hushell commited on
Commit
3cd3403
1 Parent(s): c94f5da

Training in progress, step 100

Browse files
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ondevicellm/tinyllama_mole_v1",
3
+ "adapter_alpha": 0.01,
4
+ "adapter_dim": 16,
5
+ "architectures": [
6
+ "MixtralMoleForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "auto_map": {
11
+ "AutoConfig": "ondevicellm/tinyllama_mole_v1--configuration_mixtral_mole.MixtralMoleConfig",
12
+ "AutoModel": "ondevicellm/tinyllama_mole_v1--modeling_mixtral_mole.MixtralMoleModel",
13
+ "AutoModelForCausalLM": "ondevicellm/tinyllama_mole_v1--modeling_mixtral_mole.MixtralMoleForCausalLM"
14
+ },
15
+ "bos_token_id": 1,
16
+ "eos_token_id": 2,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 2048,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 5632,
21
+ "max_position_embeddings": 2048,
22
+ "model_type": "mixtralmole",
23
+ "num_attention_heads": 32,
24
+ "num_experts_per_tok": 2,
25
+ "num_hidden_layers": 22,
26
+ "num_key_value_heads": 4,
27
+ "num_local_experts": 8,
28
+ "output_router_logits": true,
29
+ "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": null,
32
+ "rope_theta": 10000.0,
33
+ "router_aux_loss_coef": 0.05,
34
+ "sliding_window": null,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.37.0",
38
+ "trust_remote_code": true,
39
+ "use_cache": false,
40
+ "vocab_size": 32000
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce72cd29d1dfbce6dfc1b68e9a6edddd7e49fdebbdc597c217e11eeff3a03167
3
+ size 2223960880
runs/Jan29_16-09-48_main1/events.out.tfevents.1706545612.main1.82737.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa3a4a4c4b22b13e6dab180535d59b4f2e6c932c4e94b66740549556ea62d06
3
+ size 8370
runs/Jan29_17-10-56_main1/events.out.tfevents.1706548384.main1.84367.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08d3e50ba5e8fee58a48d10da8f988d61bc41e1b2252f3637f0b6666738672a6
3
+ size 8636
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "<s>",
37
+ "padding_side": "left",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7554a2284bee58fe2adf584e3c6544d7090c3e51481b2f28a0151d13119d713
3
+ size 5816