farbodtavakkoli commited on
Commit
037bcfd
·
verified ·
1 Parent(s): 3ea74a4

Upload artifacts for Open_Telco_LLM_32B_IT

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 -%}{%- if not has_system -%}{{- '<|im_start|>system
2
+ You are Olmo, a helpful AI assistant built by Ai2. Your date cutoff is December 2024, and your model weights are available at https://huggingface.co/allenai. ' -}}{%- if tools is none or (tools | length) == 0 -%}{{- 'You do not currently have access to any functions. <functions></functions><|im_end|>
3
+ ' -}}{%- else -%}{{- 'You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Do not make assumptions about what values to plug into functions.' -}}{{- '<functions>' -}}{{- tools | tojson -}}{{- '</functions><|im_end|>
4
+ ' -}}{%- endif -%}{%- endif -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{{- '<|im_start|>system
5
+ ' + message['content'] -}}{%- if tools is not none -%}{{- '<functions>' -}}{{- tools | tojson -}}{{- '</functions>' -}}{%- elif message.get('functions', none) is not none -%}{{- ' <functions>' + message['functions'] + '</functions>' -}}{%- endif -%}{{- '<|im_end|>
6
+ ' -}}{%- elif message['role'] == 'user' -%}{{- '<|im_start|>user
7
+ ' + message['content'] + '<|im_end|>
8
+ ' -}}{%- elif message['role'] == 'assistant' -%}{{- '<|im_start|>assistant
9
+ ' -}}{%- if message.get('content', none) is not none -%}{{- message['content'] -}}{%- endif -%}{%- if message.get('function_calls', none) is not none -%}{{- '<function_calls>' + message['function_calls'] + '</function_calls>' -}}{% elif message.get('tool_calls', none) is not none %}{{- '<function_calls>' -}}{%- for tool_call in message['tool_calls'] %}{%- if tool_call is mapping and tool_call.get('function', none) is not none %}{%- set args = tool_call['function']['arguments'] -%}{%- set ns = namespace(arguments_list=[]) -%}{%- for key, value in args.items() -%}{%- set ns.arguments_list = ns.arguments_list + [key ~ '=' ~ (value | tojson)] -%}{%- endfor -%}{%- set arguments = ns.arguments_list | join(', ') -%}{{- tool_call['function']['name'] + '(' + arguments + ')' -}}{%- if not loop.last -%}{{ '
10
+ ' }}{%- endif -%}{% else %}{{- tool_call -}}{%- endif %}{%- endfor %}{{- '</function_calls>' -}}{%- endif -%}{%- if not loop.last -%}{{- '<|im_end|>' + '
11
+ ' -}}{%- else -%}{{- eos_token -}}{%- endif -%}{%- elif message['role'] == 'environment' -%}{{- '<|im_start|>environment
12
+ ' + message['content'] + '<|im_end|>
13
+ ' -}}{%- elif message['role'] == 'tool' -%}{{- '<|im_start|>environment
14
+ ' + message['content'] + '<|im_end|>
15
+ ' -}}{%- endif -%}{%- if loop.last and add_generation_prompt -%}{{- '<|im_start|>assistant\n' -}}{%- endif -%}{%- endfor -%}
config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Olmo3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 100257,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 27648,
14
+ "layer_types": [
15
+ "sliding_attention",
16
+ "sliding_attention",
17
+ "sliding_attention",
18
+ "full_attention",
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "full_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "full_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "full_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "full_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "full_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "full_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "full_attention"
79
+ ],
80
+ "max_position_embeddings": 65536,
81
+ "model_type": "olmo3",
82
+ "num_attention_heads": 40,
83
+ "num_hidden_layers": 64,
84
+ "num_key_value_heads": 8,
85
+ "pad_token_id": 100277,
86
+ "rms_norm_eps": 1e-06,
87
+ "rope_scaling": {
88
+ "attention_factor": 1.2079441541679836,
89
+ "beta_fast": 32,
90
+ "beta_slow": 1,
91
+ "factor": 8.0,
92
+ "original_max_position_embeddings": 8192,
93
+ "rope_type": "yarn"
94
+ },
95
+ "rope_theta": 500000,
96
+ "sliding_window": 4096,
97
+ "tie_word_embeddings": false,
98
+ "transformers_version": "4.57.6",
99
+ "use_cache": false,
100
+ "vocab_size": 100278
101
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 100257
7
+ ],
8
+ "max_new_tokens": 32768,
9
+ "pad_token_id": 100277,
10
+ "temperature": 0.6,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.6"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cb9334321c1c6187d25161500d50da59fd13989f660fc8aaf21b52784cc8f3
3
+ size 4821939691
pytorch_model-00002-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31786520912e1ae1b96af8ee632982440083e95c2f4a22237738dd9f0fc2d958
3
+ size 4466940047
pytorch_model-00003-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e627da78035bb3c315c047a66068c99e889c6ef396fae148d52137d56cc88ffa
3
+ size 4718599559
pytorch_model-00004-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198a103f1769c387108f5f797a6cfd221b64eb233c8284ed71ca055d36a655da
3
+ size 4466940047
pytorch_model-00005-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1fe357d02ad3e38a8cec3447498306a5e510c57bcc1dfb788da05ba3e84748b
3
+ size 4466940047
pytorch_model-00006-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d516b0220b87f1995dbdb695e505e59835236818af8d1544dbee9bc01d48f74
3
+ size 4718599623
pytorch_model-00007-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c86637ceb3827a122dff2b300a74bd4beda21f8749c605d77d1b434695d94b
3
+ size 4466940047
pytorch_model-00008-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8443d3682aa4cce31ece9089c852b46c70c5b26ee23cc1d4bdfc442de14e81b5
3
+ size 4466940047
pytorch_model-00009-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92669c4b4d10287e4acf8a4251c74653c81b0422ddd70d1ce67e681cf262aed2
3
+ size 4718599623
pytorch_model-00010-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4528228f7979434518e98c350c9ea6705b16c3f0f39daa593b4cc7191c984945
3
+ size 4466940047
pytorch_model-00011-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2355ff0dfd5ea2cc73502d7bbfb51ea5370b4ba7aeb08ff40844eb6881a35d
3
+ size 4466940047
pytorch_model-00012-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a393b64bcd76285b8548c6a24936ea77f98280cb49dcb6f61443320037d6f736
3
+ size 4718599623
pytorch_model-00013-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c9bb9bb35735b00e85a40aa6a6e8fb02f325a5309a6fc9b029f579efaaa105
3
+ size 4466940047
pytorch_model-00014-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7abe7cbe0d5b8f2531129f44c84a1ec342e73b47c768145c33a127f644ce9a53
3
+ size 4466940047
pytorch_model-00015-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e378ab2201f2bbb54b467aed91b41a2eb6e8e4f5a020cf911e702a31d67fa78
3
+ size 4718599623
pytorch_model-00016-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9caa3716fb4f4330bd5edde078829eb8cf2c53b7399d11daa922db17ed1102b3
3
+ size 4466940047
pytorch_model-00017-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c524b5d44041474a66e7efb6f8da3a1fbd469e2304dea2ae06632eaac1d1e2a
3
+ size 4466940047
pytorch_model-00018-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5838d3389178f0a053886d2689eba9ec70042220623c205d637a4d0253459bab
3
+ size 4718599623
pytorch_model-00019-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99524ed1df952ed6056e65a82d967cb1b3b518e1212b3686aa6eeb65afb37471
3
+ size 4466940047
pytorch_model-00020-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31cea200a5222e04103be7e810a69c5a5783a12445b04752ea12aff4e2f66242
3
+ size 4466940047
pytorch_model-00021-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119d4a590951208fbec8112e11436b922f77c4e45e4e1c59f4428f477770e3f8
3
+ size 4718599623
pytorch_model-00022-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd57b497d3ee500d1b75ef9a5be808572a609463ff8fd604a60d70e0c2f0db5
3
+ size 4466940047
pytorch_model-00023-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e7d9aa2d83569e084ffde5d5704096b08b93ef08d79cee07ec552f54006634
3
+ size 4466940047
pytorch_model-00024-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9336d52e4015285d23e3ee631278b714688c0a892f8c5a23cbd837a9a0fae3cd
3
+ size 4718599623
pytorch_model-00025-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218834d70444153f4fa99a0998939c65381d8786235ec9afef8a0de8f1d86429
3
+ size 4466940047
pytorch_model-00026-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704908f0300c3272a26c99447f8c5d6551759ba4b987eff3c3db52f12c3127f7
3
+ size 4466940047
pytorch_model-00027-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64b37ca0f762797f30fddd45f6b125228faf8b1d203c051925510477849e246
3
+ size 4718599623
pytorch_model-00028-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5067d43a79b1271f33317b67e62df0dbceb40dafe063d65ef7544eede75341
3
+ size 3649049173
pytorch_model-00029-of-00029.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bba24484c46b50368615223d02dcefef6bb5a30ee342a7198f6074fa81af295
3
+ size 2057996067
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,714 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 128934088704
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00029-of-00029.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00029.bin",
8
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
9
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
10
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
11
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
12
+ "model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
13
+ "model.layers.0.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
14
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
15
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
16
+ "model.layers.0.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
17
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
18
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
23
+ "model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
24
+ "model.layers.1.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
25
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
26
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
27
+ "model.layers.1.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
28
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
29
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
30
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
31
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
32
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
33
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
34
+ "model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
35
+ "model.layers.10.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
36
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
37
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
38
+ "model.layers.10.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
39
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
40
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
41
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
42
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
43
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
44
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
45
+ "model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
46
+ "model.layers.11.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
47
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
48
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
49
+ "model.layers.11.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
50
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
51
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
52
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
53
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
54
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
55
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
56
+ "model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
57
+ "model.layers.12.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
58
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
59
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
60
+ "model.layers.12.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
61
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
62
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
63
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
64
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
65
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
66
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
67
+ "model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
68
+ "model.layers.13.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
69
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
70
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
71
+ "model.layers.13.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
72
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
73
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
74
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
75
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
76
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
77
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
78
+ "model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
79
+ "model.layers.14.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
80
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
81
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
82
+ "model.layers.14.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
83
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
84
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
85
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
86
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
87
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
88
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
89
+ "model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
90
+ "model.layers.15.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
91
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
92
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
93
+ "model.layers.15.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
94
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
95
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
96
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
97
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
98
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
99
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
100
+ "model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
101
+ "model.layers.16.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
102
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
103
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
104
+ "model.layers.16.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
105
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
106
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
107
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
108
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
109
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
110
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
111
+ "model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
112
+ "model.layers.17.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
113
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
114
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
115
+ "model.layers.17.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
116
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
117
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
118
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
119
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
120
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
121
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
122
+ "model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
123
+ "model.layers.18.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
124
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
125
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
126
+ "model.layers.18.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
127
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
128
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
129
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
130
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
131
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
132
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
133
+ "model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
134
+ "model.layers.19.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
135
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
136
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
137
+ "model.layers.19.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
138
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
139
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
140
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
141
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
142
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
143
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
144
+ "model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
145
+ "model.layers.2.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
146
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
147
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
148
+ "model.layers.2.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
149
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
150
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
151
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
152
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
153
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
154
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
155
+ "model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
156
+ "model.layers.20.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
157
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
158
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
159
+ "model.layers.20.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
160
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
161
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
162
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
163
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
164
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
165
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
166
+ "model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
167
+ "model.layers.21.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
168
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
169
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
170
+ "model.layers.21.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
171
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
172
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
173
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
174
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
175
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
176
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
177
+ "model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
178
+ "model.layers.22.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
179
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
180
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
181
+ "model.layers.22.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
182
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
183
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
184
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
185
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
186
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
187
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
188
+ "model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
189
+ "model.layers.23.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
190
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
191
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
192
+ "model.layers.23.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
193
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
194
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
195
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
196
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
197
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
198
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
199
+ "model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
200
+ "model.layers.24.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
201
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
202
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
203
+ "model.layers.24.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
204
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
205
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
206
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
207
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
208
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
209
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
210
+ "model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
211
+ "model.layers.25.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
212
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
213
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
214
+ "model.layers.25.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
215
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
216
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
217
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
218
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
219
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
220
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
221
+ "model.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
222
+ "model.layers.26.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
223
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
224
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
225
+ "model.layers.26.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
226
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
227
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
228
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
229
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
230
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
231
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
232
+ "model.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
233
+ "model.layers.27.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
234
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
235
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
236
+ "model.layers.27.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
237
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
238
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
239
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
240
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
241
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
242
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
243
+ "model.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
244
+ "model.layers.28.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
245
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
246
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
247
+ "model.layers.28.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
248
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
249
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
250
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
251
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
252
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
253
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
254
+ "model.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
255
+ "model.layers.29.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
256
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
257
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
258
+ "model.layers.29.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
259
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
260
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
261
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
262
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
263
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
264
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
265
+ "model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
266
+ "model.layers.3.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
267
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
268
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
269
+ "model.layers.3.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
270
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
271
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
272
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
273
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
274
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
275
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
276
+ "model.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
277
+ "model.layers.30.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
278
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
279
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
280
+ "model.layers.30.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
281
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
282
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
283
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
284
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
285
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
286
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
287
+ "model.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
288
+ "model.layers.31.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
289
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
290
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
291
+ "model.layers.31.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
292
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
293
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
294
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
295
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
296
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
297
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
298
+ "model.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
299
+ "model.layers.32.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
300
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
301
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
302
+ "model.layers.32.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
303
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
304
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
305
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
306
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
307
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
308
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
309
+ "model.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
310
+ "model.layers.33.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
311
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
312
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
313
+ "model.layers.33.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
314
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
315
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
316
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
317
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
318
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
319
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
320
+ "model.layers.34.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
321
+ "model.layers.34.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
322
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
323
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
324
+ "model.layers.34.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
325
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
326
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
327
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
328
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
329
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
330
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
331
+ "model.layers.35.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
332
+ "model.layers.35.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
333
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
334
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
335
+ "model.layers.35.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
336
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
337
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
338
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
339
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
340
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
341
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
342
+ "model.layers.36.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
343
+ "model.layers.36.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
344
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
345
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
346
+ "model.layers.36.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
347
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
348
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
349
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
350
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
351
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
352
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
353
+ "model.layers.37.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
354
+ "model.layers.37.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
355
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
356
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
357
+ "model.layers.37.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
358
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
359
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
360
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
361
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
362
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
363
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
364
+ "model.layers.38.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
365
+ "model.layers.38.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
366
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
367
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
368
+ "model.layers.38.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
369
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
370
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
371
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
372
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
373
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
374
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
375
+ "model.layers.39.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
376
+ "model.layers.39.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
377
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
378
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
379
+ "model.layers.39.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
380
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
381
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
382
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
383
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
384
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
385
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
386
+ "model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
387
+ "model.layers.4.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
388
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
389
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
390
+ "model.layers.4.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
391
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
392
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
393
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
394
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
395
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
396
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
397
+ "model.layers.40.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
398
+ "model.layers.40.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
399
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
400
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
401
+ "model.layers.40.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
402
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
403
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
404
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
405
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
406
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
407
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
408
+ "model.layers.41.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
409
+ "model.layers.41.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
410
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
411
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
412
+ "model.layers.41.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
413
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
414
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
415
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
416
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
417
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
418
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
419
+ "model.layers.42.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
420
+ "model.layers.42.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
421
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
422
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
423
+ "model.layers.42.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
424
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
425
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
426
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
427
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
428
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
429
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
430
+ "model.layers.43.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
431
+ "model.layers.43.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
432
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
433
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
434
+ "model.layers.43.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
435
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
436
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
437
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
438
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
439
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
440
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
441
+ "model.layers.44.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
442
+ "model.layers.44.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
443
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
444
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
445
+ "model.layers.44.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
446
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
447
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
448
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
449
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
450
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
451
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
452
+ "model.layers.45.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
453
+ "model.layers.45.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
454
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
455
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
456
+ "model.layers.45.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
457
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
458
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
459
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
460
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
461
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
462
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
463
+ "model.layers.46.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
464
+ "model.layers.46.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
465
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
466
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
467
+ "model.layers.46.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
468
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
469
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
470
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
471
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
472
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
473
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
474
+ "model.layers.47.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
475
+ "model.layers.47.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
476
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
477
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
478
+ "model.layers.47.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
479
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
480
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
481
+ "model.layers.48.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
482
+ "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
483
+ "model.layers.48.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
484
+ "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
485
+ "model.layers.48.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
486
+ "model.layers.48.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
487
+ "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
488
+ "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
489
+ "model.layers.48.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
490
+ "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
491
+ "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
492
+ "model.layers.49.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
493
+ "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
494
+ "model.layers.49.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
495
+ "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
496
+ "model.layers.49.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
497
+ "model.layers.49.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
498
+ "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
499
+ "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
500
+ "model.layers.49.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
501
+ "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
502
+ "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
503
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
504
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
505
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
506
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
507
+ "model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
508
+ "model.layers.5.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
509
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
510
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
511
+ "model.layers.5.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
512
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
513
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
514
+ "model.layers.50.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
515
+ "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
516
+ "model.layers.50.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
517
+ "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
518
+ "model.layers.50.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
519
+ "model.layers.50.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
520
+ "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
521
+ "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
522
+ "model.layers.50.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
523
+ "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
524
+ "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
525
+ "model.layers.51.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
526
+ "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
527
+ "model.layers.51.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
528
+ "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
529
+ "model.layers.51.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
530
+ "model.layers.51.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
531
+ "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
532
+ "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
533
+ "model.layers.51.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
534
+ "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
535
+ "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
536
+ "model.layers.52.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
537
+ "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
538
+ "model.layers.52.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
539
+ "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
540
+ "model.layers.52.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
541
+ "model.layers.52.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
542
+ "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
543
+ "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
544
+ "model.layers.52.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
545
+ "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
546
+ "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
547
+ "model.layers.53.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
548
+ "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
549
+ "model.layers.53.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
550
+ "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
551
+ "model.layers.53.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
552
+ "model.layers.53.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
553
+ "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
554
+ "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
555
+ "model.layers.53.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
556
+ "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
557
+ "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
558
+ "model.layers.54.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
559
+ "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
560
+ "model.layers.54.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
561
+ "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
562
+ "model.layers.54.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
563
+ "model.layers.54.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
564
+ "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
565
+ "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
566
+ "model.layers.54.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
567
+ "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
568
+ "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
569
+ "model.layers.55.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
570
+ "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
571
+ "model.layers.55.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
572
+ "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
573
+ "model.layers.55.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
574
+ "model.layers.55.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
575
+ "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
576
+ "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
577
+ "model.layers.55.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
578
+ "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
579
+ "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
580
+ "model.layers.56.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
581
+ "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
582
+ "model.layers.56.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
583
+ "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
584
+ "model.layers.56.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
585
+ "model.layers.56.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
586
+ "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
587
+ "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
588
+ "model.layers.56.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
589
+ "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
590
+ "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
591
+ "model.layers.57.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
592
+ "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
593
+ "model.layers.57.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
594
+ "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
595
+ "model.layers.57.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
596
+ "model.layers.57.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
597
+ "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
598
+ "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
599
+ "model.layers.57.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
600
+ "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
601
+ "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
602
+ "model.layers.58.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
603
+ "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
604
+ "model.layers.58.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
605
+ "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
606
+ "model.layers.58.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
607
+ "model.layers.58.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
608
+ "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
609
+ "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
610
+ "model.layers.58.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
611
+ "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
612
+ "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
613
+ "model.layers.59.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
614
+ "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
615
+ "model.layers.59.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
616
+ "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
617
+ "model.layers.59.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
618
+ "model.layers.59.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
619
+ "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
620
+ "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
621
+ "model.layers.59.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
622
+ "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
623
+ "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
624
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
625
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
626
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
627
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
628
+ "model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
629
+ "model.layers.6.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
630
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
631
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
632
+ "model.layers.6.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
633
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
634
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
635
+ "model.layers.60.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
636
+ "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
637
+ "model.layers.60.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
638
+ "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
639
+ "model.layers.60.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
640
+ "model.layers.60.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
641
+ "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
642
+ "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
643
+ "model.layers.60.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
644
+ "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
645
+ "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
646
+ "model.layers.61.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
647
+ "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
648
+ "model.layers.61.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
649
+ "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
650
+ "model.layers.61.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
651
+ "model.layers.61.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
652
+ "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
653
+ "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
654
+ "model.layers.61.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
655
+ "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
656
+ "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
657
+ "model.layers.62.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
658
+ "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
659
+ "model.layers.62.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
660
+ "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
661
+ "model.layers.62.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
662
+ "model.layers.62.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
663
+ "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
664
+ "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
665
+ "model.layers.62.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
666
+ "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
667
+ "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
668
+ "model.layers.63.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
669
+ "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
670
+ "model.layers.63.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
671
+ "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
672
+ "model.layers.63.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
673
+ "model.layers.63.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
674
+ "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
675
+ "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
676
+ "model.layers.63.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
677
+ "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
678
+ "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
679
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
680
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
681
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
682
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
683
+ "model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
684
+ "model.layers.7.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
685
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
686
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
687
+ "model.layers.7.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
688
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
689
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
690
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
691
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
692
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
693
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
694
+ "model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
695
+ "model.layers.8.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
696
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
697
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
698
+ "model.layers.8.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
699
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
700
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
701
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
702
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
703
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
704
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
705
+ "model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00029-of-00029.bin",
706
+ "model.layers.9.self_attn.k_norm.weight": "pytorch_model-00029-of-00029.bin",
707
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
708
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
709
+ "model.layers.9.self_attn.q_norm.weight": "pytorch_model-00029-of-00029.bin",
710
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
711
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
712
+ "model.norm.weight": "pytorch_model-00029-of-00029.bin"
713
+ }
714
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "100256": {
6
+ "content": "<|extra_id_0|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "100257": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "100258": {
22
+ "content": "<|fim_prefix|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "100259": {
30
+ "content": "<|fim_middle|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "100260": {
38
+ "content": "<|fim_suffix|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "100261": {
46
+ "content": "|||PHONE_NUMBER|||",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "100262": {
54
+ "content": "|||EMAIL_ADDRESS|||",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "100263": {
62
+ "content": "|||IP_ADDRESS|||",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "100264": {
70
+ "content": "<|im_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "100265": {
78
+ "content": "<|im_end|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "100266": {
86
+ "content": "<functions>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "100267": {
94
+ "content": "</functions>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "100268": {
102
+ "content": "<function_calls>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "100269": {
110
+ "content": "</function_calls>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "100270": {
118
+ "content": "<|extra_id_1|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "100271": {
126
+ "content": "<|extra_id_2|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "100272": {
134
+ "content": "<|extra_id_3|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "100273": {
142
+ "content": "<|extra_id_4|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "100274": {
150
+ "content": "<|extra_id_5|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "100275": {
158
+ "content": "<|extra_id_6|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "100276": {
166
+ "content": "<|endofprompt|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "100277": {
174
+ "content": "<|pad|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ }
181
+ },
182
+ "bos_token": "<|endoftext|>",
183
+ "clean_up_tokenization_spaces": false,
184
+ "eos_token": "<|endoftext|>",
185
+ "extra_special_tokens": {},
186
+ "model_max_length": 1100,
187
+ "pad_token": "<|pad|>",
188
+ "tokenizer_class": "GPT2Tokenizer",
189
+ "unk_token": "<|endoftext|>"
190
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff