Hugging Face's logo

Orange02
/
OPD-FP8

Model card Files
xet
 Community
Orange02 commited on
Commit
7d907fc
·
verified ·
1 Parent(s): 9f6ccf1

Upload checkpoint global_step_480

Browse files
Files changed (18) hide show
  1. global_step_480/actor/chat_template.jinja +54 -0
  2. global_step_480/actor/config.json +61 -0
  3. global_step_480/actor/extra_state_world_size_4_rank_0.pt +3 -0
  4. global_step_480/actor/extra_state_world_size_4_rank_1.pt +3 -0
  5. global_step_480/actor/extra_state_world_size_4_rank_2.pt +3 -0
  6. global_step_480/actor/extra_state_world_size_4_rank_3.pt +3 -0
  7. global_step_480/actor/generation_config.json +14 -0
  8. global_step_480/actor/model_world_size_4_rank_0.pt +3 -0
  9. global_step_480/actor/model_world_size_4_rank_1.pt +3 -0
  10. global_step_480/actor/model_world_size_4_rank_2.pt +3 -0
  11. global_step_480/actor/model_world_size_4_rank_3.pt +3 -0
  12. global_step_480/actor/optim_world_size_4_rank_0.pt +3 -0
  13. global_step_480/actor/optim_world_size_4_rank_1.pt +3 -0
  14. global_step_480/actor/optim_world_size_4_rank_2.pt +3 -0
  15. global_step_480/actor/optim_world_size_4_rank_3.pt +3 -0
  16. global_step_480/actor/tokenizer.json +3 -0
  17. global_step_480/actor/tokenizer_config.json +19 -0
  18. global_step_480/data.pt +3 -0
global_step_480/actor/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
global_step_480/actor/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 32768,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": 151643,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.6.0",
58
+ "use_cache": true,
59
+ "use_sliding_window": false,
60
+ "vocab_size": 152064
61
+ }
global_step_480/actor/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:099639037960bf4ae8ff8d9fef3230111bdedd8017262f1d9ba188b8eb926bb9
3
+ size 15141
global_step_480/actor/extra_state_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb19216fcb554813ca00e024cf07aea338ec2f68e49ecc8411c7ccb9ae4b6429
3
+ size 15141
global_step_480/actor/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d92468d17275212420aa7c2bbbc9a579df6445d9606d93834d04e56c260e914b
3
+ size 15141
global_step_480/actor/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91e9e5c3957b4efc722f02740b221f718f80b8302536701bd79a4d67c88a296
3
+ size 15077
global_step_480/actor/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "5.6.0"
14
+ }
global_step_480/actor/model_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a132fc88f06329baa9a70ac07c5661dde4d2b4819e21aaba57b4e9c96e76ecd5
3
+ size 7615806095
global_step_480/actor/model_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c10517614e3890588a9e7571c7e89bba0c6437bf44931c9ce7c2aa650c39f94
3
+ size 7615806095
global_step_480/actor/model_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd321a36417c7240d2b0862b8798f029d18b335b2106433c332c3a598bf5607
3
+ size 7615806095
global_step_480/actor/model_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606f1d93dd5a7e467a51d572bdef7a9764f2a1d16c261d8447d3ab52b9378f9c
3
+ size 7615806095
global_step_480/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7914d0021cbb6ab7b76305b86e886ffd9cfd1a24ea8036641d866e86dd40719c
3
+ size 15231260548
global_step_480/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca3918a45b8729f87535c905541cd3ead92f52ee4619bd1df141a5da6800e61
3
+ size 15231260548
global_step_480/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8908e95c62af1a732a2c0673d21a4d7064a4fcf269cd93ab85be03f90782ca9
3
+ size 15231260548
global_step_480/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb366ee5ee48438341430094a9ca03df8d81e893fb82f9da3a03cba61059c88
3
+ size 15231260548
global_step_480/actor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2b7649a086fbb9771cd78ec5b7ffa7069e16a82424a382950fedfa1e057861
3
+ size 11421991
global_step_480/actor/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": true,
9
+ "local_files_only": false,
10
+ "max_length": 2048,
11
+ "model_max_length": 131072,
12
+ "pad_token": "<|endoftext|>",
13
+ "split_special_tokens": false,
14
+ "stride": 0,
15
+ "tokenizer_class": "Qwen2Tokenizer",
16
+ "truncation_side": "right",
17
+ "truncation_strategy": "longest_first",
18
+ "unk_token": null
19
+ }
global_step_480/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a03d56c276836c902946db983cf9968f8cefae8f7d3e0e700c5a30010f2d0cd
3
+ size 1947