Commit
•
d8c354f
1
Parent(s):
54eb473
Training in progress, step 500
Browse files- config.json +3 -3
- model.safetensors +1 -1
- tokenizer_config.json +7 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"JambaForCausalLM"
|
5 |
],
|
@@ -7,9 +7,9 @@
|
|
7 |
"attn_layer_offset": 4,
|
8 |
"attn_layer_period": 8,
|
9 |
"auto_map": {
|
10 |
-
"AutoConfig": "
|
11 |
"AutoModel": "ai21labs/Jamba-v0.1--modeling_jamba.JambaModel",
|
12 |
-
"AutoModelForCausalLM": "
|
13 |
"AutoModelForSequenceClassification": "ai21labs/Jamba-v0.1--model.JambaForSequenceClassification"
|
14 |
},
|
15 |
"bos_token_id": 1,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "PyJamba1B/checkpoint-265000",
|
3 |
"architectures": [
|
4 |
"JambaForCausalLM"
|
5 |
],
|
|
|
7 |
"attn_layer_offset": 4,
|
8 |
"attn_layer_period": 8,
|
9 |
"auto_map": {
|
10 |
+
"AutoConfig": "configuration_jamba.JambaConfig",
|
11 |
"AutoModel": "ai21labs/Jamba-v0.1--modeling_jamba.JambaModel",
|
12 |
+
"AutoModelForCausalLM": "modeling_jamba.JambaForCausalLM",
|
13 |
"AutoModelForSequenceClassification": "ai21labs/Jamba-v0.1--model.JambaForSequenceClassification"
|
14 |
},
|
15 |
"bos_token_id": 1,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2039780704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ef35299fdad7c9943ff2813779e8c46ea8e50805c3c469ef39758059b404624
|
3 |
size 2039780704
|
tokenizer_config.json
CHANGED
@@ -38,10 +38,17 @@
|
|
38 |
"bos_token": "<|startoftext|>",
|
39 |
"clean_up_tokenization_spaces": false,
|
40 |
"eos_token": "<|endoftext|>",
|
|
|
41 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
42 |
"pad_token": "<|pad|>",
|
|
|
|
|
43 |
"spaces_between_special_tokens": false,
|
|
|
44 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
45 |
"unk_token": "<|unk|>",
|
46 |
"use_default_system_prompt": false
|
47 |
}
|
|
|
38 |
"bos_token": "<|startoftext|>",
|
39 |
"clean_up_tokenization_spaces": false,
|
40 |
"eos_token": "<|endoftext|>",
|
41 |
+
"max_length": 8192,
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_to_multiple_of": null,
|
44 |
"pad_token": "<|pad|>",
|
45 |
+
"pad_token_type_id": 0,
|
46 |
+
"padding_side": "left",
|
47 |
"spaces_between_special_tokens": false,
|
48 |
+
"stride": 0,
|
49 |
"tokenizer_class": "LlamaTokenizer",
|
50 |
+
"truncation_side": "right",
|
51 |
+
"truncation_strategy": "longest_first",
|
52 |
"unk_token": "<|unk|>",
|
53 |
"use_default_system_prompt": false
|
54 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aab7473090ad215f01ae27b884f529a64b7e25ed3088c0e3bc5b9257406e4e92
|
3 |
size 4920
|