Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +0 -0
- chat_template.jinja +54 -0
- config.json +56 -0
- generation_config.json +8 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 %}
|
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 896,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4864,
|
12 |
+
"layer_types": [
|
13 |
+
"full_attention",
|
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 |
+
],
|
38 |
+
"max_position_embeddings": 32768,
|
39 |
+
"max_window_layers": 21,
|
40 |
+
"model_type": "qwen2",
|
41 |
+
"num_attention_heads": 14,
|
42 |
+
"num_hidden_layers": 24,
|
43 |
+
"num_key_value_heads": 2,
|
44 |
+
"pad_token_id": 151643,
|
45 |
+
"rms_norm_eps": 1e-06,
|
46 |
+
"rope_scaling": null,
|
47 |
+
"rope_theta": 1000000.0,
|
48 |
+
"sliding_window": null,
|
49 |
+
"tie_word_embeddings": true,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.54.0",
|
52 |
+
"unsloth_version": "2025.7.8",
|
53 |
+
"use_cache": true,
|
54 |
+
"use_sliding_window": false,
|
55 |
+
"vocab_size": 166000
|
56 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 151643,
|
4 |
+
"eos_token_id": 151645,
|
5 |
+
"max_length": 32768,
|
6 |
+
"pad_token_id": 151643,
|
7 |
+
"transformers_version": "4.54.0"
|
8 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d119d993d9ecbe4eb01afd5218d452c34cfbd0be376a6c4c2187076ef62fc22
|
3 |
+
size 2026568872
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdd8fe4fd6080a61e5d2d7ae6a4da53462a737db2bb52e82bece55ff303f46c8
|
3 |
+
size 1917566219
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
|
3 |
+
size 14645
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:755d4abba88f340f91b1a377e6e817a46939b246ab101aeb899634f2fdf75cfd
|
3 |
+
size 1465
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fecfbcc54145cc47e3f540ea595d9b4ab627b2f1859d01d6ed16918058f6bdb0
|
3 |
+
size 14129730
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e91443afbbad6c0eb943933e5d86065919ddb4073fc98bb3f168b18d8d69bc1
|
3 |
+
size 6161
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|