Hugging Face's logo

Ba2han
/
lqd-test

Text Generation
Transformers
Safetensors
lfm2_moe
Generated from Trainer
unsloth
trl
sft
conversational
Model card Files
xet
 Community
Ba2han commited on
Commit
35713cc
·
verified ·
1 Parent(s): 266e370

Delete last-checkpoint

Browse files
Files changed (11) hide show
  1. last-checkpoint/chat_template.jinja +0 -4
  2. last-checkpoint/config.json +0 -62
  3. last-checkpoint/generation_config.json +0 -10
  4. last-checkpoint/model.safetensors +0 -3
  5. last-checkpoint/optimizer.pt +0 -3
  6. last-checkpoint/rng_state.pth +0 -3
  7. last-checkpoint/scheduler.pt +0 -3
  8. last-checkpoint/tokenizer.json +0 -0
  9. last-checkpoint/tokenizer_config.json +0 -20
  10. last-checkpoint/trainer_state.json +0 -0
  11. last-checkpoint/training_args.bin +0 -3
last-checkpoint/chat_template.jinja DELETED
@@ -1,4 +0,0 @@
1
- {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
- ' + message['content'] + '<|im_end|>' + '
3
- '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
- ' }}{% endif %}
 
 
 
 
 
last-checkpoint/config.json DELETED
@@ -1,62 +0,0 @@
1
- {
2
- "architectures": [
3
- "Lfm2MoeForCausalLM"
4
- ],
5
- "bos_token_id": 1,
6
- "conv_L_cache": 3,
7
- "conv_bias": false,
8
- "dtype": "bfloat16",
9
- "eos_token_id": 7,
10
- "hidden_size": 2048,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 7168,
13
- "layer_types": [
14
- "conv",
15
- "conv",
16
- "full_attention",
17
- "conv",
18
- "conv",
19
- "conv",
20
- "full_attention",
21
- "conv",
22
- "conv",
23
- "conv",
24
- "full_attention",
25
- "conv",
26
- "conv",
27
- "conv",
28
- "full_attention",
29
- "conv",
30
- "conv",
31
- "conv",
32
- "full_attention",
33
- "conv",
34
- "conv",
35
- "full_attention",
36
- "conv",
37
- "conv"
38
- ],
39
- "max_position_embeddings": 128000,
40
- "model_type": "lfm2_moe",
41
- "moe_intermediate_size": 1792,
42
- "norm_eps": 1e-05,
43
- "norm_topk_prob": true,
44
- "num_attention_heads": 32,
45
- "num_dense_layers": 2,
46
- "num_experts": 32,
47
- "num_experts_per_tok": 4,
48
- "num_hidden_layers": 24,
49
- "num_key_value_heads": 8,
50
- "pad_token_id": 0,
51
- "rope_parameters": {
52
- "rope_theta": 1000000.0,
53
- "rope_type": "default"
54
- },
55
- "routed_scaling_factor": 1.0,
56
- "tie_word_embeddings": true,
57
- "transformers_version": "5.1.0",
58
- "unsloth_version": "2026.2.1",
59
- "use_cache": false,
60
- "use_expert_bias": true,
61
- "vocab_size": 65536
62
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/generation_config.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": [
5
- 7
6
- ],
7
- "max_length": 128000,
8
- "pad_token_id": 0,
9
- "transformers_version": "5.1.0"
10
- }
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:64beb12622e19cca2045f0634a56a449f1a0aaea999b2dbee11c8001ebd9b112
3
- size 16680154224
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5d9fae89fe76cde5ef7f65cbdd6759487d3658cde2655ed67d430046a541c3f
3
- size 17742419627
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e831a926501c469a9775d4b96fe9f086ccb9933946219ebf4fe959ebd9224d3
3
- size 14709
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:323e1e9949439118ebc53215a98800c88f5564bca62341a82117e15308ea1242
3
- size 1465
 
 
 
 
last-checkpoint/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json DELETED
@@ -1,20 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "bos_token": "<|startoftext|>",
4
- "clean_up_tokenization_spaces": false,
5
- "eos_token": "<|im_end|>",
6
- "is_local": false,
7
- "legacy": false,
8
- "model_input_names": [
9
- "input_ids",
10
- "attention_mask"
11
- ],
12
- "model_max_length": 1000000000000000019884624838656,
13
- "pad_token": "<|pad|>",
14
- "padding_side": "right",
15
- "sp_model_kwargs": {},
16
- "spaces_between_special_tokens": false,
17
- "tokenizer_class": "TokenizersBackend",
18
- "use_default_system_prompt": false,
19
- "use_fast": true
20
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e1054e6e7ce279a673725c2b632faa41f3bb2be2ae60c9f1cbc4bf38a253be6
3
- size 5713