Model save
Browse files- README.md +45 -11
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- tokenizer.json +1 -6
- tokenizer_config.json +1 -5
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,23 +1,57 @@
|
|
1 |
---
|
2 |
base_model: unsloth/llama-2-7b-chat-bnb-4bit
|
3 |
-
|
4 |
-
- en
|
5 |
license: apache-2.0
|
6 |
tags:
|
7 |
-
- text-generation-inference
|
8 |
-
- transformers
|
9 |
- unsloth
|
10 |
-
- llama
|
11 |
- trl
|
12 |
- sft
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
-
|
|
|
16 |
|
17 |
-
|
18 |
-
- **License:** apache-2.0
|
19 |
-
- **Finetuned from model :** unsloth/llama-2-7b-chat-bnb-4bit
|
20 |
|
21 |
-
This
|
22 |
|
23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
base_model: unsloth/llama-2-7b-chat-bnb-4bit
|
3 |
+
library_name: peft
|
|
|
4 |
license: apache-2.0
|
5 |
tags:
|
|
|
|
|
6 |
- unsloth
|
|
|
7 |
- trl
|
8 |
- sft
|
9 |
+
- generated_from_trainer
|
10 |
+
model-index:
|
11 |
+
- name: Llama-2-7b-chat-hf-hotel-booking-assistant
|
12 |
+
results: []
|
13 |
---
|
14 |
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
+
# Llama-2-7b-chat-hf-hotel-booking-assistant
|
|
|
|
|
19 |
|
20 |
+
This model is a fine-tuned version of [unsloth/llama-2-7b-chat-bnb-4bit](https://huggingface.co/unsloth/llama-2-7b-chat-bnb-4bit) on an unknown dataset.
|
21 |
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 2
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 8
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 10
|
48 |
+
- training_steps: 60
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- PEFT 0.11.1
|
54 |
+
- Transformers 4.41.2
|
55 |
+
- Pytorch 2.3.0+cu121
|
56 |
+
- Datasets 2.20.0
|
57 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-2-7b-chat-bnb-4bit",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": "unsloth",
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"up_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:047fe78e1e3f21ab4e0595a19bc7e25780602d8305792ba322d7df902abce0a5
|
3 |
+
size 159967880
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 2048,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
tokenizer_config.json
CHANGED
@@ -32,15 +32,11 @@
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": false,
|
35 |
-
"max_length": 2048,
|
36 |
"model_max_length": 4096,
|
37 |
"pad_token": "<unk>",
|
38 |
-
"padding_side": "
|
39 |
"sp_model_kwargs": {},
|
40 |
-
"stride": 0,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
42 |
-
"truncation_side": "right",
|
43 |
-
"truncation_strategy": "longest_first",
|
44 |
"unk_token": "<unk>",
|
45 |
"use_default_system_prompt": false
|
46 |
}
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": false,
|
|
|
35 |
"model_max_length": 4096,
|
36 |
"pad_token": "<unk>",
|
37 |
+
"padding_side": "right",
|
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 sha256:4df80b8e13ea13cda04c01234baa8cd80e5966c0a0bd1ded5e38597b8b967ff3
|
3 |
+
size 5176
|