Delete 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000
Browse files- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/added_tokens.json +0 -5
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/config.json +0 -32
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/generation_config.json +0 -14
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/merges.txt +0 -0
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/mlp_projector.bin +0 -3
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/model.safetensors +0 -3
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/optimizer.pt +0 -3
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/rng_state.pth +0 -3
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/scheduler.pt +0 -3
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/special_tokens_map.json +0 -20
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/tokenizer.json +0 -3
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/tokenizer_config.json +0 -44
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/trainer_state.json +0 -0
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/training_args.bin +0 -3
- 2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/vocab.json +0 -0
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/added_tokens.json
DELETED
|
@@ -1,5 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<|endoftext|>": 151643,
|
| 3 |
-
"<|im_end|>": 151645,
|
| 4 |
-
"<|im_start|>": 151644
|
| 5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/config.json
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
|
| 3 |
-
"action_dim": 4,
|
| 4 |
-
"architectures": [
|
| 5 |
-
"LowdimQwen2ForCausalLM"
|
| 6 |
-
],
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id": 151643,
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"hidden_act": "silu",
|
| 11 |
-
"hidden_size": 896,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size": 4864,
|
| 14 |
-
"max_position_embeddings": 32768,
|
| 15 |
-
"max_window_layers": 24,
|
| 16 |
-
"model_type": "qwen2_lowdim",
|
| 17 |
-
"num_attention_heads": 14,
|
| 18 |
-
"num_hidden_layers": 24,
|
| 19 |
-
"num_key_value_heads": 2,
|
| 20 |
-
"obs_dim": 9,
|
| 21 |
-
"rms_norm_eps": 1e-06,
|
| 22 |
-
"rope_scaling": null,
|
| 23 |
-
"rope_theta": 1000000.0,
|
| 24 |
-
"sliding_window": null,
|
| 25 |
-
"tie_word_embeddings": true,
|
| 26 |
-
"torch_dtype": "float32",
|
| 27 |
-
"transformers_version": "4.47.1",
|
| 28 |
-
"use_cache": false,
|
| 29 |
-
"use_joint_mlp_projector": true,
|
| 30 |
-
"use_sliding_window": false,
|
| 31 |
-
"vocab_size": 151936
|
| 32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/generation_config.json
DELETED
|
@@ -1,14 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token_id": 151643,
|
| 3 |
-
"do_sample": true,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
151645,
|
| 6 |
-
151643
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 151643,
|
| 9 |
-
"repetition_penalty": 1.1,
|
| 10 |
-
"temperature": 0.7,
|
| 11 |
-
"top_k": 20,
|
| 12 |
-
"top_p": 0.8,
|
| 13 |
-
"transformers_version": "4.47.1"
|
| 14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/mlp_projector.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:dc3b1b487dcc689fd5e6c73db8b5e32a3800f93e05b592970be038e7546f2d72
|
| 3 |
-
size 3267200
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e5e179f4fc46570f79ba9c40c408e2ef4a82f40a53b9e4578361b93215c259fe
|
| 3 |
-
size 1979428992
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7abb480af21a95ca044a35b6d6a65d8c85dea07c4243213a70d66a50a1da3125
|
| 3 |
-
size 3958970426
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bcfd7b020de52099d4b11d841de4b14a9d805e7b70aa6afbfdd0c3060ab3d237
|
| 3 |
-
size 14244
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bb6bea096222d99ff50df439a78a5a93b2bf846f18435312cf0b73a4d9f9797f
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/special_tokens_map.json
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|im_start|>",
|
| 4 |
-
"<|im_end|>"
|
| 5 |
-
],
|
| 6 |
-
"eos_token": {
|
| 7 |
-
"content": "<|im_end|>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false
|
| 12 |
-
},
|
| 13 |
-
"pad_token": {
|
| 14 |
-
"content": "<|endoftext|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
}
|
| 20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
-
size 11418266
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/tokenizer_config.json
DELETED
|
@@ -1,44 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"151643": {
|
| 5 |
-
"content": "<|endoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"151644": {
|
| 13 |
-
"content": "<|im_start|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"151645": {
|
| 21 |
-
"content": "<|im_end|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
}
|
| 28 |
-
},
|
| 29 |
-
"additional_special_tokens": [
|
| 30 |
-
"<|im_start|>",
|
| 31 |
-
"<|im_end|>"
|
| 32 |
-
],
|
| 33 |
-
"bos_token": null,
|
| 34 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
-
"clean_up_tokenization_spaces": false,
|
| 36 |
-
"eos_token": "<|im_end|>",
|
| 37 |
-
"errors": "replace",
|
| 38 |
-
"extra_special_tokens": {},
|
| 39 |
-
"model_max_length": 32768,
|
| 40 |
-
"pad_token": "<|endoftext|>",
|
| 41 |
-
"split_special_tokens": false,
|
| 42 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
-
"unk_token": null
|
| 44 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/trainer_state.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e352bbf79fe71f7b32e56f82547a77a248dd86186015e71486b983673d6022f3
|
| 3 |
-
size 5944
|
|
|
|
|
|
|
|
|
|
|
|
2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|