add bt7274 qwen3.5-27b lora v4 adapter config
This commit is contained in:
@@ -0,0 +1,63 @@
|
||||
---
|
||||
base_model: Qwen/Qwen3.5-27B
|
||||
library_name: peft
|
||||
model_name: bt7274-qwen35-27b-lora-v4
|
||||
tags:
|
||||
- base_model:adapter:Qwen/Qwen3.5-27B
|
||||
- lora
|
||||
- sft
|
||||
- transformers
|
||||
- trl
|
||||
- unsloth
|
||||
licence: license
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Model Card for bt7274-qwen35-27b-lora-v4
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3.5-27B](https://huggingface.co/Qwen/Qwen3.5-27B).
|
||||
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
|
||||
|
||||
- PEFT 0.19.1
|
||||
- TRL: 0.24.0
|
||||
- Transformers: 5.5.0
|
||||
- Pytorch: 2.12.0+cu132
|
||||
- Datasets: 4.3.0
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## Citations
|
||||
|
||||
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,52 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": {
|
||||
"base_model_class": "Qwen3_5ForConditionalGeneration",
|
||||
"parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
|
||||
"unsloth_fixed": true
|
||||
},
|
||||
"base_model_name_or_path": "Qwen/Qwen3.5-27B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 16,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 16,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"o_proj",
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"gate_proj",
|
||||
"up_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"image_processor": {
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessor",
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"merge_size": 2,
|
||||
"patch_size": 16,
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"longest_edge": 16777216,
|
||||
"shortest_edge": 65536
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"video_processor": {
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": true,
|
||||
"fps": 2,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"max_frames": 768,
|
||||
"merge_size": 2,
|
||||
"min_frames": 4,
|
||||
"patch_size": 16,
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_metadata": false,
|
||||
"size": {
|
||||
"longest_edge": 25165824,
|
||||
"shortest_edge": 4096
|
||||
},
|
||||
"temporal_patch_size": 2,
|
||||
"video_processor_type": "Qwen3VLVideoProcessor"
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"audio_bos_token": "<|audio_start|>",
|
||||
"audio_eos_token": "<|audio_end|>",
|
||||
"audio_token": "<|audio_pad|>",
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"image_token": "<|image_pad|>",
|
||||
"is_local": false,
|
||||
"model_max_length": 262144,
|
||||
"model_specific_special_tokens": {
|
||||
"audio_bos_token": "<|audio_start|>",
|
||||
"audio_eos_token": "<|audio_end|>",
|
||||
"audio_token": "<|audio_pad|>",
|
||||
"image_token": "<|image_pad|>",
|
||||
"video_token": "<|video_pad|>",
|
||||
"vision_bos_token": "<|vision_start|>",
|
||||
"vision_eos_token": "<|vision_end|>"
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": null,
|
||||
"video_token": "<|video_pad|>",
|
||||
"vision_bos_token": "<|vision_start|>",
|
||||
"vision_eos_token": "<|vision_end|>",
|
||||
"added_tokens_decoder": {
|
||||
"248044": {
|
||||
"content": "<|endoftext|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248045": {
|
||||
"content": "<|im_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248046": {
|
||||
"content": "<|im_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248047": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248048": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248049": {
|
||||
"content": "<|box_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248050": {
|
||||
"content": "<|box_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248051": {
|
||||
"content": "<|quad_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248052": {
|
||||
"content": "<|quad_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248053": {
|
||||
"content": "<|vision_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248054": {
|
||||
"content": "<|vision_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248055": {
|
||||
"content": "<|vision_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248056": {
|
||||
"content": "<|image_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248057": {
|
||||
"content": "<|video_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248058": {
|
||||
"content": "<tool_call>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248059": {
|
||||
"content": "</tool_call>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248060": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248061": {
|
||||
"content": "<|fim_middle|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248062": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248063": {
|
||||
"content": "<|fim_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248064": {
|
||||
"content": "<|repo_name|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248065": {
|
||||
"content": "<|file_sep|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248066": {
|
||||
"content": "<tool_response>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248067": {
|
||||
"content": "</tool_response>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248068": {
|
||||
"content": "<think>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248069": {
|
||||
"content": "</think>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"248070": {
|
||||
"content": "<|audio_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248071": {
|
||||
"content": "<|audio_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248072": {
|
||||
"content": "<tts_pad>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248073": {
|
||||
"content": "<tts_text_bos>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248074": {
|
||||
"content": "<tts_text_eod>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248075": {
|
||||
"content": "<tts_text_bos_single>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"248076": {
|
||||
"content": "<|audio_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user