Hugging Face's logo

meihant
/
AnonymousModel-mht

Text Generation
Transformers
Safetensors
English
qwen3_5
pretraining
Model card Files
xet
 Community
meihant commited on
Commit
19a3e6d
·
verified ·
1 Parent(s): b224605

Add models/KLLM-SmolLM2-360M-20B/checkpoints/2B artifacts 0-5

Browse files
Files changed (6) hide show
  1. models/KLLM-SmolLM2-360M-20B/checkpoints/2B/config.json +34 -0
  2. models/KLLM-SmolLM2-360M-20B/checkpoints/2B/generation_config.json +9 -0
  3. models/KLLM-SmolLM2-360M-20B/checkpoints/2B/model.safetensors +3 -0
  4. models/KLLM-SmolLM2-360M-20B/checkpoints/2B/tokenizer.json +0 -0
  5. models/KLLM-SmolLM2-360M-20B/checkpoints/2B/tokenizer_config.json +20 -0
  6. models/KLLM-SmolLM2-360M-20B/checkpoints/2B/training_progress.json +27 -0
models/KLLM-SmolLM2-360M-20B/checkpoints/2B/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 0,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 960,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2560,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 15,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 5,
22
+ "pad_token_id": null,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_parameters": {
27
+ "rope_theta": 100000,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.6.2",
32
+ "use_cache": true,
33
+ "vocab_size": 49266
34
+ }
models/KLLM-SmolLM2-360M-20B/checkpoints/2B/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.6.2",
8
+ "use_cache": true
9
+ }
models/KLLM-SmolLM2-360M-20B/checkpoints/2B/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f4c96435dab2fc011d80b1dc3970d8b03c26538f38a90f14c1d4b3e4ee5af03
3
+ size 723893792
models/KLLM-SmolLM2-360M-20B/checkpoints/2B/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/KLLM-SmolLM2-360M-20B/checkpoints/2B/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<FACT>",
10
+ "</FACT>",
11
+ "<FACT-q>"
12
+ ],
13
+ "is_local": true,
14
+ "local_files_only": false,
15
+ "model_max_length": 8192,
16
+ "pad_token": "<|endoftext|>",
17
+ "tokenizer_class": "GPT2Tokenizer",
18
+ "unk_token": "<|endoftext|>",
19
+ "vocab_size": 49152
20
+ }
models/KLLM-SmolLM2-360M-20B/checkpoints/2B/training_progress.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 3989,
3
+ "records": 4898104,
4
+ "retained_source_tokens": 2000000031,
5
+ "training_tokens": 2080118116,
6
+ "question_tokens": 4898104,
7
+ "seconds": 6056.634463310242,
8
+ "completed_segments": 1,
9
+ "job_ids": [
10
+ "2724351"
11
+ ],
12
+ "checkpoint_unix_time": 1794105134.7246706,
13
+ "job_id": "2724351",
14
+ "source_manifest_sha256": "3467ec6846c9a44f645a2d387ed158f5f5f8f1898e5e5945a318f829037ee6f0",
15
+ "final": false,
16
+ "passed": true,
17
+ "training_gpu_hours": 6.729593848122491,
18
+ "source_budget_tokens": 2000000031,
19
+ "per_rank_records": [
20
+ 1224324,
21
+ 1224674,
22
+ 1224005,
23
+ 1225101
24
+ ],
25
+ "checkpoint_kind": "evaluation",
26
+ "resumable": false
27
+ }