初始化项目，由ModelHub XC社区提供模型
Model: HoangTran223/SFT_5e-5_Qwen2.5-1.5B_Ultrafb_2e Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
checkpoint-1910/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
checkpoint-3820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
57
README.md
Normal file
57
README.md
Normal file
@@ -0,0 +1,57 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
model_name: sft_qwen2.5_1.5b_ultrafb_20260412_190227
|
||||||
|
tags:
|
||||||
|
- generated_from_trainer
|
||||||
|
- trl
|
||||||
|
- sft
|
||||||
|
licence: license
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for sft_qwen2.5_1.5b_ultrafb_20260412_190227
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
||||||
|
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||||
|
|
||||||
|
## Quick start
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import pipeline
|
||||||
|
|
||||||
|
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||||
|
generator = pipeline("text-generation", model="None", device="cuda")
|
||||||
|
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||||
|
print(output["generated_text"])
|
||||||
|
```
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
This model was trained with SFT.
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- TRL: 1.1.0
|
||||||
|
- Transformers: 4.57.6
|
||||||
|
- Pytorch: 2.10.0
|
||||||
|
- Datasets: 4.8.4
|
||||||
|
- Tokenizers: 0.22.2
|
||||||
|
|
||||||
|
## Citations
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Cite TRL as:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@software{vonwerra2020trl,
|
||||||
|
title = {{TRL: Transformers Reinforcement Learning}},
|
||||||
|
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||||
|
license = {Apache-2.0},
|
||||||
|
url = {https://github.com/huggingface/trl},
|
||||||
|
year = {2020}
|
||||||
|
}
|
||||||
|
```
|
||||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- messages[0]['content'] }}
|
||||||
|
{%- else %}
|
||||||
|
{{- 'You are a helpful assistant.' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "\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>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\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" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role }}
|
||||||
|
{%- if message.content %}
|
||||||
|
{{- '\n' + message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if tool_call.function is defined %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- endif %}
|
||||||
24
checkpoint-1910/added_tokens.json
Normal file
24
checkpoint-1910/added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
54
checkpoint-1910/chat_template.jinja
Normal file
54
checkpoint-1910/chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- messages[0]['content'] }}
|
||||||
|
{%- else %}
|
||||||
|
{{- 'You are a helpful assistant.' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "\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>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\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" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role }}
|
||||||
|
{%- if message.content %}
|
||||||
|
{{- '\n' + message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if tool_call.function is defined %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- endif %}
|
||||||
59
checkpoint-1910/config.json
Normal file
59
checkpoint-1910/config.json
Normal file
@@ -0,0 +1,59 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8960,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "4.57.6",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_mrope": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
8
checkpoint-1910/generation_config.json
Normal file
8
checkpoint-1910/generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"eos_token_id": [
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"transformers_version": "4.57.6"
|
||||||
|
}
|
||||||
151388
checkpoint-1910/merges.txt
Normal file
151388
checkpoint-1910/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-1910/model.safetensors
Normal file
3
checkpoint-1910/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8f701dd06812160d0b50459b3c44426e9d20a2dd253df1082abacfc39b8f6bc6
|
||||||
|
size 3087467144
|
||||||
3
checkpoint-1910/optimizer.pt
Normal file
3
checkpoint-1910/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b22c308d4dd16d8b1e3b14dcb2f3920fac80f84010c76d25924670c10bdb1a60
|
||||||
|
size 6175153765
|
||||||
3
checkpoint-1910/rng_state.pth
Normal file
3
checkpoint-1910/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
|
||||||
|
size 14645
|
||||||
3
checkpoint-1910/scheduler.pt
Normal file
3
checkpoint-1910/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5570bc7c25651d7dcb54343501e58e83b06767a14ee45a22c42427ee182456ae
|
||||||
|
size 1465
|
||||||
25
checkpoint-1910/special_tokens_map.json
Normal file
25
checkpoint-1910/special_tokens_map.json
Normal file
@@ -0,0 +1,25 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
3
checkpoint-1910/tokenizer.json
Normal file
3
checkpoint-1910/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
207
checkpoint-1910/tokenizer_config.json
Normal file
207
checkpoint-1910/tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
1955
checkpoint-1910/trainer_state.json
Normal file
1955
checkpoint-1910/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-1910/training_args.bin
Normal file
3
checkpoint-1910/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b3bd5a58b9866f68427c85fc3d31c032ddecfb57e41b0cad03ac75f356429283
|
||||||
|
size 6353
|
||||||
1
checkpoint-1910/vocab.json
Normal file
1
checkpoint-1910/vocab.json
Normal file
File diff suppressed because one or more lines are too long
24
checkpoint-3820/added_tokens.json
Normal file
24
checkpoint-3820/added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
54
checkpoint-3820/chat_template.jinja
Normal file
54
checkpoint-3820/chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- messages[0]['content'] }}
|
||||||
|
{%- else %}
|
||||||
|
{{- 'You are a helpful assistant.' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "\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>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\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" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role }}
|
||||||
|
{%- if message.content %}
|
||||||
|
{{- '\n' + message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if tool_call.function is defined %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- endif %}
|
||||||
59
checkpoint-3820/config.json
Normal file
59
checkpoint-3820/config.json
Normal file
@@ -0,0 +1,59 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8960,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "4.57.6",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_mrope": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
8
checkpoint-3820/generation_config.json
Normal file
8
checkpoint-3820/generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"eos_token_id": [
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"transformers_version": "4.57.6"
|
||||||
|
}
|
||||||
151388
checkpoint-3820/merges.txt
Normal file
151388
checkpoint-3820/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-3820/model.safetensors
Normal file
3
checkpoint-3820/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2683c7b909433d4b0e70bd686f58160195b73388489656aa8c82979d67d29548
|
||||||
|
size 3087467144
|
||||||
3
checkpoint-3820/optimizer.pt
Normal file
3
checkpoint-3820/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:033d504bf99217659a5122a2f3690fee6191645236afd43bc6c19e3f8e989597
|
||||||
|
size 6175153765
|
||||||
3
checkpoint-3820/rng_state.pth
Normal file
3
checkpoint-3820/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
|
||||||
|
size 14645
|
||||||
3
checkpoint-3820/scheduler.pt
Normal file
3
checkpoint-3820/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a234fdc83826dcda179e3c7f72fbd03cf879992f38203b49281ed7d253dbd398
|
||||||
|
size 1465
|
||||||
25
checkpoint-3820/special_tokens_map.json
Normal file
25
checkpoint-3820/special_tokens_map.json
Normal file
@@ -0,0 +1,25 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
3
checkpoint-3820/tokenizer.json
Normal file
3
checkpoint-3820/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
207
checkpoint-3820/tokenizer_config.json
Normal file
207
checkpoint-3820/tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
3876
checkpoint-3820/trainer_state.json
Normal file
3876
checkpoint-3820/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-3820/training_args.bin
Normal file
3
checkpoint-3820/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b3bd5a58b9866f68427c85fc3d31c032ddecfb57e41b0cad03ac75f356429283
|
||||||
|
size 6353
|
||||||
1
checkpoint-3820/vocab.json
Normal file
1
checkpoint-3820/vocab.json
Normal file
File diff suppressed because one or more lines are too long
59
config.json
Normal file
59
config.json
Normal file
@@ -0,0 +1,59 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8960,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "4.57.6",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_mrope": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"eos_token_id": [
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"transformers_version": "4.57.6"
|
||||||
|
}
|
||||||
70
leaderboard_results_base_model/arc_challenge_results.json
Normal file
70
leaderboard_results_base_model/arc_challenge_results.json
Normal file
@@ -0,0 +1,70 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"arc_challenge": {
|
||||||
|
"acc,none": 0.492320819112628,
|
||||||
|
"acc_stderr,none": 0.014609667440892515,
|
||||||
|
"acc_norm,none": 0.5460750853242321,
|
||||||
|
"acc_norm_stderr,none": 0.014549221105171829,
|
||||||
|
"alias": "arc_challenge"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"arc_challenge": {
|
||||||
|
"task": "arc_challenge",
|
||||||
|
"group": [
|
||||||
|
"ai2_arc"
|
||||||
|
],
|
||||||
|
"dataset_path": "ai2_arc",
|
||||||
|
"dataset_name": "ARC-Challenge",
|
||||||
|
"training_split": "train",
|
||||||
|
"validation_split": "validation",
|
||||||
|
"test_split": "test",
|
||||||
|
"doc_to_text": "Question: {{question}}\nAnswer:",
|
||||||
|
"doc_to_target": "{{choices.label.index(answerKey)}}",
|
||||||
|
"doc_to_choice": "{{choices.text}}",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 25,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "acc",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"metric": "acc_norm",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "multiple_choice",
|
||||||
|
"repeats": 1,
|
||||||
|
"should_decontaminate": true,
|
||||||
|
"doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 1.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"arc_challenge": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"arc_challenge": 25
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/model_hub/Qwen2.5-1.5B,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
90
leaderboard_results_base_model/gsm8k_results.json
Normal file
90
leaderboard_results_base_model/gsm8k_results.json
Normal file
@@ -0,0 +1,90 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"gsm8k": {
|
||||||
|
"exact_match,get-answer": 0.6087945413191812,
|
||||||
|
"exact_match_stderr,get-answer": 0.013442502402794302,
|
||||||
|
"alias": "gsm8k"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"gsm8k": {
|
||||||
|
"task": "gsm8k",
|
||||||
|
"group": [
|
||||||
|
"math_word_problems"
|
||||||
|
],
|
||||||
|
"dataset_path": "gsm8k",
|
||||||
|
"dataset_name": "main",
|
||||||
|
"training_split": "train",
|
||||||
|
"test_split": "test",
|
||||||
|
"fewshot_split": "train",
|
||||||
|
"doc_to_text": "Question: {{question}}\nAnswer:",
|
||||||
|
"doc_to_target": "{{answer}}",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 5,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "exact_match",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true,
|
||||||
|
"ignore_case": true,
|
||||||
|
"ignore_punctuation": false,
|
||||||
|
"regexes_to_ignore": [
|
||||||
|
",",
|
||||||
|
"\\$",
|
||||||
|
"(?s).*#### "
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "generate_until",
|
||||||
|
"generation_kwargs": {
|
||||||
|
"until": [
|
||||||
|
"\n\n",
|
||||||
|
"Question:"
|
||||||
|
],
|
||||||
|
"do_sample": false,
|
||||||
|
"temperature": 0.0
|
||||||
|
},
|
||||||
|
"repeats": 1,
|
||||||
|
"filter_list": [
|
||||||
|
{
|
||||||
|
"name": "get-answer",
|
||||||
|
"filter": [
|
||||||
|
{
|
||||||
|
"function": "regex",
|
||||||
|
"regex_pattern": "#### (\\-?[0-9\\.\\,]+)"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"function": "take_first"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"should_decontaminate": false,
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 1.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"gsm8k": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"gsm8k": 5
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/model_hub/Qwen2.5-1.5B,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
68
leaderboard_results_base_model/hellaswag_results.json
Normal file
68
leaderboard_results_base_model/hellaswag_results.json
Normal file
@@ -0,0 +1,68 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"hellaswag": {
|
||||||
|
"acc,none": 0.5028878709420435,
|
||||||
|
"acc_stderr,none": 0.004989698183207901,
|
||||||
|
"acc_norm,none": 0.6787492531368253,
|
||||||
|
"acc_norm_stderr,none": 0.004660025270816849,
|
||||||
|
"alias": "hellaswag"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"hellaswag": {
|
||||||
|
"task": "hellaswag",
|
||||||
|
"group": [
|
||||||
|
"multiple_choice"
|
||||||
|
],
|
||||||
|
"dataset_path": "hellaswag",
|
||||||
|
"training_split": "train",
|
||||||
|
"validation_split": "validation",
|
||||||
|
"process_docs": "<function process_docs at 0x7f84c1667240>",
|
||||||
|
"doc_to_text": "{{query}}",
|
||||||
|
"doc_to_target": "{{label}}",
|
||||||
|
"doc_to_choice": "{{choices}}",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 10,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "acc",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"metric": "acc_norm",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "multiple_choice",
|
||||||
|
"repeats": 1,
|
||||||
|
"should_decontaminate": false,
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 1.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"hellaswag": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"hellaswag": 10
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/model_hub/Qwen2.5-1.5B,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
2763
leaderboard_results_base_model/mmlu_results.json
Normal file
2763
leaderboard_results_base_model/mmlu_results.json
Normal file
File diff suppressed because it is too large
Load Diff
62
leaderboard_results_base_model/truthfulqa_mc2_results.json
Normal file
62
leaderboard_results_base_model/truthfulqa_mc2_results.json
Normal file
@@ -0,0 +1,62 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"truthfulqa_mc2": {
|
||||||
|
"acc,none": 0.46611639164182933,
|
||||||
|
"acc_stderr,none": 0.01483185593624306,
|
||||||
|
"alias": "truthfulqa_mc2"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"truthfulqa_mc2": {
|
||||||
|
"task": "truthfulqa_mc2",
|
||||||
|
"group": [
|
||||||
|
"truthfulqa"
|
||||||
|
],
|
||||||
|
"dataset_path": "truthful_qa",
|
||||||
|
"dataset_name": "multiple_choice",
|
||||||
|
"validation_split": "validation",
|
||||||
|
"doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
|
||||||
|
"doc_to_target": 0,
|
||||||
|
"doc_to_choice": "{{mc2_targets.choices}}",
|
||||||
|
"process_results": "<function process_results_mc2 at 0x7fa1b3088360>",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 0,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "acc",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "multiple_choice",
|
||||||
|
"repeats": 1,
|
||||||
|
"should_decontaminate": true,
|
||||||
|
"doc_to_decontamination_query": "question",
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 2.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"truthfulqa_mc2": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"truthfulqa_mc2": 0
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/model_hub/Qwen2.5-1.5B,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
59
leaderboard_results_base_model/winogrande_results.json
Normal file
59
leaderboard_results_base_model/winogrande_results.json
Normal file
@@ -0,0 +1,59 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"winogrande": {
|
||||||
|
"acc,none": 0.632991318074191,
|
||||||
|
"acc_stderr,none": 0.013546284512919693,
|
||||||
|
"alias": "winogrande"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"winogrande": {
|
||||||
|
"task": "winogrande",
|
||||||
|
"dataset_path": "winogrande",
|
||||||
|
"dataset_name": "winogrande_xl",
|
||||||
|
"training_split": "train",
|
||||||
|
"validation_split": "validation",
|
||||||
|
"doc_to_text": "<function doc_to_text at 0x7f3304801440>",
|
||||||
|
"doc_to_target": "<function doc_to_target at 0x7f3304801800>",
|
||||||
|
"doc_to_choice": "<function doc_to_choice at 0x7f3304801bc0>",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 5,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "acc",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "multiple_choice",
|
||||||
|
"repeats": 1,
|
||||||
|
"should_decontaminate": true,
|
||||||
|
"doc_to_decontamination_query": "sentence",
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 1.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"winogrande": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"winogrande": 5
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/model_hub/Qwen2.5-1.5B,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
@@ -0,0 +1,70 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"arc_challenge": {
|
||||||
|
"acc,none": 0.48208191126279865,
|
||||||
|
"acc_stderr,none": 0.014602005585490881,
|
||||||
|
"acc_norm,none": 0.5298634812286689,
|
||||||
|
"acc_norm_stderr,none": 0.014585305840007116,
|
||||||
|
"alias": "arc_challenge"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"arc_challenge": {
|
||||||
|
"task": "arc_challenge",
|
||||||
|
"group": [
|
||||||
|
"ai2_arc"
|
||||||
|
],
|
||||||
|
"dataset_path": "ai2_arc",
|
||||||
|
"dataset_name": "ARC-Challenge",
|
||||||
|
"training_split": "train",
|
||||||
|
"validation_split": "validation",
|
||||||
|
"test_split": "test",
|
||||||
|
"doc_to_text": "Question: {{question}}\nAnswer:",
|
||||||
|
"doc_to_target": "{{choices.label.index(answerKey)}}",
|
||||||
|
"doc_to_choice": "{{choices.text}}",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 25,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "acc",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"metric": "acc_norm",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "multiple_choice",
|
||||||
|
"repeats": 1,
|
||||||
|
"should_decontaminate": true,
|
||||||
|
"doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 1.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"arc_challenge": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"arc_challenge": 25
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/output/sft_qwen2.5_1.5b_ultrafb_20260412_190227/checkpoint-3820,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
@@ -0,0 +1,90 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"gsm8k": {
|
||||||
|
"exact_match,get-answer": 0.47536012130401817,
|
||||||
|
"exact_match_stderr,get-answer": 0.013755751352764918,
|
||||||
|
"alias": "gsm8k"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"gsm8k": {
|
||||||
|
"task": "gsm8k",
|
||||||
|
"group": [
|
||||||
|
"math_word_problems"
|
||||||
|
],
|
||||||
|
"dataset_path": "gsm8k",
|
||||||
|
"dataset_name": "main",
|
||||||
|
"training_split": "train",
|
||||||
|
"test_split": "test",
|
||||||
|
"fewshot_split": "train",
|
||||||
|
"doc_to_text": "Question: {{question}}\nAnswer:",
|
||||||
|
"doc_to_target": "{{answer}}",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 5,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "exact_match",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true,
|
||||||
|
"ignore_case": true,
|
||||||
|
"ignore_punctuation": false,
|
||||||
|
"regexes_to_ignore": [
|
||||||
|
",",
|
||||||
|
"\\$",
|
||||||
|
"(?s).*#### "
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "generate_until",
|
||||||
|
"generation_kwargs": {
|
||||||
|
"until": [
|
||||||
|
"\n\n",
|
||||||
|
"Question:"
|
||||||
|
],
|
||||||
|
"do_sample": false,
|
||||||
|
"temperature": 0.0
|
||||||
|
},
|
||||||
|
"repeats": 1,
|
||||||
|
"filter_list": [
|
||||||
|
{
|
||||||
|
"name": "get-answer",
|
||||||
|
"filter": [
|
||||||
|
{
|
||||||
|
"function": "regex",
|
||||||
|
"regex_pattern": "#### (\\-?[0-9\\.\\,]+)"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"function": "take_first"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"should_decontaminate": false,
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 1.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"gsm8k": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"gsm8k": 5
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/output/sft_qwen2.5_1.5b_ultrafb_20260412_190227/checkpoint-3820,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
@@ -0,0 +1,68 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"hellaswag": {
|
||||||
|
"acc,none": 0.5153355905198168,
|
||||||
|
"acc_stderr,none": 0.0049874338622748204,
|
||||||
|
"acc_norm,none": 0.6958773152758415,
|
||||||
|
"acc_norm_stderr,none": 0.004590946839727457,
|
||||||
|
"alias": "hellaswag"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"hellaswag": {
|
||||||
|
"task": "hellaswag",
|
||||||
|
"group": [
|
||||||
|
"multiple_choice"
|
||||||
|
],
|
||||||
|
"dataset_path": "hellaswag",
|
||||||
|
"training_split": "train",
|
||||||
|
"validation_split": "validation",
|
||||||
|
"process_docs": "<function process_docs at 0x7f4269697240>",
|
||||||
|
"doc_to_text": "{{query}}",
|
||||||
|
"doc_to_target": "{{label}}",
|
||||||
|
"doc_to_choice": "{{choices}}",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 10,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "acc",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"metric": "acc_norm",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "multiple_choice",
|
||||||
|
"repeats": 1,
|
||||||
|
"should_decontaminate": false,
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 1.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"hellaswag": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"hellaswag": 10
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/output/sft_qwen2.5_1.5b_ultrafb_20260412_190227/checkpoint-3820,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
2763
leaderboard_results_sft_lr5e5_ultrafb_epoch_2/mmlu_results.json
Normal file
2763
leaderboard_results_sft_lr5e5_ultrafb_epoch_2/mmlu_results.json
Normal file
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,62 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"truthfulqa_mc2": {
|
||||||
|
"acc,none": 0.45683006430749684,
|
||||||
|
"acc_stderr,none": 0.014652867678401628,
|
||||||
|
"alias": "truthfulqa_mc2"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"truthfulqa_mc2": {
|
||||||
|
"task": "truthfulqa_mc2",
|
||||||
|
"group": [
|
||||||
|
"truthfulqa"
|
||||||
|
],
|
||||||
|
"dataset_path": "truthful_qa",
|
||||||
|
"dataset_name": "multiple_choice",
|
||||||
|
"validation_split": "validation",
|
||||||
|
"doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
|
||||||
|
"doc_to_target": 0,
|
||||||
|
"doc_to_choice": "{{mc2_targets.choices}}",
|
||||||
|
"process_results": "<function process_results_mc2 at 0x7f980557c360>",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 0,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "acc",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "multiple_choice",
|
||||||
|
"repeats": 1,
|
||||||
|
"should_decontaminate": true,
|
||||||
|
"doc_to_decontamination_query": "question",
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 2.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"truthfulqa_mc2": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"truthfulqa_mc2": 0
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/output/sft_qwen2.5_1.5b_ultrafb_20260412_190227/checkpoint-3820,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
@@ -0,0 +1,59 @@
|
|||||||
|
{
|
||||||
|
"results": {
|
||||||
|
"winogrande": {
|
||||||
|
"acc,none": 0.6337805840568271,
|
||||||
|
"acc_stderr,none": 0.013540144376588965,
|
||||||
|
"alias": "winogrande"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"configs": {
|
||||||
|
"winogrande": {
|
||||||
|
"task": "winogrande",
|
||||||
|
"dataset_path": "winogrande",
|
||||||
|
"dataset_name": "winogrande_xl",
|
||||||
|
"training_split": "train",
|
||||||
|
"validation_split": "validation",
|
||||||
|
"doc_to_text": "<function doc_to_text at 0x7f26c933d440>",
|
||||||
|
"doc_to_target": "<function doc_to_target at 0x7f26c933d800>",
|
||||||
|
"doc_to_choice": "<function doc_to_choice at 0x7f26c933dbc0>",
|
||||||
|
"description": "",
|
||||||
|
"target_delimiter": " ",
|
||||||
|
"fewshot_delimiter": "\n\n",
|
||||||
|
"num_fewshot": 5,
|
||||||
|
"metric_list": [
|
||||||
|
{
|
||||||
|
"metric": "acc",
|
||||||
|
"aggregation": "mean",
|
||||||
|
"higher_is_better": true
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"output_type": "multiple_choice",
|
||||||
|
"repeats": 1,
|
||||||
|
"should_decontaminate": true,
|
||||||
|
"doc_to_decontamination_query": "sentence",
|
||||||
|
"metadata": [
|
||||||
|
{
|
||||||
|
"version": 1.0
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"versions": {
|
||||||
|
"winogrande": "Yaml"
|
||||||
|
},
|
||||||
|
"n-shot": {
|
||||||
|
"winogrande": 5
|
||||||
|
},
|
||||||
|
"config": {
|
||||||
|
"model": "vllm",
|
||||||
|
"model_args": "pretrained=/home/hungpv/projects/SWIFT/output/sft_qwen2.5_1.5b_ultrafb_20260412_190227/checkpoint-3820,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8",
|
||||||
|
"batch_size": "auto",
|
||||||
|
"batch_sizes": [],
|
||||||
|
"device": null,
|
||||||
|
"use_cache": null,
|
||||||
|
"limit": null,
|
||||||
|
"bootstrap_iters": 100000,
|
||||||
|
"gen_kwargs": {}
|
||||||
|
},
|
||||||
|
"git_hash": "24768f7"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2683c7b909433d4b0e70bd686f58160195b73388489656aa8c82979d67d29548
|
||||||
|
size 3087467144
|
||||||
25
special_tokens_map.json
Normal file
25
special_tokens_map.json
Normal file
@@ -0,0 +1,25 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b3bd5a58b9866f68427c85fc3d31c032ddecfb57e41b0cad03ac75f356429283
|
||||||
|
size 6353
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user