Hugging Face's logo

ibm-granite
/
granite-speech-3.3-2b

Automatic Speech Recognition
Transformers
Safetensors
granite_speech
Model card Files
xet
Community
7
gsaon commited on
Commit
42d8bd8
·
verified ·
1 Parent(s): c6ad303

Upload 16 files (#1)

Browse files

- Upload 16 files (ea8391c111e059f348231a906c9793c19d1d9e59)

Files changed (16) hide show
  1. adapter_config.json +29 -0
  2. adapter_model.safetensors +3 -0
  3. added_tokens.json +10 -0
  4. chat_template.jinja +62 -0
  5. config.json +79 -0
  6. generation_config.json +8 -0
  7. merges.txt +0 -0
  8. model-00001-of-00003.safetensors +3 -0
  9. model-00002-of-00003.safetensors +3 -0
  10. model-00003-of-00003.safetensors +3 -0
  11. model.safetensors.index.json +762 -0
  12. preprocessor_config.json +1 -0
  13. special_tokens_map.json +39 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +242 -0
  16. vocab.json +0 -0
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ibm-granite/granite-speech-3.3-2b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9833221a08ad71b2406bcbc0364ae8682878cc9013b2e9dec65b95a03808883b
3
+ size 68178600
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|audio|>": 49159,
3
+ "<|end_of_cite|>": 49156,
4
+ "<|end_of_plugin|>": 49158,
5
+ "<|end_of_role|>": 49153,
6
+ "<|start_of_cite|>": 49155,
7
+ "<|start_of_plugin|>": 49157,
8
+ "<|start_of_role|>": 49152,
9
+ "<|tool_call|>": 49154
10
+ }
chat_template.jinja ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# Alias tools -> available_tools #}
2
+ {%- if tools and not available_tools -%}
3
+ {%- set available_tools = tools -%}
4
+ {%- endif -%}
5
+ {%- if messages[0]['role'] == 'system' %}
6
+ {%- set system_message = messages[0]['content'] %}
7
+ {%- set loop_messages = messages[1:] %}
8
+ {%- else %}
9
+ {%- set system_message = "Knowledge Cutoff Date: April 2024.
10
+ Today's Date: " + strftime_now('%B %d, %Y') + ".
11
+ You are Granite, developed by IBM." %}
12
+ {%- if available_tools and documents %}
13
+ {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.
14
+ Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
15
+ {%- elif available_tools %}
16
+ {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
17
+ {%- elif documents %}
18
+ {%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
19
+ {%- elif thinking %}
20
+ {%- set system_message = system_message + " You are a helpful AI assistant.
21
+ Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
22
+ {%- else %}
23
+ {%- set system_message = system_message + " You are a helpful AI assistant." %}
24
+ {%- endif %}
25
+ {%- if 'citations' in controls and documents %}
26
+ {%- set system_message = system_message + '
27
+ Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
28
+ {%- endif %}
29
+ {%- if 'hallucinations' in controls and documents %}
30
+ {%- set system_message = system_message + '
31
+ Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
32
+ {%- endif %}
33
+ {%- set loop_messages = messages %}
34
+ {%- endif %}
35
+ {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
36
+ ' }}
37
+ {%- if available_tools %}
38
+ {{- '<|start_of_role|>available_tools<|end_of_role|>' }}
39
+ {{- available_tools | tojson(indent=4) }}
40
+ {{- '<|end_of_text|>
41
+ ' }}
42
+ {%- endif %}
43
+ {%- if documents %}
44
+ {%- for document in documents %}
45
+ {{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
46
+ ' }}
47
+ {{- document['text'] }}
48
+ {{- '<|end_of_text|>
49
+ ' }}
50
+ {%- endfor %}
51
+ {%- endif %}
52
+ {%- for message in loop_messages %}
53
+ {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
54
+ ' }}
55
+ {%- if loop.last and add_generation_prompt %}
56
+ {{- '<|start_of_role|>assistant' }}
57
+ {%- if controls %}
58
+ {{- ' ' + controls | tojson()}}
59
+ {%- endif %}
60
+ {{- '<|end_of_role|>' }}
61
+ {%- endif %}
62
+ {%- endfor %}
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteSpeechForConditionalGeneration"
4
+ ],
5
+ "audio_token_index": 49159,
6
+ "downsample_rate": 5,
7
+ "encoder_config": {
8
+ "context_size": 200,
9
+ "conv_expansion_factor": 2,
10
+ "conv_kernel_size": 15,
11
+ "dim_head": 128,
12
+ "dropout": 0.1,
13
+ "feedforward_mult": 4,
14
+ "hidden_dim": 1024,
15
+ "input_dim": 160,
16
+ "max_pos_emb": 512,
17
+ "model_type": "granite_speech_encoder",
18
+ "num_heads": 8,
19
+ "num_layers": 10,
20
+ "output_dim": 42
21
+ },
22
+ "has_lora_adapter": true,
23
+ "initializer_range": 0.02,
24
+ "model_type": "granite_speech",
25
+ "projector_config": {
26
+ "_attn_implementation_autoset": true,
27
+ "attention_probs_dropout_prob": 0.1,
28
+ "cross_attention_frequency": 1,
29
+ "encoder_hidden_size": 1024,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 1024,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 4096,
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 2048,
37
+ "model_type": "blip_2_qformer",
38
+ "num_attention_heads": 16,
39
+ "num_hidden_layers": 2,
40
+ "position_embedding_type": "absolute",
41
+ "use_qformer_text_input": false,
42
+ "vocab_size": 30522
43
+ },
44
+ "text_config": {
45
+ "_name_or_path": "ibm-granite/granite-3.3-2b-instruct",
46
+ "architectures": [
47
+ "GraniteForCausalLM"
48
+ ],
49
+ "attention_bias": false,
50
+ "attention_dropout": 0.0,
51
+ "attention_multiplier": 0.015625,
52
+ "bos_token_id": 0,
53
+ "embedding_multiplier": 12.0,
54
+ "eos_token_id": 0,
55
+ "hidden_act": "silu",
56
+ "hidden_size": 2048,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 8192,
59
+ "logits_scaling": 8.0,
60
+ "max_position_embeddings": 131072,
61
+ "mlp_bias": false,
62
+ "model_type": "granite",
63
+ "num_attention_heads": 32,
64
+ "num_hidden_layers": 40,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 0,
67
+ "residual_multiplier": 0.22,
68
+ "rms_norm_eps": 1e-05,
69
+ "rope_scaling": null,
70
+ "rope_theta": 10000000.0,
71
+ "tie_word_embeddings": true,
72
+ "torch_dtype": "bfloat16",
73
+ "use_cache": true,
74
+ "vocab_size": 49160
75
+ },
76
+ "torch_dtype": "bfloat16",
77
+ "transformers_version": "4.52.0.dev0",
78
+ "window_size": 15
79
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.52.0.dev0",
7
+ "use_cache": true
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd355249426713a1628972b46d82d4cc1e5efc5af62b77884410d4d2b42004c7
3
+ size 1992459128
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6fb9326afc6776e711662437ae38957b898b38716772ad24f6ef0a3c3e06694
3
+ size 1992453224
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eaba70566e777f00625eac8762390fcaa5b786d8113e6e4c9d723609b5a0bb2
3
+ size 1703356524
model.safetensors.index.json ADDED
@@ -0,0 +1,762 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5688173220
4
+ },
5
+ "weight_map": {
6
+ "encoder.input_linear.bias": "model-00003-of-00003.safetensors",
7
+ "encoder.input_linear.weight": "model-00003-of-00003.safetensors",
8
+ "encoder.layers.0.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
9
+ "encoder.layers.0.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
10
+ "encoder.layers.0.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
11
+ "encoder.layers.0.attn.to_kv.weight": "model-00003-of-00003.safetensors",
12
+ "encoder.layers.0.attn.to_out.bias": "model-00003-of-00003.safetensors",
13
+ "encoder.layers.0.attn.to_out.weight": "model-00003-of-00003.safetensors",
14
+ "encoder.layers.0.attn.to_q.weight": "model-00003-of-00003.safetensors",
15
+ "encoder.layers.0.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
16
+ "encoder.layers.0.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
17
+ "encoder.layers.0.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
18
+ "encoder.layers.0.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
19
+ "encoder.layers.0.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
20
+ "encoder.layers.0.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
21
+ "encoder.layers.0.conv.down_conv.bias": "model-00003-of-00003.safetensors",
22
+ "encoder.layers.0.conv.down_conv.weight": "model-00003-of-00003.safetensors",
23
+ "encoder.layers.0.conv.norm.bias": "model-00003-of-00003.safetensors",
24
+ "encoder.layers.0.conv.norm.weight": "model-00003-of-00003.safetensors",
25
+ "encoder.layers.0.conv.up_conv.bias": "model-00003-of-00003.safetensors",
26
+ "encoder.layers.0.conv.up_conv.weight": "model-00003-of-00003.safetensors",
27
+ "encoder.layers.0.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
28
+ "encoder.layers.0.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
29
+ "encoder.layers.0.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
30
+ "encoder.layers.0.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
31
+ "encoder.layers.0.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
32
+ "encoder.layers.0.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
33
+ "encoder.layers.0.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
34
+ "encoder.layers.0.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
35
+ "encoder.layers.0.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
36
+ "encoder.layers.0.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
37
+ "encoder.layers.0.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
38
+ "encoder.layers.0.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
39
+ "encoder.layers.0.post_norm.bias": "model-00003-of-00003.safetensors",
40
+ "encoder.layers.0.post_norm.weight": "model-00003-of-00003.safetensors",
41
+ "encoder.layers.1.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
42
+ "encoder.layers.1.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
43
+ "encoder.layers.1.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
44
+ "encoder.layers.1.attn.to_kv.weight": "model-00003-of-00003.safetensors",
45
+ "encoder.layers.1.attn.to_out.bias": "model-00003-of-00003.safetensors",
46
+ "encoder.layers.1.attn.to_out.weight": "model-00003-of-00003.safetensors",
47
+ "encoder.layers.1.attn.to_q.weight": "model-00003-of-00003.safetensors",
48
+ "encoder.layers.1.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
49
+ "encoder.layers.1.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
50
+ "encoder.layers.1.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
51
+ "encoder.layers.1.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
52
+ "encoder.layers.1.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
53
+ "encoder.layers.1.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
54
+ "encoder.layers.1.conv.down_conv.bias": "model-00003-of-00003.safetensors",
55
+ "encoder.layers.1.conv.down_conv.weight": "model-00003-of-00003.safetensors",
56
+ "encoder.layers.1.conv.norm.bias": "model-00003-of-00003.safetensors",
57
+ "encoder.layers.1.conv.norm.weight": "model-00003-of-00003.safetensors",
58
+ "encoder.layers.1.conv.up_conv.bias": "model-00003-of-00003.safetensors",
59
+ "encoder.layers.1.conv.up_conv.weight": "model-00003-of-00003.safetensors",
60
+ "encoder.layers.1.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
61
+ "encoder.layers.1.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
62
+ "encoder.layers.1.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
63
+ "encoder.layers.1.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
64
+ "encoder.layers.1.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
65
+ "encoder.layers.1.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
66
+ "encoder.layers.1.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
67
+ "encoder.layers.1.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
68
+ "encoder.layers.1.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
69
+ "encoder.layers.1.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
70
+ "encoder.layers.1.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
71
+ "encoder.layers.1.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
72
+ "encoder.layers.1.post_norm.bias": "model-00003-of-00003.safetensors",
73
+ "encoder.layers.1.post_norm.weight": "model-00003-of-00003.safetensors",
74
+ "encoder.layers.2.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
75
+ "encoder.layers.2.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
76
+ "encoder.layers.2.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
77
+ "encoder.layers.2.attn.to_kv.weight": "model-00003-of-00003.safetensors",
78
+ "encoder.layers.2.attn.to_out.bias": "model-00003-of-00003.safetensors",
79
+ "encoder.layers.2.attn.to_out.weight": "model-00003-of-00003.safetensors",
80
+ "encoder.layers.2.attn.to_q.weight": "model-00003-of-00003.safetensors",
81
+ "encoder.layers.2.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
82
+ "encoder.layers.2.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
83
+ "encoder.layers.2.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
84
+ "encoder.layers.2.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
85
+ "encoder.layers.2.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
86
+ "encoder.layers.2.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
87
+ "encoder.layers.2.conv.down_conv.bias": "model-00003-of-00003.safetensors",
88
+ "encoder.layers.2.conv.down_conv.weight": "model-00003-of-00003.safetensors",
89
+ "encoder.layers.2.conv.norm.bias": "model-00003-of-00003.safetensors",
90
+ "encoder.layers.2.conv.norm.weight": "model-00003-of-00003.safetensors",
91
+ "encoder.layers.2.conv.up_conv.bias": "model-00003-of-00003.safetensors",
92
+ "encoder.layers.2.conv.up_conv.weight": "model-00003-of-00003.safetensors",
93
+ "encoder.layers.2.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
94
+ "encoder.layers.2.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
95
+ "encoder.layers.2.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
96
+ "encoder.layers.2.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
97
+ "encoder.layers.2.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
98
+ "encoder.layers.2.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
99
+ "encoder.layers.2.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
100
+ "encoder.layers.2.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
101
+ "encoder.layers.2.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
102
+ "encoder.layers.2.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
103
+ "encoder.layers.2.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
104
+ "encoder.layers.2.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
105
+ "encoder.layers.2.post_norm.bias": "model-00003-of-00003.safetensors",
106
+ "encoder.layers.2.post_norm.weight": "model-00003-of-00003.safetensors",
107
+ "encoder.layers.3.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
108
+ "encoder.layers.3.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
109
+ "encoder.layers.3.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
110
+ "encoder.layers.3.attn.to_kv.weight": "model-00003-of-00003.safetensors",
111
+ "encoder.layers.3.attn.to_out.bias": "model-00003-of-00003.safetensors",
112
+ "encoder.layers.3.attn.to_out.weight": "model-00003-of-00003.safetensors",
113
+ "encoder.layers.3.attn.to_q.weight": "model-00003-of-00003.safetensors",
114
+ "encoder.layers.3.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
115
+ "encoder.layers.3.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
116
+ "encoder.layers.3.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
117
+ "encoder.layers.3.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
118
+ "encoder.layers.3.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
119
+ "encoder.layers.3.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
120
+ "encoder.layers.3.conv.down_conv.bias": "model-00003-of-00003.safetensors",
121
+ "encoder.layers.3.conv.down_conv.weight": "model-00003-of-00003.safetensors",
122
+ "encoder.layers.3.conv.norm.bias": "model-00003-of-00003.safetensors",
123
+ "encoder.layers.3.conv.norm.weight": "model-00003-of-00003.safetensors",
124
+ "encoder.layers.3.conv.up_conv.bias": "model-00003-of-00003.safetensors",
125
+ "encoder.layers.3.conv.up_conv.weight": "model-00003-of-00003.safetensors",
126
+ "encoder.layers.3.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
127
+ "encoder.layers.3.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
128
+ "encoder.layers.3.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
129
+ "encoder.layers.3.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
130
+ "encoder.layers.3.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
131
+ "encoder.layers.3.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
132
+ "encoder.layers.3.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
133
+ "encoder.layers.3.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
134
+ "encoder.layers.3.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
135
+ "encoder.layers.3.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
136
+ "encoder.layers.3.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
137
+ "encoder.layers.3.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
138
+ "encoder.layers.3.post_norm.bias": "model-00003-of-00003.safetensors",
139
+ "encoder.layers.3.post_norm.weight": "model-00003-of-00003.safetensors",
140
+ "encoder.layers.4.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
141
+ "encoder.layers.4.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
142
+ "encoder.layers.4.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
143
+ "encoder.layers.4.attn.to_kv.weight": "model-00003-of-00003.safetensors",
144
+ "encoder.layers.4.attn.to_out.bias": "model-00003-of-00003.safetensors",
145
+ "encoder.layers.4.attn.to_out.weight": "model-00003-of-00003.safetensors",
146
+ "encoder.layers.4.attn.to_q.weight": "model-00003-of-00003.safetensors",
147
+ "encoder.layers.4.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
148
+ "encoder.layers.4.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
149
+ "encoder.layers.4.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
150
+ "encoder.layers.4.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
151
+ "encoder.layers.4.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
152
+ "encoder.layers.4.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
153
+ "encoder.layers.4.conv.down_conv.bias": "model-00003-of-00003.safetensors",
154
+ "encoder.layers.4.conv.down_conv.weight": "model-00003-of-00003.safetensors",
155
+ "encoder.layers.4.conv.norm.bias": "model-00003-of-00003.safetensors",
156
+ "encoder.layers.4.conv.norm.weight": "model-00003-of-00003.safetensors",
157
+ "encoder.layers.4.conv.up_conv.bias": "model-00003-of-00003.safetensors",
158
+ "encoder.layers.4.conv.up_conv.weight": "model-00003-of-00003.safetensors",
159
+ "encoder.layers.4.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
160
+ "encoder.layers.4.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
161
+ "encoder.layers.4.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
162
+ "encoder.layers.4.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
163
+ "encoder.layers.4.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
164
+ "encoder.layers.4.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "encoder.layers.4.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
166
+ "encoder.layers.4.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
167
+ "encoder.layers.4.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
168
+ "encoder.layers.4.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
169
+ "encoder.layers.4.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
170
+ "encoder.layers.4.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
171
+ "encoder.layers.4.post_norm.bias": "model-00003-of-00003.safetensors",
172
+ "encoder.layers.4.post_norm.weight": "model-00003-of-00003.safetensors",
173
+ "encoder.layers.5.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
174
+ "encoder.layers.5.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
175
+ "encoder.layers.5.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
176
+ "encoder.layers.5.attn.to_kv.weight": "model-00003-of-00003.safetensors",
177
+ "encoder.layers.5.attn.to_out.bias": "model-00003-of-00003.safetensors",
178
+ "encoder.layers.5.attn.to_out.weight": "model-00003-of-00003.safetensors",
179
+ "encoder.layers.5.attn.to_q.weight": "model-00003-of-00003.safetensors",
180
+ "encoder.layers.5.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
181
+ "encoder.layers.5.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
182
+ "encoder.layers.5.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
183
+ "encoder.layers.5.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
184
+ "encoder.layers.5.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
185
+ "encoder.layers.5.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
186
+ "encoder.layers.5.conv.down_conv.bias": "model-00003-of-00003.safetensors",
187
+ "encoder.layers.5.conv.down_conv.weight": "model-00003-of-00003.safetensors",
188
+ "encoder.layers.5.conv.norm.bias": "model-00003-of-00003.safetensors",
189
+ "encoder.layers.5.conv.norm.weight": "model-00003-of-00003.safetensors",
190
+ "encoder.layers.5.conv.up_conv.bias": "model-00003-of-00003.safetensors",
191
+ "encoder.layers.5.conv.up_conv.weight": "model-00003-of-00003.safetensors",
192
+ "encoder.layers.5.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
193
+ "encoder.layers.5.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
194
+ "encoder.layers.5.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
195
+ "encoder.layers.5.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
196
+ "encoder.layers.5.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
197
+ "encoder.layers.5.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
198
+ "encoder.layers.5.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
199
+ "encoder.layers.5.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
200
+ "encoder.layers.5.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
201
+ "encoder.layers.5.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
202
+ "encoder.layers.5.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
203
+ "encoder.layers.5.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
204
+ "encoder.layers.5.post_norm.bias": "model-00003-of-00003.safetensors",
205
+ "encoder.layers.5.post_norm.weight": "model-00003-of-00003.safetensors",
206
+ "encoder.layers.6.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
207
+ "encoder.layers.6.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
208
+ "encoder.layers.6.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
209
+ "encoder.layers.6.attn.to_kv.weight": "model-00003-of-00003.safetensors",
210
+ "encoder.layers.6.attn.to_out.bias": "model-00003-of-00003.safetensors",
211
+ "encoder.layers.6.attn.to_out.weight": "model-00003-of-00003.safetensors",
212
+ "encoder.layers.6.attn.to_q.weight": "model-00003-of-00003.safetensors",
213
+ "encoder.layers.6.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
214
+ "encoder.layers.6.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
215
+ "encoder.layers.6.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
216
+ "encoder.layers.6.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
217
+ "encoder.layers.6.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
218
+ "encoder.layers.6.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
219
+ "encoder.layers.6.conv.down_conv.bias": "model-00003-of-00003.safetensors",
220
+ "encoder.layers.6.conv.down_conv.weight": "model-00003-of-00003.safetensors",
221
+ "encoder.layers.6.conv.norm.bias": "model-00003-of-00003.safetensors",
222
+ "encoder.layers.6.conv.norm.weight": "model-00003-of-00003.safetensors",
223
+ "encoder.layers.6.conv.up_conv.bias": "model-00003-of-00003.safetensors",
224
+ "encoder.layers.6.conv.up_conv.weight": "model-00003-of-00003.safetensors",
225
+ "encoder.layers.6.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
226
+ "encoder.layers.6.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
227
+ "encoder.layers.6.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
228
+ "encoder.layers.6.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
229
+ "encoder.layers.6.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
230
+ "encoder.layers.6.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
231
+ "encoder.layers.6.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
232
+ "encoder.layers.6.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
233
+ "encoder.layers.6.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
234
+ "encoder.layers.6.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
235
+ "encoder.layers.6.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
236
+ "encoder.layers.6.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "encoder.layers.6.post_norm.bias": "model-00003-of-00003.safetensors",
238
+ "encoder.layers.6.post_norm.weight": "model-00003-of-00003.safetensors",
239
+ "encoder.layers.7.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
240
+ "encoder.layers.7.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
241
+ "encoder.layers.7.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
242
+ "encoder.layers.7.attn.to_kv.weight": "model-00003-of-00003.safetensors",
243
+ "encoder.layers.7.attn.to_out.bias": "model-00003-of-00003.safetensors",
244
+ "encoder.layers.7.attn.to_out.weight": "model-00003-of-00003.safetensors",
245
+ "encoder.layers.7.attn.to_q.weight": "model-00003-of-00003.safetensors",
246
+ "encoder.layers.7.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
247
+ "encoder.layers.7.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
248
+ "encoder.layers.7.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
249
+ "encoder.layers.7.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
250
+ "encoder.layers.7.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
251
+ "encoder.layers.7.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
252
+ "encoder.layers.7.conv.down_conv.bias": "model-00003-of-00003.safetensors",
253
+ "encoder.layers.7.conv.down_conv.weight": "model-00003-of-00003.safetensors",
254
+ "encoder.layers.7.conv.norm.bias": "model-00003-of-00003.safetensors",
255
+ "encoder.layers.7.conv.norm.weight": "model-00003-of-00003.safetensors",
256
+ "encoder.layers.7.conv.up_conv.bias": "model-00003-of-00003.safetensors",
257
+ "encoder.layers.7.conv.up_conv.weight": "model-00003-of-00003.safetensors",
258
+ "encoder.layers.7.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
259
+ "encoder.layers.7.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
260
+ "encoder.layers.7.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
261
+ "encoder.layers.7.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
262
+ "encoder.layers.7.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
263
+ "encoder.layers.7.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
264
+ "encoder.layers.7.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
265
+ "encoder.layers.7.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
266
+ "encoder.layers.7.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
267
+ "encoder.layers.7.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
268
+ "encoder.layers.7.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
269
+ "encoder.layers.7.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
270
+ "encoder.layers.7.post_norm.bias": "model-00003-of-00003.safetensors",
271
+ "encoder.layers.7.post_norm.weight": "model-00003-of-00003.safetensors",
272
+ "encoder.layers.8.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
273
+ "encoder.layers.8.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
274
+ "encoder.layers.8.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
275
+ "encoder.layers.8.attn.to_kv.weight": "model-00003-of-00003.safetensors",
276
+ "encoder.layers.8.attn.to_out.bias": "model-00003-of-00003.safetensors",
277
+ "encoder.layers.8.attn.to_out.weight": "model-00003-of-00003.safetensors",
278
+ "encoder.layers.8.attn.to_q.weight": "model-00003-of-00003.safetensors",
279
+ "encoder.layers.8.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
280
+ "encoder.layers.8.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
281
+ "encoder.layers.8.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
282
+ "encoder.layers.8.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
283
+ "encoder.layers.8.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
284
+ "encoder.layers.8.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
285
+ "encoder.layers.8.conv.down_conv.bias": "model-00003-of-00003.safetensors",
286
+ "encoder.layers.8.conv.down_conv.weight": "model-00003-of-00003.safetensors",
287
+ "encoder.layers.8.conv.norm.bias": "model-00003-of-00003.safetensors",
288
+ "encoder.layers.8.conv.norm.weight": "model-00003-of-00003.safetensors",
289
+ "encoder.layers.8.conv.up_conv.bias": "model-00003-of-00003.safetensors",
290
+ "encoder.layers.8.conv.up_conv.weight": "model-00003-of-00003.safetensors",
291
+ "encoder.layers.8.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
292
+ "encoder.layers.8.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
293
+ "encoder.layers.8.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
294
+ "encoder.layers.8.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
295
+ "encoder.layers.8.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
296
+ "encoder.layers.8.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
297
+ "encoder.layers.8.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
298
+ "encoder.layers.8.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
299
+ "encoder.layers.8.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
300
+ "encoder.layers.8.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
301
+ "encoder.layers.8.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
302
+ "encoder.layers.8.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
303
+ "encoder.layers.8.post_norm.bias": "model-00003-of-00003.safetensors",
304
+ "encoder.layers.8.post_norm.weight": "model-00003-of-00003.safetensors",
305
+ "encoder.layers.9.attn.pre_norm.bias": "model-00003-of-00003.safetensors",
306
+ "encoder.layers.9.attn.pre_norm.weight": "model-00003-of-00003.safetensors",
307
+ "encoder.layers.9.attn.rel_pos_emb.weight": "model-00003-of-00003.safetensors",
308
+ "encoder.layers.9.attn.to_kv.weight": "model-00003-of-00003.safetensors",
309
+ "encoder.layers.9.attn.to_out.bias": "model-00003-of-00003.safetensors",
310
+ "encoder.layers.9.attn.to_out.weight": "model-00003-of-00003.safetensors",
311
+ "encoder.layers.9.attn.to_q.weight": "model-00003-of-00003.safetensors",
312
+ "encoder.layers.9.conv.batch_norm.bias": "model-00003-of-00003.safetensors",
313
+ "encoder.layers.9.conv.batch_norm.num_batches_tracked": "model-00003-of-00003.safetensors",
314
+ "encoder.layers.9.conv.batch_norm.running_mean": "model-00003-of-00003.safetensors",
315
+ "encoder.layers.9.conv.batch_norm.running_var": "model-00003-of-00003.safetensors",
316
+ "encoder.layers.9.conv.batch_norm.weight": "model-00003-of-00003.safetensors",
317
+ "encoder.layers.9.conv.depth_conv.conv.weight": "model-00003-of-00003.safetensors",
318
+ "encoder.layers.9.conv.down_conv.bias": "model-00003-of-00003.safetensors",
319
+ "encoder.layers.9.conv.down_conv.weight": "model-00003-of-00003.safetensors",
320
+ "encoder.layers.9.conv.norm.bias": "model-00003-of-00003.safetensors",
321
+ "encoder.layers.9.conv.norm.weight": "model-00003-of-00003.safetensors",
322
+ "encoder.layers.9.conv.up_conv.bias": "model-00003-of-00003.safetensors",
323
+ "encoder.layers.9.conv.up_conv.weight": "model-00003-of-00003.safetensors",
324
+ "encoder.layers.9.ff1.down_proj.bias": "model-00003-of-00003.safetensors",
325
+ "encoder.layers.9.ff1.down_proj.weight": "model-00003-of-00003.safetensors",
326
+ "encoder.layers.9.ff1.pre_norm.bias": "model-00003-of-00003.safetensors",
327
+ "encoder.layers.9.ff1.pre_norm.weight": "model-00003-of-00003.safetensors",
328
+ "encoder.layers.9.ff1.up_proj.bias": "model-00003-of-00003.safetensors",
329
+ "encoder.layers.9.ff1.up_proj.weight": "model-00003-of-00003.safetensors",
330
+ "encoder.layers.9.ff2.down_proj.bias": "model-00003-of-00003.safetensors",
331
+ "encoder.layers.9.ff2.down_proj.weight": "model-00003-of-00003.safetensors",
332
+ "encoder.layers.9.ff2.pre_norm.bias": "model-00003-of-00003.safetensors",
333
+ "encoder.layers.9.ff2.pre_norm.weight": "model-00003-of-00003.safetensors",
334
+ "encoder.layers.9.ff2.up_proj.bias": "model-00003-of-00003.safetensors",
335
+ "encoder.layers.9.ff2.up_proj.weight": "model-00003-of-00003.safetensors",
336
+ "encoder.layers.9.post_norm.bias": "model-00003-of-00003.safetensors",
337
+ "encoder.layers.9.post_norm.weight": "model-00003-of-00003.safetensors",
338
+ "encoder.out.bias": "model-00003-of-00003.safetensors",
339
+ "encoder.out.weight": "model-00003-of-00003.safetensors",
340
+ "encoder.out_mid.bias": "model-00003-of-00003.safetensors",
341
+ "encoder.out_mid.weight": "model-00003-of-00003.safetensors",
342
+ "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
343
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
344
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
345
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
346
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
347
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
348
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
349
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
350
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
351
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
352
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
353
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
354
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
355
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
356
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
357
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
358
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
359
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
360
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
361
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
362
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
363
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
364
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
365
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
366
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
367
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
368
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
369
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
370
+ "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
371
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
372
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
373
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
374
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
375
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
376
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
377
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
378
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
379
+ "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
380
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
381
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
382
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
383
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
384
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
385
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
386
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
387
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
388
+ "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
389
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
390
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
391
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
392
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
393
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
394
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
395
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
396
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
397
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
398
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
399
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
400
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
401
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
402
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
403
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
404
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
405
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
406
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
407
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
408
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
409
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
410
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
411
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
412
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
413
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
414
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
415
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
416
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
417
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
418
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
419
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
420
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
421
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
422
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
423
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
424
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
425
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
426
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
427
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
428
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
429
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
430
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
431
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
432
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
433
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
434
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
435
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
436
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
437
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
438
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
439
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
440
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
441
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
442
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
443
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
444
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
445
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
446
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
447
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
448
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
449
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
450
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
451
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
452
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
453
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
454
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
455
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
456
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
457
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
458
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
459
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
460
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
461
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
462
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
463
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
464
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
465
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
466
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
467
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
468
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
469
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
470
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
471
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
472
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
473
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
474
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
475
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
476
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
477
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
478
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
479
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
480
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
481
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
482
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
483
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
484
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
485
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
486
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
487
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
488
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
489
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
490
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
491
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
492
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
493
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
494
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
495
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
496
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
497
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
498
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
499
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
500
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
501
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
502
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
503
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
504
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
505
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
506
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
507
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
508
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
509
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
510
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
511
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
512
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
513
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
514
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
515
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
516
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
517
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
518
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
519
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
520
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
521
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
522
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
523
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
524
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
525
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
526
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
527
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
528
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
529
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
530
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
531
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
532
+ "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
533
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
534
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
535
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
536
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
537
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
538
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
539
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
540
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
541
+ "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
542
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
543
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
544
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
545
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
546
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
547
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
548
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
549
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
550
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
551
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
552
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
553
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
554
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
555
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
556
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
557
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
558
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
559
+ "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
560
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
561
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
562
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
563
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
564
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
565
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
566
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
567
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
568
+ "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
569
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
570
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
571
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
572
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
573
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
574
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
575
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
576
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
577
+ "language_model.model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
578
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
579
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
580
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
581
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
582
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
583
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
584
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
585
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
586
+ "language_model.model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
587
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
588
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
589
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
590
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
591
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
592
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
593
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
594
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
595
+ "language_model.model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
596
+ "language_model.model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
597
+ "language_model.model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
598
+ "language_model.model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
599
+ "language_model.model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
600
+ "language_model.model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
601
+ "language_model.model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
602
+ "language_model.model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
603
+ "language_model.model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
604
+ "language_model.model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
605
+ "language_model.model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
606
+ "language_model.model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
607
+ "language_model.model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
608
+ "language_model.model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
609
+ "language_model.model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
610
+ "language_model.model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
611
+ "language_model.model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
612
+ "language_model.model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
613
+ "language_model.model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
614
+ "language_model.model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
615
+ "language_model.model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
616
+ "language_model.model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
617
+ "language_model.model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
618
+ "language_model.model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
619
+ "language_model.model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
620
+ "language_model.model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
621
+ "language_model.model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
622
+ "language_model.model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
623
+ "language_model.model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
624
+ "language_model.model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
625
+ "language_model.model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
626
+ "language_model.model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
627
+ "language_model.model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
628
+ "language_model.model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
629
+ "language_model.model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
630
+ "language_model.model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
631
+ "language_model.model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
632
+ "language_model.model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
633
+ "language_model.model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
634
+ "language_model.model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
635
+ "language_model.model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
636
+ "language_model.model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
637
+ "language_model.model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
638
+ "language_model.model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
639
+ "language_model.model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
640
+ "language_model.model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
641
+ "language_model.model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
642
+ "language_model.model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
643
+ "language_model.model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
644
+ "language_model.model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
645
+ "language_model.model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
646
+ "language_model.model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
647
+ "language_model.model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
648
+ "language_model.model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
649
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
650
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
651
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
652
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
653
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
654
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
655
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
656
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
657
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
658
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
659
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
660
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
661
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
662
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
663
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
664
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
665
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
666
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
667
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
668
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
669
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
670
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
671
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
672
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
673
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
674
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
675
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
676
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
677
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
678
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
679
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
680
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
681
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
682
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
683
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
684
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
685
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
686
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
687
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
688
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
689
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
690
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
691
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
692
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
693
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
694
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
695
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
696
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
697
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
698
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
699
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
700
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
701
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
702
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
703
+ "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
704
+ "projector.linear.bias": "model-00003-of-00003.safetensors",
705
+ "projector.linear.weight": "model-00003-of-00003.safetensors",
706
+ "projector.qformer.encoder.layer.0.attention.attention.key.bias": "model-00003-of-00003.safetensors",
707
+ "projector.qformer.encoder.layer.0.attention.attention.key.weight": "model-00003-of-00003.safetensors",
708
+ "projector.qformer.encoder.layer.0.attention.attention.query.bias": "model-00003-of-00003.safetensors",
709
+ "projector.qformer.encoder.layer.0.attention.attention.query.weight": "model-00003-of-00003.safetensors",
710
+ "projector.qformer.encoder.layer.0.attention.attention.value.bias": "model-00003-of-00003.safetensors",
711
+ "projector.qformer.encoder.layer.0.attention.attention.value.weight": "model-00003-of-00003.safetensors",
712
+ "projector.qformer.encoder.layer.0.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
713
+ "projector.qformer.encoder.layer.0.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
714
+ "projector.qformer.encoder.layer.0.attention.output.dense.bias": "model-00003-of-00003.safetensors",
715
+ "projector.qformer.encoder.layer.0.attention.output.dense.weight": "model-00003-of-00003.safetensors",
716
+ "projector.qformer.encoder.layer.0.crossattention.attention.key.bias": "model-00003-of-00003.safetensors",
717
+ "projector.qformer.encoder.layer.0.crossattention.attention.key.weight": "model-00003-of-00003.safetensors",
718
+ "projector.qformer.encoder.layer.0.crossattention.attention.query.bias": "model-00003-of-00003.safetensors",
719
+ "projector.qformer.encoder.layer.0.crossattention.attention.query.weight": "model-00003-of-00003.safetensors",
720
+ "projector.qformer.encoder.layer.0.crossattention.attention.value.bias": "model-00003-of-00003.safetensors",
721
+ "projector.qformer.encoder.layer.0.crossattention.attention.value.weight": "model-00003-of-00003.safetensors",
722
+ "projector.qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
723
+ "projector.qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
724
+ "projector.qformer.encoder.layer.0.crossattention.output.dense.bias": "model-00003-of-00003.safetensors",
725
+ "projector.qformer.encoder.layer.0.crossattention.output.dense.weight": "model-00003-of-00003.safetensors",
726
+ "projector.qformer.encoder.layer.0.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
727
+ "projector.qformer.encoder.layer.0.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
728
+ "projector.qformer.encoder.layer.0.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
729
+ "projector.qformer.encoder.layer.0.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
730
+ "projector.qformer.encoder.layer.0.output_query.dense.bias": "model-00003-of-00003.safetensors",
731
+ "projector.qformer.encoder.layer.0.output_query.dense.weight": "model-00003-of-00003.safetensors",
732
+ "projector.qformer.encoder.layer.1.attention.attention.key.bias": "model-00003-of-00003.safetensors",
733
+ "projector.qformer.encoder.layer.1.attention.attention.key.weight": "model-00003-of-00003.safetensors",
734
+ "projector.qformer.encoder.layer.1.attention.attention.query.bias": "model-00003-of-00003.safetensors",
735
+ "projector.qformer.encoder.layer.1.attention.attention.query.weight": "model-00003-of-00003.safetensors",
736
+ "projector.qformer.encoder.layer.1.attention.attention.value.bias": "model-00003-of-00003.safetensors",
737
+ "projector.qformer.encoder.layer.1.attention.attention.value.weight": "model-00003-of-00003.safetensors",
738
+ "projector.qformer.encoder.layer.1.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
739
+ "projector.qformer.encoder.layer.1.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
740
+ "projector.qformer.encoder.layer.1.attention.output.dense.bias": "model-00003-of-00003.safetensors",
741
+ "projector.qformer.encoder.layer.1.attention.output.dense.weight": "model-00003-of-00003.safetensors",
742
+ "projector.qformer.encoder.layer.1.crossattention.attention.key.bias": "model-00003-of-00003.safetensors",
743
+ "projector.qformer.encoder.layer.1.crossattention.attention.key.weight": "model-00003-of-00003.safetensors",
744
+ "projector.qformer.encoder.layer.1.crossattention.attention.query.bias": "model-00003-of-00003.safetensors",
745
+ "projector.qformer.encoder.layer.1.crossattention.attention.query.weight": "model-00003-of-00003.safetensors",
746
+ "projector.qformer.encoder.layer.1.crossattention.attention.value.bias": "model-00003-of-00003.safetensors",
747
+ "projector.qformer.encoder.layer.1.crossattention.attention.value.weight": "model-00003-of-00003.safetensors",
748
+ "projector.qformer.encoder.layer.1.crossattention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
749
+ "projector.qformer.encoder.layer.1.crossattention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
750
+ "projector.qformer.encoder.layer.1.crossattention.output.dense.bias": "model-00003-of-00003.safetensors",
751
+ "projector.qformer.encoder.layer.1.crossattention.output.dense.weight": "model-00003-of-00003.safetensors",
752
+ "projector.qformer.encoder.layer.1.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
753
+ "projector.qformer.encoder.layer.1.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
754
+ "projector.qformer.encoder.layer.1.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
755
+ "projector.qformer.encoder.layer.1.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
756
+ "projector.qformer.encoder.layer.1.output_query.dense.bias": "model-00003-of-00003.safetensors",
757
+ "projector.qformer.encoder.layer.1.output_query.dense.weight": "model-00003-of-00003.safetensors",
758
+ "projector.qformer.layernorm.bias": "model-00003-of-00003.safetensors",
759
+ "projector.qformer.layernorm.weight": "model-00003-of-00003.safetensors",
760
+ "projector.query": "model-00003-of-00003.safetensors"
761
+ }
762
+ }
preprocessor_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|start_of_role|>",
4
+ "<|end_of_role|>",
5
+ "<|tool_call|>",
6
+ "<|start_of_cite|>",
7
+ "<|end_of_cite|>",
8
+ "<|start_of_plugin|>",
9
+ "<|end_of_plugin|>"
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|end_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|end_of_text|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<|end_of_text|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|end_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<fim_prefix>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<fim_middle>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<fim_suffix>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<fim_pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<filename>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<gh_stars>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<issue_start>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<issue_comment>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<issue_closed>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<jupyter_start>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<jupyter_text>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<jupyter_code>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<jupyter_output>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<empty_output>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<commit_before>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<commit_msg>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<commit_after>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<reponame>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "49152": {
158
+ "content": "<|start_of_role|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "49153": {
166
+ "content": "<|end_of_role|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "49154": {
174
+ "content": "<|tool_call|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "49155": {
182
+ "content": "<|start_of_cite|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "49156": {
190
+ "content": "<|end_of_cite|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "49157": {
198
+ "content": "<|start_of_plugin|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "49158": {
206
+ "content": "<|end_of_plugin|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "49159": {
214
+ "content": "<|audio|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ }
221
+ },
222
+ "additional_special_tokens": [
223
+ "<|start_of_role|>",
224
+ "<|end_of_role|>",
225
+ "<|tool_call|>",
226
+ "<|start_of_cite|>",
227
+ "<|end_of_cite|>",
228
+ "<|start_of_plugin|>",
229
+ "<|end_of_plugin|>"
230
+ ],
231
+ "bos_token": "<|end_of_text|>",
232
+ "clean_up_tokenization_spaces": true,
233
+ "eos_token": "<|end_of_text|>",
234
+ "errors": "replace",
235
+ "extra_special_tokens": {},
236
+ "model_max_length": 9223372036854775807,
237
+ "pad_token": "<|end_of_text|>",
238
+ "padding_side": "left",
239
+ "tokenizer_class": "GPT2Tokenizer",
240
+ "unk_token": "<|end_of_text|>",
241
+ "vocab_size": 49152
242
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff