Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- config.json +2 -2
- generation_config.json +1 -1
- mamba-790m-chat.gguf +3 -0
- model.safetensors +1 -1
- optimizer.pt +2 -2
- rng_state_0.pth +2 -2
- rng_state_1.pth +2 -2
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +1 -1
- tokenizer.json +25 -4
- tokenizer_config.json +6 -0
- trainer_state.json +0 -0
- training_args.bin +2 -2
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
mamba-790m-chat.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "voidful/mamba-790m-
|
3 |
"architectures": [
|
4 |
"MambaForCausalLM"
|
5 |
],
|
@@ -31,7 +31,7 @@
|
|
31 |
"time_step_rank": 96,
|
32 |
"time_step_scale": 1.0,
|
33 |
"torch_dtype": "bfloat16",
|
34 |
-
"transformers_version": "4.
|
35 |
"use_bias": false,
|
36 |
"use_cache": true,
|
37 |
"use_conv_bias": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "voidful/mamba-790m-chat",
|
3 |
"architectures": [
|
4 |
"MambaForCausalLM"
|
5 |
],
|
|
|
31 |
"time_step_rank": 96,
|
32 |
"time_step_scale": 1.0,
|
33 |
"torch_dtype": "bfloat16",
|
34 |
+
"transformers_version": "4.41.2",
|
35 |
"use_bias": false,
|
36 |
"use_cache": true,
|
37 |
"use_conv_bias": true,
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 0,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 0,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.41.2"
|
7 |
}
|
mamba-790m-chat.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b2ff4c58e86c863c5777e2258b0fb5454bbc1f012cd32b5011dce1fb35b5fd6
|
3 |
+
size 1690030496
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1685432032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f3bcefe881c19a63b712301bd7770e676d632df914223adafc2eb7d1c80b4b7
|
3 |
size 1685432032
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c04b2046a900485c0fbd849bd9703446cd973a7a4e56cd869ea5e23198720269
|
3 |
+
size 1687495450
|
rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deae52a5d5be076c874536f0aade9a502c9a1b50a39e9feafd53759f4862709c
|
3 |
+
size 15920
|
rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afab10b429acf92e0244a895189614f02a5e7744234dfeb2dcf618f193df74ae
|
3 |
+
size 15920
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85faf95634676c14aee5e8b1dd2a48c129fee9b0a2237093440926e6c88d8d5e
|
3 |
+
size 15920
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbd5ba4e9d0e65b0e02d9257748f23754704f0221399f81c9c9c13192e40272d
|
3 |
+
size 15920
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bd9cce5c1921b68e37f81d030aee11ccc1594443c286c8ca3abbd35e6c0bcd2
|
3 |
+
size 15920
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5420e3f692f20fc11644e91f6ea935e2098125ef686be2629a80f8e3d37f80e5
|
3 |
+
size 15920
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09abd313620bc17205bb41c832419ab4e77fa2e14f6be06ee7fc297fe96705b7
|
3 |
+
size 15920
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa75be5ee01f8a9f7a5b5bdc90a525d191e87779cd922f427f6b8637d0841875
|
3 |
+
size 15920
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:177cd19791ffd6ffb0cdedadf3499d9bbbfc5d802ecbfe67163386a640b1719a
|
3 |
size 1064
|
tokenizer.json
CHANGED
@@ -276409,10 +276409,30 @@
|
|
276409 |
"use_regex": true
|
276410 |
},
|
276411 |
"post_processor": {
|
276412 |
-
"type": "
|
276413 |
-
"
|
276414 |
-
|
276415 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
276416 |
},
|
276417 |
"decoder": {
|
276418 |
"type": "ByteLevel",
|
@@ -276428,6 +276448,7 @@
|
|
276428 |
"end_of_word_suffix": null,
|
276429 |
"fuse_unk": false,
|
276430 |
"byte_fallback": false,
|
|
|
276431 |
"vocab": {
|
276432 |
"<|endoftext|>": 0,
|
276433 |
"<|padding|>": 1,
|
|
|
276409 |
"use_regex": true
|
276410 |
},
|
276411 |
"post_processor": {
|
276412 |
+
"type": "TemplateProcessing",
|
276413 |
+
"single": [
|
276414 |
+
{
|
276415 |
+
"Sequence": {
|
276416 |
+
"id": "A",
|
276417 |
+
"type_id": 0
|
276418 |
+
}
|
276419 |
+
}
|
276420 |
+
],
|
276421 |
+
"pair": [
|
276422 |
+
{
|
276423 |
+
"Sequence": {
|
276424 |
+
"id": "A",
|
276425 |
+
"type_id": 0
|
276426 |
+
}
|
276427 |
+
},
|
276428 |
+
{
|
276429 |
+
"Sequence": {
|
276430 |
+
"id": "B",
|
276431 |
+
"type_id": 1
|
276432 |
+
}
|
276433 |
+
}
|
276434 |
+
],
|
276435 |
+
"special_tokens": {}
|
276436 |
},
|
276437 |
"decoder": {
|
276438 |
"type": "ByteLevel",
|
|
|
276448 |
"end_of_word_suffix": null,
|
276449 |
"fuse_unk": false,
|
276450 |
"byte_fallback": false,
|
276451 |
+
"ignore_merges": false,
|
276452 |
"vocab": {
|
276453 |
"<|endoftext|>": 0,
|
276454 |
"<|padding|>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
@@ -245685,8 +245687,12 @@
|
|
245685 |
"bos_token": "<|endoftext|>",
|
245686 |
"clean_up_tokenization_spaces": true,
|
245687 |
"eos_token": "<|endoftext|>",
|
|
|
245688 |
"model_max_length": 1000000000000000019884624838656,
|
245689 |
"pad_token": "<|endoftext|>",
|
|
|
245690 |
"tokenizer_class": "GPTNeoXTokenizer",
|
|
|
|
|
245691 |
"unk_token": "<|endoftext|>"
|
245692 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
"add_prefix_space": false,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
|
|
245687 |
"bos_token": "<|endoftext|>",
|
245688 |
"clean_up_tokenization_spaces": true,
|
245689 |
"eos_token": "<|endoftext|>",
|
245690 |
+
"max_length": 10000,
|
245691 |
"model_max_length": 1000000000000000019884624838656,
|
245692 |
"pad_token": "<|endoftext|>",
|
245693 |
+
"stride": 0,
|
245694 |
"tokenizer_class": "GPTNeoXTokenizer",
|
245695 |
+
"truncation_side": "right",
|
245696 |
+
"truncation_strategy": "longest_first",
|
245697 |
"unk_token": "<|endoftext|>"
|
245698 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a8f6ce00176d186cdc5f79cd71344b2d0ffaaf948a0559c63e80ff9fe39ce83
|
3 |
+
size 5368
|