Reinforcement Learning
PEFT
Safetensors
Korean
deep-reinforcement-learning
ppo
robotics
decision-making
link01
connect-ai-world
connect-ai-lab
connectailab
lora
Instructions to use nexflow/connectailab-rl-coco-v4-link01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nexflow/connectailab-rl-coco-v4-link01 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-0.8B") model = PeftModel.from_pretrained(base_model, "nexflow/connectailab-rl-coco-v4-link01") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- adapter_config.json +56 -0
- adapter_model.safetensors +3 -0
- rl_history.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +48 -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
|
adapter_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"kasa_config": null,
|
| 16 |
+
"layer_replication": null,
|
| 17 |
+
"layers_pattern": null,
|
| 18 |
+
"layers_to_transform": null,
|
| 19 |
+
"loftq_config": {},
|
| 20 |
+
"lora_alpha": 16,
|
| 21 |
+
"lora_bias": false,
|
| 22 |
+
"lora_dropout": 0.0,
|
| 23 |
+
"lora_ga_config": null,
|
| 24 |
+
"megatron_config": null,
|
| 25 |
+
"megatron_core": "megatron.core",
|
| 26 |
+
"modules_to_save": null,
|
| 27 |
+
"monteclora_config": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"peft_version": "0.21.2",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 8,
|
| 32 |
+
"rank_pattern": {},
|
| 33 |
+
"revision": null,
|
| 34 |
+
"target_modules": [
|
| 35 |
+
"out_proj",
|
| 36 |
+
"in_proj_qkv",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"down_proj",
|
| 39 |
+
"in_proj_a",
|
| 40 |
+
"v_proj",
|
| 41 |
+
"in_proj_b",
|
| 42 |
+
"in_proj_z",
|
| 43 |
+
"up_proj",
|
| 44 |
+
"q_proj",
|
| 45 |
+
"k_proj",
|
| 46 |
+
"gate_proj"
|
| 47 |
+
],
|
| 48 |
+
"target_parameters": null,
|
| 49 |
+
"task_type": "CAUSAL_LM",
|
| 50 |
+
"trainable_token_indices": null,
|
| 51 |
+
"use_bdlora": null,
|
| 52 |
+
"use_dora": false,
|
| 53 |
+
"use_qalora": false,
|
| 54 |
+
"use_rslora": false,
|
| 55 |
+
"velora_config": null
|
| 56 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0890e566f97e6ec66ffd9e67cbfac41cf15c2f587774ddea6e4499fa91c0260e
|
| 3 |
+
size 21694976
|
rl_history.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"start": "adapters/sft",
|
| 3 |
+
"steps": 100,
|
| 4 |
+
"batch": 8,
|
| 5 |
+
"lr": 5e-06,
|
| 6 |
+
"beta": 0.2,
|
| 7 |
+
"history": [
|
| 8 |
+
{
|
| 9 |
+
"step": 50,
|
| 10 |
+
"loss": 0.0015675351023674011,
|
| 11 |
+
"accuracy": 0.5909090909090909,
|
| 12 |
+
"regret": 0.5763941558441559,
|
| 13 |
+
"n": 154
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"step": 100,
|
| 17 |
+
"loss": 0.0022423425689339638,
|
| 18 |
+
"accuracy": 0.5974025974025974,
|
| 19 |
+
"regret": 0.5384824675324675,
|
| 20 |
+
"n": 154
|
| 21 |
+
}
|
| 22 |
+
]
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5cd9732badce41de57e6efce8302930ded1c1188c5f81feb2bd6c24c4a1941f
|
| 3 |
+
size 19989339
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"extra_special_tokens": [
|
| 12 |
+
"<|im_start|>",
|
| 13 |
+
"<|im_end|>",
|
| 14 |
+
"<|object_ref_start|>",
|
| 15 |
+
"<|object_ref_end|>",
|
| 16 |
+
"<|box_start|>",
|
| 17 |
+
"<|box_end|>",
|
| 18 |
+
"<|quad_start|>",
|
| 19 |
+
"<|quad_end|>",
|
| 20 |
+
"<|vision_start|>",
|
| 21 |
+
"<|vision_end|>",
|
| 22 |
+
"<|vision_pad|>",
|
| 23 |
+
"<|image_pad|>",
|
| 24 |
+
"<|video_pad|>"
|
| 25 |
+
],
|
| 26 |
+
"image_token": "<|image_pad|>",
|
| 27 |
+
"is_local": false,
|
| 28 |
+
"local_files_only": false,
|
| 29 |
+
"merges_file": null,
|
| 30 |
+
"model_max_length": 262144,
|
| 31 |
+
"model_specific_special_tokens": {
|
| 32 |
+
"audio_bos_token": "<|audio_start|>",
|
| 33 |
+
"audio_eos_token": "<|audio_end|>",
|
| 34 |
+
"audio_token": "<|audio_pad|>",
|
| 35 |
+
"image_token": "<|image_pad|>",
|
| 36 |
+
"video_token": "<|video_pad|>",
|
| 37 |
+
"vision_bos_token": "<|vision_start|>",
|
| 38 |
+
"vision_eos_token": "<|vision_end|>"
|
| 39 |
+
},
|
| 40 |
+
"pad_token": "<|endoftext|>",
|
| 41 |
+
"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+",
|
| 42 |
+
"split_special_tokens": false,
|
| 43 |
+
"tokenizer_class": "Qwen3_5Tokenizer",
|
| 44 |
+
"unk_token": null,
|
| 45 |
+
"video_token": "<|video_pad|>",
|
| 46 |
+
"vision_bos_token": "<|vision_start|>",
|
| 47 |
+
"vision_eos_token": "<|vision_end|>"
|
| 48 |
+
}
|