Remove old files
Browse files- .gitattributes +0 -35
- README.md +0 -52
- adapter_config.json +0 -23
- adapter_model.safetensors +0 -3
- added_tokens.json +0 -5
- config.json +0 -25
- generation_config.json +0 -6
- model.safetensors +0 -3
- special_tokens_map.json +0 -30
- tokenizer.json +0 -0
- tokenizer.model +0 -3
- tokenizer_config.json +0 -68
- training_args.bin +0 -3
- training_params.json +0 -1
.gitattributes
DELETED
@@ -1,35 +0,0 @@
|
|
1 |
-
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
-
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
-
*.xz 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
README.md
DELETED
@@ -1,52 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
tags:
|
4 |
-
- autotrain
|
5 |
-
- text-generation
|
6 |
-
base_model: Locutusque/TinyMistral-248M
|
7 |
-
datasets:
|
8 |
-
- tatsu-lab/alpaca
|
9 |
-
widget:
|
10 |
-
- text: |-
|
11 |
-
Find me a list of some nice places to visit around the world.
|
12 |
-
|
13 |
-
### Response:
|
14 |
-
- text: |-
|
15 |
-
Tell me a story.
|
16 |
-
Once upon a time...
|
17 |
-
|
18 |
-
### Response:
|
19 |
-
inference:
|
20 |
-
parameters:
|
21 |
-
max_new_tokens: 32
|
22 |
-
repetition_penalty: 1.15
|
23 |
-
do_sample: true
|
24 |
-
temperature: 0.5
|
25 |
-
top_p: 0.5
|
26 |
-
---
|
27 |
-
|
28 |
-
# Locutusque's TinyMistral-248M trained on the Alpaca dataset using AutoTrain
|
29 |
-
|
30 |
-
- Base model: [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M)
|
31 |
-
- Dataset: [tatsu-lab/alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca)
|
32 |
-
- Training: 2h under [these parameters](https://huggingface.co/Felladrin/TinyMistral-248M-Alpaca/blob/93533a5f190f79a8ad5e5a9765ce9ec498dfa5bd/training_params.json)
|
33 |
-
- Availability in other ML formats:
|
34 |
-
- GGUF: [afrideva/TinyMistral-248M-Alpaca-GGUF](https://huggingface.co/afrideva/TinyMistral-248M-Alpaca-GGUF)
|
35 |
-
- ONNX: [Felladrin/onnx-int8-TinyMistral-248M-Alpaca](https://huggingface.co/Felladrin/onnx-int8-TinyMistral-248M-Alpaca)
|
36 |
-
|
37 |
-
## Recommended Prompt Format
|
38 |
-
|
39 |
-
```
|
40 |
-
<instruction>
|
41 |
-
|
42 |
-
### Response:
|
43 |
-
```
|
44 |
-
|
45 |
-
## Recommended Inference Parameters
|
46 |
-
|
47 |
-
```yml
|
48 |
-
repetition_penalty: 1.15
|
49 |
-
do_sample: true
|
50 |
-
temperature: 0.5
|
51 |
-
top_p: 0.5
|
52 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter_config.json
DELETED
@@ -1,23 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"alpha_pattern": {},
|
3 |
-
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "Locutusque/TinyMistral-248M",
|
5 |
-
"bias": "none",
|
6 |
-
"fan_in_fan_out": false,
|
7 |
-
"inference_mode": true,
|
8 |
-
"init_lora_weights": true,
|
9 |
-
"layers_pattern": null,
|
10 |
-
"layers_to_transform": null,
|
11 |
-
"lora_alpha": 32,
|
12 |
-
"lora_dropout": 0.1,
|
13 |
-
"modules_to_save": null,
|
14 |
-
"peft_type": "LORA",
|
15 |
-
"r": 16,
|
16 |
-
"rank_pattern": {},
|
17 |
-
"revision": null,
|
18 |
-
"target_modules": [
|
19 |
-
"v_proj",
|
20 |
-
"q_proj"
|
21 |
-
],
|
22 |
-
"task_type": "CAUSAL_LM"
|
23 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter_model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:0a72090cf094386524699f1ffde78dbfa49612d01ce25362daf8359a6c9c9658
|
3 |
-
size 2562232
|
|
|
|
|
|
|
|
added_tokens.json
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"<|bos|>": 32000,
|
3 |
-
"<|endoftext|>": 32001,
|
4 |
-
"[PAD]": 32002
|
5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
@@ -1,25 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "Locutusque/TinyMistral-248M",
|
3 |
-
"architectures": [
|
4 |
-
"MistralForCausalLM"
|
5 |
-
],
|
6 |
-
"bos_token_id": 1,
|
7 |
-
"eos_token_id": 2,
|
8 |
-
"hidden_act": "silu",
|
9 |
-
"hidden_size": 1024,
|
10 |
-
"initializer_range": 0.02,
|
11 |
-
"intermediate_size": 4096,
|
12 |
-
"max_position_embeddings": 32768,
|
13 |
-
"model_type": "mistral",
|
14 |
-
"num_attention_heads": 32,
|
15 |
-
"num_hidden_layers": 12,
|
16 |
-
"num_key_value_heads": 8,
|
17 |
-
"rms_norm_eps": 1e-06,
|
18 |
-
"rope_theta": 10000.0,
|
19 |
-
"sliding_window": 32,
|
20 |
-
"tie_word_embeddings": false,
|
21 |
-
"torch_dtype": "float16",
|
22 |
-
"transformers_version": "4.35.2",
|
23 |
-
"use_cache": true,
|
24 |
-
"vocab_size": 32003
|
25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
generation_config.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 1,
|
4 |
-
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.35.2"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:11446cbb74a03bc7811be5e3e998a7bcea64a96f72286a9588b650d6ca0994dc
|
3 |
-
size 496052392
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
@@ -1,30 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<|bos|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
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
DELETED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
-
size 493443
|
|
|
|
|
|
|
|
tokenizer_config.json
DELETED
@@ -1,68 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "<unk>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<s>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "</s>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"32000": {
|
28 |
-
"content": "<|bos|>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"32001": {
|
36 |
-
"content": "<|endoftext|>",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"32002": {
|
44 |
-
"content": "[PAD]",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
-
}
|
51 |
-
},
|
52 |
-
"additional_special_tokens": [],
|
53 |
-
"bos_token": "<|bos|>",
|
54 |
-
"clean_up_tokenization_spaces": false,
|
55 |
-
"eos_token": "<|endoftext|>",
|
56 |
-
"legacy": true,
|
57 |
-
"max_length": 1536,
|
58 |
-
"model_max_length": 1000000000000000019884624838656,
|
59 |
-
"pad_token": "[PAD]",
|
60 |
-
"sp_model_kwargs": {},
|
61 |
-
"spaces_between_special_tokens": false,
|
62 |
-
"stride": 0,
|
63 |
-
"tokenizer_class": "LlamaTokenizer",
|
64 |
-
"truncation_side": "right",
|
65 |
-
"truncation_strategy": "longest_first",
|
66 |
-
"unk_token": "<unk>",
|
67 |
-
"use_default_system_prompt": true
|
68 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b22e21c0170936f6869ad8d8ae1fa4cce19c0217ef64f5de8bc135e9591c3a8f
|
3 |
-
size 4600
|
|
|
|
|
|
|
|
training_params.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"model": "Locutusque/TinyMistral-248M", "data_path": "Felladrin/autotrain-data-k6w0-qx4m-hzdq", "project_name": "/tmp/model", "train_split": "train", "valid_split": null, "text_column": "autotrain_text", "rejected_text_column": null, "lr": 0.0002, "epochs": 3, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": true, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.1, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 2048, "repo_id": "Felladrin/k6w0-qx4m-hzdq-0", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": "Felladrin", "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": null}
|
|
|
|