction="Give me the following information about the audio [Transcript]", max_new_tokens=2000):
 
74
  pre_speech_prompt = f'''Instruction:
75
  {instruction}
76
 
@@ -89,13 +95,13 @@ Output:'''
89
  post_tokenized_ids = self.llm_tokenizer(post_speech_prompt, padding="do_not_pad", return_tensors='pt', truncation=False, add_special_tokens=False)["input_ids"]
90
  output_tokenized_ids = self.llm_tokenizer(output_prompt, padding="do_not_pad", return_tensors='pt', truncation=False, add_special_tokens=False)["input_ids"]
91
 
92
- combined_embeds, atts, label_ids = self.encode(wav_tensor, pre_tokenized_ids, post_tokenized_ids, output_tokenized_ids)
93
 
94
  out = self.llm_model.generate(
95
  inputs_embeds=combined_embeds,
96
  max_new_tokens=max_new_tokens,
97
  ).cpu().tolist()[0]
98
 
99
- output_text = self.llm_tokenizer.decode(out, skip_special_tokens=False)
100
  return output_text
101
 
 
6
  from peft import LoraConfig, get_peft_model
7
 
8
  class HubertXCNNEnoder(nn.Module):
9
+ def __init__(self, audio_enc_dim, llm_dim, encoder_name):
10
  super().__init__()
11
+ self.encoder = HubertModel.from_pretrained(encoder_name)
 
 
 
12
  self.cnn = nn.Sequential(
13
  nn.ReLU(),
14
  nn.Conv1d(audio_enc_dim, llm_dim // 2, kernel_size=5, stride=1, padding=0),
 
22
  x = self.encoder(x).last_hidden_state
23
  x = self.cnn(x.transpose(1, 2)).transpose(1, 2)
24
  return x
25
+
26
+ def return_device(self):
27
+ return next(self.parameters()).device
28
 
29
  class SpeechLLMModel(PreTrainedModel):
30
  config_class = SpeechLLMModelConfig
31
 
32
  def __init__(self, config):
33
  super().__init__(config)
34
+ self.audio_processor = AutoProcessor.from_pretrained(config.audio_processor_name)
35
+ self.audio_encoder = HubertXCNNEnoder(config.audio_enc_dim, config.llm_dim, config.audio_encoder_name)
36
+
37
+ self.llm_model = AutoModelForCausalLM.from_pretrained(config.llm_model_checkpoint)
38
+ self.llm_tokenizer = AutoTokenizer.from_pretrained(config.llm_model_name)
39
+
40
+
41
+ # self.llm_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
42
+ # self.llm_tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
43
+
44
+ # peft_config = LoraConfig(
45
+ # r=4,
46
+ # lora_alpha=8,
47
+ # target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'up_proj', 'down_proj', 'gate_proj'],
48
+ # lora_dropout=0.05,
49
+ # task_type="CAUSAL_LM",
50
+ # )
51
+ # self.llm_model = get_peft_model(self.llm_model, peft_config)
52
 
53
  def encode(self, mel, pre_tokenized_ids, post_tokenized_ids, output_tokenized_ids):
54
  batch_size = mel.shape[0]
55
 
56
  with torch.no_grad():
57
  speech_embeds = self.audio_encoder(mel)
58
+ embedder = self.llm_model.model.embed_tokens
59
  pre_prompt_embeds = embedder(pre_tokenized_ids)
60
  post_prompt_embeds = embedder(post_tokenized_ids)
61
  output_prompt_embeds = embedder(output_tokenized_ids)
 
76
  return outputs
77
 
78
  def generate_meta(self, audio_path, instruction="Give me the following information about the audio [Transcript]", max_new_tokens=2000):
79
+ device = self.audio_encoder.return_device()
80
  pre_speech_prompt = f'''Instruction:
81
  {instruction}
82
 
 
95
  post_tokenized_ids = self.llm_tokenizer(post_speech_prompt, padding="do_not_pad", return_tensors='pt', truncation=False, add_special_tokens=False)["input_ids"]
96
  output_tokenized_ids = self.llm_tokenizer(output_prompt, padding="do_not_pad", return_tensors='pt', truncation=False, add_special_tokens=False)["input_ids"]
97
 
98
+ combined_embeds, atts, label_ids = self.encode(wav_tensor.to(device), pre_tokenized_ids.to(device), post_tokenized_ids.to(device), output_tokenized_ids.to(device))
99
 
100
  out = self.llm_model.generate(
101
  inputs_embeds=combined_embeds,
102
  max_new_tokens=max_new_tokens,
103
  ).cpu().tolist()[0]
104
 
105
+ output_text = self.llm_tokenizer.decode(out, skip_special_tokens=True)
106
  return output_text
107
 
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 8381308416
4
  },
5
  "weight_map": {
6
  "audio_encoder.cnn.1.bias": "model-00001-of-00002.safetensors",
@@ -815,514 +815,206 @@
815
  "audio_encoder.encoder.feature_projection.projection.bias": "model-00001-of-00002.safetensors",
816
  "audio_encoder.encoder.feature_projection.projection.weight": "model-00001-of-00002.safetensors",
817
  "audio_encoder.encoder.masked_spec_embed": "model-00001-of-00002.safetensors",
818
- "llm_model.base_model.model.lm_head.weight": "model-00002-of-00002.safetensors",
819
- "llm_model.base_model.model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
820
- "llm_model.base_model.model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
821
- "llm_model.base_model.model.model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
822
- "llm_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
823
- "llm_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
824
- "llm_model.base_model.model.model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
825
- "llm_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
826
- "llm_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
827
- "llm_model.base_model.model.model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
828
- "llm_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
829
- "llm_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
830
- "llm_model.base_model.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
831
- "llm_model.base_model.model.model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
832
- "llm_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
833
- "llm_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
834
- "llm_model.base_model.model.model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
835
- "llm_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
836
- "llm_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
837
- "llm_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
838
- "llm_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
839
- "llm_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
840
- "llm_model.base_model.model.model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
841
- "llm_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
842
- "llm_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
843
- "llm_model.base_model.model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
844
- "llm_model.base_model.model.model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
845
- "llm_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
846
- "llm_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
847
- "llm_model.base_model.model.model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
848
- "llm_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
849
- "llm_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
850
- "llm_model.base_model.model.model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
851
- "llm_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
852
- "llm_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
853
- "llm_model.base_model.model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
854
- "llm_model.base_model.model.model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
855
- "llm_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
856
- "llm_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
857
- "llm_model.base_model.model.model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
858
- "llm_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
859
- "llm_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
860
- "llm_model.base_model.model.model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
861
- "llm_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
862
- "llm_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
863
- "llm_model.base_model.model.model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
864
- "llm_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
865
- "llm_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
866
- "llm_model.base_model.model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
867
- "llm_model.base_model.model.model.layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
868
- "llm_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
869
- "llm_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
870
- "llm_model.base_model.model.model.layers.10.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
871
- "llm_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
872
- "llm_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
873
- "llm_model.base_model.model.model.layers.10.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
874
- "llm_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
875
- "llm_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
876
- "llm_model.base_model.model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
877
- "llm_model.base_model.model.model.layers.10.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
878
- "llm_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
879
- "llm_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
880
- "llm_model.base_model.model.model.layers.10.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
881
- "llm_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
882
- "llm_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
883
- "llm_model.base_model.model.model.layers.10.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
884
- "llm_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
885
- "llm_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
886
- "llm_model.base_model.model.model.layers.10.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
887
- "llm_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
888
- "llm_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
889
- "llm_model.base_model.model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
890
- "llm_model.base_model.model.model.layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
891
- "llm_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
892
- "llm_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
893
- "llm_model.base_model.model.model.layers.11.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
894
- "llm_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
895
- "llm_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
896
- "llm_model.base_model.model.model.layers.11.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
897
- "llm_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
898
- "llm_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
899
- "llm_model.base_model.model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
900
- "llm_model.base_model.model.model.layers.11.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
901
- "llm_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
902
- "llm_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
903
- "llm_model.base_model.model.model.layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
904
- "llm_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
905
- "llm_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
906
- "llm_model.base_model.model.model.layers.11.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
907
- "llm_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
908
- "llm_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
909
- "llm_model.base_model.model.model.layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
910
- "llm_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
911
- "llm_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
912
- "llm_model.base_model.model.model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
913
- "llm_model.base_model.model.model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
914
- "llm_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
915
- "llm_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
916
- "llm_model.base_model.model.model.layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
917
- "llm_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
918
- "llm_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
919
- "llm_model.base_model.model.model.layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
920
- "llm_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
921
- "llm_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
922
- "llm_model.base_model.model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
923
- "llm_model.base_model.model.model.layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
924
- "llm_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
925
- "llm_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
926
- "llm_model.base_model.model.model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
927
- "llm_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
928
- "llm_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
929
- "llm_model.base_model.model.model.layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
930
- "llm_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
931
- "llm_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
932
- "llm_model.base_model.model.model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
933
- "llm_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
934
- "llm_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
935
- "llm_model.base_model.model.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
936
- "llm_model.base_model.model.model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
937
- "llm_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
938
- "llm_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
939
- "llm_model.base_model.model.model.layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
940
- "llm_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
941
- "llm_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
942
- "llm_model.base_model.model.model.layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
943
- "llm_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
944
- "llm_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
945
- "llm_model.base_model.model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
946
- "llm_model.base_model.model.model.layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
947
- "llm_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
948
- "llm_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
949
- "llm_model.base_model.model.model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
950
- "llm_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
951
- "llm_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
952
- "llm_model.base_model.model.model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
953
- "llm_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
954
- "llm_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
955
- "llm_model.base_model.model.model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
956
- "llm_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
957
- "llm_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
958
- "llm_model.base_model.model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
959
- "llm_model.base_model.model.model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
960
- "llm_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
961
- "llm_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
962
- "llm_model.base_model.model.model.layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
963
- "llm_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
964
- "llm_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
965
- "llm_model.base_model.model.model.layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
966
- "llm_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
967
- "llm_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
968
- "llm_model.base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
969
- "llm_model.base_model.model.model.layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
970
- "llm_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
971
- "llm_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
972
- "llm_model.base_model.model.model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
973
- "llm_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
974
- "llm_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
975
- "llm_model.base_model.model.model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
976
- "llm_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
977
- "llm_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
978
- "llm_model.base_model.model.model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
979
- "llm_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
980
- "llm_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
981
- "llm_model.base_model.model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
982
- "llm_model.base_model.model.model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
983
- "llm_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
984
- "llm_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
985
- "llm_model.base_model.model.model.layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
986
- "llm_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
987
- "llm_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
988
- "llm_model.base_model.model.model.layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
989
- "llm_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
990
- "llm_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
991
- "llm_model.base_model.model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
992
- "llm_model.base_model.model.model.layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
993
- "llm_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
994
- "llm_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
995
- "llm_model.base_model.model.model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
996
- "llm_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
997
- "llm_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
998
- "llm_model.base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
999
- "llm_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1000
- "llm_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1001
- "llm_model.base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1002
- "llm_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1003
- "llm_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1004
- "llm_model.base_model.model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
1005
- "llm_model.base_model.model.model.layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1006
- "llm_model.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1007
- "llm_model.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1008
- "llm_model.base_model.model.model.layers.16.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1009
- "llm_model.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1010
- "llm_model.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1011
- "llm_model.base_model.model.model.layers.16.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1012
- "llm_model.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1013
- "llm_model.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1014
- "llm_model.base_model.model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1015
- "llm_model.base_model.model.model.layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1016
- "llm_model.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1017
- "llm_model.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1018
- "llm_model.base_model.model.model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1019
- "llm_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1020
- "llm_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1021
- "llm_model.base_model.model.model.layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1022
- "llm_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1023
- "llm_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1024
- "llm_model.base_model.model.model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1025
- "llm_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1026
- "llm_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1027
- "llm_model.base_model.model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
1028
- "llm_model.base_model.model.model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1029
- "llm_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1030
- "llm_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1031
- "llm_model.base_model.model.model.layers.17.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1032
- "llm_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1033
- "llm_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1034
- "llm_model.base_model.model.model.layers.17.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1035
- "llm_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1036
- "llm_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1037
- "llm_model.base_model.model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1038
- "llm_model.base_model.model.model.layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1039
- "llm_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1040
- "llm_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1041
- "llm_model.base_model.model.model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1042
- "llm_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1043
- "llm_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1044
- "llm_model.base_model.model.model.layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1045
- "llm_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1046
- "llm_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1047
- "llm_model.base_model.model.model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1048
- "llm_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1049
- "llm_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1050
- "llm_model.base_model.model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
1051
- "llm_model.base_model.model.model.layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1052
- "llm_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1053
- "llm_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1054
- "llm_model.base_model.model.model.layers.18.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1055
- "llm_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1056
- "llm_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1057
- "llm_model.base_model.model.model.layers.18.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1058
- "llm_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1059
- "llm_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1060
- "llm_model.base_model.model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1061
- "llm_model.base_model.model.model.layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1062
- "llm_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1063
- "llm_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1064
- "llm_model.base_model.model.model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1065
- "llm_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1066
- "llm_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1067
- "llm_model.base_model.model.model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1068
- "llm_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1069
- "llm_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1070
- "llm_model.base_model.model.model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1071
- "llm_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1072
- "llm_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1073
- "llm_model.base_model.model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
1074
- "llm_model.base_model.model.model.layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1075
- "llm_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1076
- "llm_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1077
- "llm_model.base_model.model.model.layers.19.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1078
- "llm_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1079
- "llm_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1080
- "llm_model.base_model.model.model.layers.19.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1081
- "llm_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1082
- "llm_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1083
- "llm_model.base_model.model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1084
- "llm_model.base_model.model.model.layers.19.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1085
- "llm_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1086
- "llm_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1087
- "llm_model.base_model.model.model.layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1088
- "llm_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1089
- "llm_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1090
- "llm_model.base_model.model.model.layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1091
- "llm_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1092
- "llm_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1093
- "llm_model.base_model.model.model.layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1094
- "llm_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1095
- "llm_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1096
- "llm_model.base_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
1097
- "llm_model.base_model.model.model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1098
- "llm_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1099
- "llm_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1100
- "llm_model.base_model.model.model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1101
- "llm_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1102
- "llm_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1103
- "llm_model.base_model.model.model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1104
- "llm_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1105
- "llm_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1106
- "llm_model.base_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1107
- "llm_model.base_model.model.model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1108
- "llm_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1109
- "llm_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1110
- "llm_model.base_model.model.model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1111
- "llm_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1112
- "llm_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1113
- "llm_model.base_model.model.model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1114
- "llm_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1115
- "llm_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1116
- "llm_model.base_model.model.model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1117
- "llm_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1118
- "llm_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1119
- "llm_model.base_model.model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
1120
- "llm_model.base_model.model.model.layers.20.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1121
- "llm_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1122
- "llm_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1123
- "llm_model.base_model.model.model.layers.20.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1124
- "llm_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1125
- "llm_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1126
- "llm_model.base_model.model.model.layers.20.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1127
- "llm_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1128
- "llm_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1129
- "llm_model.base_model.model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1130
- "llm_model.base_model.model.model.layers.20.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1131
- "llm_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1132
- "llm_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1133
- "llm_model.base_model.model.model.layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1134
- "llm_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1135
- "llm_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1136
- "llm_model.base_model.model.model.layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1137
- "llm_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1138
- "llm_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1139
- "llm_model.base_model.model.model.layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1140
- "llm_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1141
- "llm_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1142
- "llm_model.base_model.model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
1143
- "llm_model.base_model.model.model.layers.21.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1144
- "llm_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1145
- "llm_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1146
- "llm_model.base_model.model.model.layers.21.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1147
- "llm_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1148
- "llm_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1149
- "llm_model.base_model.model.model.layers.21.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1150
- "llm_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1151
- "llm_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1152
- "llm_model.base_model.model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1153
- "llm_model.base_model.model.model.layers.21.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1154
- "llm_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1155
- "llm_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1156
- "llm_model.base_model.model.model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1157
- "llm_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1158
- "llm_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1159
- "llm_model.base_model.model.model.layers.21.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1160
- "llm_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1161
- "llm_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1162
- "llm_model.base_model.model.model.layers.21.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1163
- "llm_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1164
- "llm_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1165
- "llm_model.base_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
1166
- "llm_model.base_model.model.model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1167
- "llm_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1168
- "llm_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1169
- "llm_model.base_model.model.model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1170
- "llm_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1171
- "llm_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1172
- "llm_model.base_model.model.model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1173
- "llm_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1174
- "llm_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1175
- "llm_model.base_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1176
- "llm_model.base_model.model.model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1177
- "llm_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1178
- "llm_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1179
- "llm_model.base_model.model.model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1180
- "llm_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1181
- "llm_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1182
- "llm_model.base_model.model.model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1183
- "llm_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1184
- "llm_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1185
- "llm_model.base_model.model.model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1186
- "llm_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1187
- "llm_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1188
- "llm_model.base_model.model.model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
1189
- "llm_model.base_model.model.model.layers.4.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1190
- "llm_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1191
- "llm_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1192
- "llm_model.base_model.model.model.layers.4.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1193
- "llm_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1194
- "llm_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1195
- "llm_model.base_model.model.model.layers.4.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1196
- "llm_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1197
- "llm_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1198
- "llm_model.base_model.model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1199
- "llm_model.base_model.model.model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1200
- "llm_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1201
- "llm_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1202
- "llm_model.base_model.model.model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1203
- "llm_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1204
- "llm_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1205
- "llm_model.base_model.model.model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1206
- "llm_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1207
- "llm_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1208
- "llm_model.base_model.model.model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
1209
- "llm_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
1210
- "llm_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
1211
- "llm_model.base_model.model.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
1212
- "llm_model.base_model.model.model.layers.5.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1213
- "llm_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1214
- "llm_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1215
- "llm_model.base_model.model.model.layers.5.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1216
- "llm_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1217
- "llm_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1218
- "llm_model.base_model.model.model.layers.5.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1219
- "llm_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1220
- "llm_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1221
- "llm_model.base_model.model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1222
- "llm_model.base_model.model.model.layers.5.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1223
- "llm_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1224
- "llm_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1225
- "llm_model.base_model.model.model.layers.5.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1226
- "llm_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1227
- "llm_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1228
- "llm_model.base_model.model.model.layers.5.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1229
- "llm_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1230
- "llm_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1231
- "llm_model.base_model.model.model.layers.5.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1232
- "llm_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1233
- "llm_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1234
- "llm_model.base_model.model.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
1235
- "llm_model.base_model.model.model.layers.6.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1236
- "llm_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1237
- "llm_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1238
- "llm_model.base_model.model.model.layers.6.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1239
- "llm_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1240
- "llm_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1241
- "llm_model.base_model.model.model.layers.6.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1242
- "llm_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1243
- "llm_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1244
- "llm_model.base_model.model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1245
- "llm_model.base_model.model.model.layers.6.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1246
- "llm_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1247
- "llm_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1248
- "llm_model.base_model.model.model.layers.6.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1249
- "llm_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1250
- "llm_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1251
- "llm_model.base_model.model.model.layers.6.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1252
- "llm_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1253
- "llm_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1254
- "llm_model.base_model.model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1255
- "llm_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1256
- "llm_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1257
- "llm_model.base_model.model.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
1258
- "llm_model.base_model.model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1259
- "llm_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1260
- "llm_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1261
- "llm_model.base_model.model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1262
- "llm_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1263
- "llm_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1264
- "llm_model.base_model.model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1265
- "llm_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1266
- "llm_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1267
- "llm_model.base_model.model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1268
- "llm_model.base_model.model.model.layers.7.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1269
- "llm_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1270
- "llm_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1271
- "llm_model.base_model.model.model.layers.7.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1272
- "llm_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1273
- "llm_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1274
- "llm_model.base_model.model.model.layers.7.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1275
- "llm_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1276
- "llm_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1277
- "llm_model.base_model.model.model.layers.7.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1278
- "llm_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1279
- "llm_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1280
- "llm_model.base_model.model.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
1281
- "llm_model.base_model.model.model.layers.8.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1282
- "llm_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1283
- "llm_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1284
- "llm_model.base_model.model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1285
- "llm_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1286
- "llm_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1287
- "llm_model.base_model.model.model.layers.8.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1288
- "llm_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1289
- "llm_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1290
- "llm_model.base_model.model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1291
- "llm_model.base_model.model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1292
- "llm_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1293
- "llm_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1294
- "llm_model.base_model.model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1295
- "llm_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1296
- "llm_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1297
- "llm_model.base_model.model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1298
- "llm_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1299
- "llm_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1300
- "llm_model.base_model.model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1301
- "llm_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1302
- "llm_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1303
- "llm_model.base_model.model.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
1304
- "llm_model.base_model.model.model.layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1305
- "llm_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1306
- "llm_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1307
- "llm_model.base_model.model.model.layers.9.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1308
- "llm_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1309
- "llm_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1310
- "llm_model.base_model.model.model.layers.9.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1311
- "llm_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1312
- "llm_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1313
- "llm_model.base_model.model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1314
- "llm_model.base_model.model.model.layers.9.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1315
- "llm_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1316
- "llm_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1317
- "llm_model.base_model.model.model.layers.9.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1318
- "llm_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1319
- "llm_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1320
- "llm_model.base_model.model.model.layers.9.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1321
- "llm_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1322
- "llm_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1323
- "llm_model.base_model.model.model.layers.9.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
1324
- "llm_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
1325
- "llm_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
1326
- "llm_model.base_model.model.model.norm.weight": "model-00002-of-00002.safetensors"
1327
  }
1328
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 8368692736
4
  },
5
  "weight_map": {
6
  "audio_encoder.cnn.1.bias": "model-00001-of-00002.safetensors",
 
815
  "audio_encoder.encoder.feature_projection.projection.bias": "model-00001-of-00002.safetensors",
816
  "audio_encoder.encoder.feature_projection.projection.weight": "model-00001-of-00002.safetensors",
817
  "audio_encoder.encoder.masked_spec_embed": "model-00001-of-00002.safetensors",
818
+ "llm_model.lm_head.weight": "model-00002-of-00002.safetensors",
819
+ "llm_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
820
+ "llm_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
821
+ "llm_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
822
+ "llm_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
823
+ "llm_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
824
+ "llm_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
825
+ "llm_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
826
+ "llm_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
827
+ "llm_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
828
+ "llm_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
829
+ "llm_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
830
+ "llm_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
831
+ "llm_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
832
+ "llm_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
833
+ "llm_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
834
+ "llm_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
835
+ "llm_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
836
+ "llm_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
837
+ "llm_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
838
+ "llm_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
839
+ "llm_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
840
+ "llm_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
841
+ "llm_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
842
+ "llm_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
843
+ "llm_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
844
+ "llm_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
845
+ "llm_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
846
+ "llm_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
847
+ "llm_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
848
+ "llm_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
849
+ "llm_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
850
+ "llm_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
851
+ "llm_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
852
+ "llm_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
853
+ "llm_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
854
+ "llm_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
855
+ "llm_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
856
+ "llm_model.model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
857
+ "llm_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
858
+ "llm_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
859
+ "llm_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
860
+ "llm_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
861
+ "llm_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
862
+ "llm_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
863
+ "llm_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
864
+ "llm_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
865
+ "llm_model.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
866
+ "llm_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
867
+ "llm_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
868
+ "llm_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
869
+ "llm_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
870
+ "llm_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
871
+ "llm_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
872
+ "llm_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
873
+ "llm_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
874
+ "llm_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
875
+ "llm_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
876
+ "llm_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
877
+ "llm_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
878
+ "llm_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
879
+ "llm_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
880
+ "llm_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
881
+ "llm_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
882
+ "llm_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
883
+ "llm_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
884
+ "llm_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
885
+ "llm_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
886
+ "llm_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
887
+ "llm_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
888
+ "llm_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
889
+ "llm_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
890
+ "llm_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
891
+ "llm_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
892
+ "llm_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
893
+ "llm_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
894
+ "llm_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
895
+ "llm_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
896
+ "llm_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
897
+ "llm_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
898
+ "llm_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
899
+ "llm_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
900
+ "llm_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
901
+ "llm_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
902
+ "llm_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
903
+ "llm_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
904
+ "llm_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
905
+ "llm_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
906
+ "llm_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
907
+ "llm_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
908
+ "llm_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
909
+ "llm_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
910
+ "llm_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
911
+ "llm_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
912
+ "llm_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
913
+ "llm_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
914
+ "llm_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
915
+ "llm_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
916
+ "llm_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
917
+ "llm_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
918
+ "llm_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
919
+ "llm_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
920
+ "llm_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
921
+ "llm_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
922
+ "llm_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
923
+ "llm_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
924
+ "llm_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
925
+ "llm_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
926
+ "llm_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
927
+ "llm_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
928
+ "llm_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
929
+ "llm_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
930
+ "llm_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
931
+ "llm_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
932
+ "llm_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
933
+ "llm_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
934
+ "llm_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
935
+ "llm_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
936
+ "llm_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
937
+ "llm_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
938
+ "llm_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
939
+ "llm_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
940
+ "llm_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
941
+ "llm_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
942
+ "llm_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
943
+ "llm_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
944
+ "llm_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
945
+ "llm_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
946
+ "llm_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
947
+ "llm_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
948
+ "llm_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
949
+ "llm_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
950
+ "llm_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
951
+ "llm_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
952
+ "llm_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
953
+ "llm_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
954
+ "llm_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
955
+ "llm_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
956
+ "llm_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
957
+ "llm_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
958
+ "llm_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
959
+ "llm_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
960
+ "llm_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
961
+ "llm_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
962
+ "llm_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
963
+ "llm_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
964
+ "llm_model.model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
965
+ "llm_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
966
+ "llm_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
967
+ "llm_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
968
+ "llm_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
969
+ "llm_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
970
+ "llm_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
971
+ "llm_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
972
+ "llm_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
973
+ "llm_model.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
974
+ "llm_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
975
+ "llm_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
976
+ "llm_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
977
+ "llm_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
978
+ "llm_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
979
+ "llm_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
980
+ "llm_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
981
+ "llm_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
982
+ "llm_model.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
983
+ "llm_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
984
+ "llm_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
985
+ "llm_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
986
+ "llm_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
987
+ "llm_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
988
+ "llm_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
989
+ "llm_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
990
+ "llm_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
991
+ "llm_model.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
992
+ "llm_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
993
+ "llm_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
994
+ "llm_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
995
+ "llm_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
996
+ "llm_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
997
+ "llm_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
998
+ "llm_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
999
+ "llm_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
1000
+ "llm_model.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
1001
+ "llm_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
1002
+ "llm_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
1003
+ "llm_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
1004
+ "llm_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1005
+ "llm_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
1006
+ "llm_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
1007
+ "llm_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
1008
+ "llm_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
1009
+ "llm_model.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
1010
+ "llm_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
1011
+ "llm_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
1012
+ "llm_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
1013
+ "llm_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
1014
+ "llm_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
1015
+ "llm_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
1016
+ "llm_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
1017
+ "llm_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
1018
+ "llm_model.model.norm.weight": "model-00002-of-00002.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1019
  }
1020
  }