Upload folder using huggingface_hub
Browse files- README.md +21 -0
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +15 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- lora
|
7 |
+
- adapters
|
8 |
+
- tinyllama
|
9 |
+
---
|
10 |
+
|
11 |
+
# TinyLlama YouTube Replies (LoRA)
|
12 |
+
|
13 |
+
LoRA adapters to fine-tune `TinyLlama-1.1B-Chat-v1.0` for generating concise, friendly replies to AI/ML YouTube comments.
|
14 |
+
|
15 |
+
## Usage
|
16 |
+
```python
|
17 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
18 |
+
from peft import PeftModel
|
19 |
+
base = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
|
20 |
+
tok = AutoTokenizer.from_pretrained("your-username/tinyllama-youtube-replies-lora")
|
21 |
+
model = PeftModel.from_pretrained(base, "your-username/tinyllama-youtube-replies-lora")
|
adapter_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 32,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.05,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"qalora_group_size": 16,
|
24 |
+
"r": 16,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"q_proj",
|
29 |
+
"up_proj",
|
30 |
+
"gate_proj",
|
31 |
+
"v_proj",
|
32 |
+
"o_proj",
|
33 |
+
"k_proj",
|
34 |
+
"down_proj"
|
35 |
+
],
|
36 |
+
"target_parameters": null,
|
37 |
+
"task_type": "CAUSAL_LM",
|
38 |
+
"trainable_token_indices": null,
|
39 |
+
"use_dora": false,
|
40 |
+
"use_qalora": false,
|
41 |
+
"use_rslora": false
|
42 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2eed4bab92fdeb70a0f6816c9315cc6333a68f06de02e7d8f9f4fa787a39a0fb
|
3 |
+
size 50503544
|
chat_template.jinja
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{% for message in messages %}
|
2 |
+
{% if message['role'] == 'user' %}
|
3 |
+
{{ '<|user|>
|
4 |
+
' + message['content'] + eos_token }}
|
5 |
+
{% elif message['role'] == 'system' %}
|
6 |
+
{{ '<|system|>
|
7 |
+
' + message['content'] + eos_token }}
|
8 |
+
{% elif message['role'] == 'assistant' %}
|
9 |
+
{{ '<|assistant|>
|
10 |
+
' + message['content'] + eos_token }}
|
11 |
+
{% endif %}
|
12 |
+
{% if loop.last and add_generation_prompt %}
|
13 |
+
{{ '<|assistant|>' }}
|
14 |
+
{% endif %}
|
15 |
+
{% endfor %}
|
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_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"extra_special_tokens": {},
|
35 |
+
"legacy": false,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|