zyyang45 commited on
Commit
b6987aa
·
verified ·
1 Parent(s): 9df311a

Add files using upload-large-folder tool

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '
2
+
3
+ ' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<|User|>' + content + '<|Assistant|>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '
4
+ ' + '```json' + '
5
+ ' + tool['function']['arguments'] + '
6
+ ' + '```' + '<|tool▁call▁end|>'}}{%- else %}{{content + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '
7
+ ' + '```json' + '
8
+ ' + tool['function']['arguments'] + '
9
+ ' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'
10
+ ' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '
11
+ ' + '```json' + '
12
+ ' + tool['function']['arguments'] + '
13
+ ' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- endfor %}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + content + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
14
+ <|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_deepseek.DeepseekV3Config",
9
+ "AutoModel": "modeling_deepseek.DeepseekV3Model",
10
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
11
+ },
12
+ "bos_token_id": 0,
13
+ "dfloat_config": {
14
+ "bytes_per_thread": 8,
15
+ "threads_per_block": 512,
16
+ "version": "0.2.0"
17
+ },
18
+ "eos_token_id": 1,
19
+ "ep_size": 1,
20
+ "first_k_dense_replace": 3,
21
+ "head_dim": 64,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 7168,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 18432,
26
+ "kv_lora_rank": 512,
27
+ "max_position_embeddings": 163840,
28
+ "model_type": "deepseek_v3",
29
+ "moe_intermediate_size": 2048,
30
+ "moe_layer_freq": 1,
31
+ "n_group": 8,
32
+ "n_routed_experts": 256,
33
+ "n_shared_experts": 1,
34
+ "norm_topk_prob": true,
35
+ "num_attention_heads": 128,
36
+ "num_experts_per_tok": 8,
37
+ "num_hidden_layers": 61,
38
+ "num_key_value_heads": 128,
39
+ "num_nextn_predict_layers": 1,
40
+ "pretraining_tp": 1,
41
+ "q_lora_rank": 1536,
42
+ "qk_head_dim": 192,
43
+ "qk_nope_head_dim": 128,
44
+ "qk_rope_head_dim": 64,
45
+ "quantization_config": {
46
+ "activation_scheme": "dynamic",
47
+ "modules_to_not_convert": null,
48
+ "quant_method": "fp8",
49
+ "weight_block_size": [
50
+ 128,
51
+ 128
52
+ ]
53
+ },
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_interleave": true,
56
+ "rope_scaling": {
57
+ "beta_fast": 32.0,
58
+ "beta_slow": 1.0,
59
+ "factor": 40.0,
60
+ "mscale": 1.0,
61
+ "mscale_all_dim": 1.0,
62
+ "original_max_position_embeddings": 4096,
63
+ "rope_type": "yarn",
64
+ "type": "yarn"
65
+ },
66
+ "rope_theta": 10000,
67
+ "routed_scaling_factor": 2.5,
68
+ "scoring_func": "sigmoid",
69
+ "tie_word_embeddings": false,
70
+ "topk_group": 4,
71
+ "topk_method": "noaux_tc",
72
+ "torch_dtype": "bfloat16",
73
+ "transformers_version": "4.55.0",
74
+ "use_cache": true,
75
+ "v_head_dim": 128,
76
+ "vocab_size": 129280
77
+ }
entropy.csv ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "do_sample": true,
5
+ "eos_token_id": 1,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.55.0"
9
+ }
model-00001-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a21d758a08598f49d1991620463879d1c8a62d41e5fed903af371c01e3ed933
3
+ size 4988393542
model-00002-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af6ff67322e93ad5b4a4ace3db971bd98823daf2a00c784d76620550bbd88b09
3
+ size 4992303997
model-00003-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e60c8135a8aa1bc9415149d339f638274ed2a3fecda1764d75d828d03c4c86
3
+ size 4983485157
model-00004-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b41b7ead1658ccbe15888b68a14fc32fc64ca8b7481c2eac6f4abfa77600cf
3
+ size 4984728472
model-00005-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a7c9b593a5750015be9ba3e86070b6c12e718a433dd8ab193d785a8d2d9b0a
3
+ size 4984619059
model-00006-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581d50c6103cb7d9f5ed769a32a2e4c4bbe4ab22ca4152e1b44ce0f237944eb0
3
+ size 4985034600
model-00007-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79718d4e739c534aca45f45450f5b7bf3007cf3fa848fc832619e6fe3e99015d
3
+ size 4997638988
model-00008-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b666bd2bc27b7914538e492ba37ca844ab4b897c2944f0752059c69d751670
3
+ size 4988695944
model-00009-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acaec70ffeca173144a5d97286dbb8ceff545007321028f9df5a42705c7f43fe
3
+ size 4986203654
model-00010-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60409156c99867db9ad64e4e3551e0f055f1e4b72ff0c16503769cecae70977
3
+ size 4979872314
model-00011-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3905c3f5c12887ccc415e24c51f84708aeb6b362b13d978edb07e96b2d3b86a
3
+ size 4984203407
model-00012-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16891b32df020ba5031f398bdc9effc2f67f2c12e6656c60632f3ea84b536229
3
+ size 4995669412
model-00013-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def3b27719f576a1ac4506369af2e948c7784cf364557abdf5187c0196362c3a
3
+ size 4999324741
model-00014-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dae8c03ee8b7633ea1d88b5f4b99ea3feece3aafcf2140deb7d61c9b2100744
3
+ size 4986284380
model-00015-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991202fdb5404be335b6fb39dee21bee0905d278fe5416b7d0cce3dabca5b078
3
+ size 4998970632
model-00016-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defeec14d3179924804f5ef434c4033fb9a44329bc47a33f699c722cdd247946
3
+ size 4993158840
model-00017-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3542f5792db1673dec905444782bebe481dbd63e5bbee58ec12d6478994f6c32
3
+ size 4998405120
model-00018-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579ae20c6d3cc7fd6458e2b982c4c020c7a416328390254ba1b4d4baf95fa375
3
+ size 4988507191
model-00019-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04327ac92684b34bfc6c560962045e8459ec198a1036f34784ddbb6364fde90
3
+ size 4985718619
model-00020-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25bc162cb50fb45d3010ff0babee0ced207a7f82579886c291d4670a1ab007eb
3
+ size 4992249769
model-00021-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f65d94c06506de5a3456f5aae2b5c8f62e7022c8676be65111c42a5cfc7e08
3
+ size 4994306315
model-00022-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1eca17a2f32523c07778e25c568d0b5ae43ead35e86fe59b4992942c0eca3d1
3
+ size 4990516291
model-00023-of-00115.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73030a89190c0b4abab2839c1628604a0695c658c73ceae767c9230baabdd3c9
3
+ size 4992150521
model_size.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ fp8_blocks,rest,total
2
+ 623.1919728964567,3.6522932052612305,626.844266101718
3
+ 530.2582089528441,3.6522932052612305,533.9105021581054