Commit
•
3312b6f
1
Parent(s):
1d5ddf2
pavelmarcolian/llama-2-13b-echelon-faq-GPTQ
Browse files- README.md +8 -6
- adapter_config.json +6 -4
- adapter_model.safetensors +2 -2
- runs/Mar28_16-03-27_23480aaa79f7/events.out.tfevents.1711641832.23480aaa79f7.1647.0 +3 -0
- tokenizer.json +16 -2
- tokenizer_config.json +2 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
---
|
2 |
license: llama2
|
3 |
-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: llama-2-13b-echelon-faq-GPTQ
|
8 |
results: []
|
@@ -13,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# llama-2-13b-echelon-faq-GPTQ
|
15 |
|
16 |
-
This model is a fine-tuned version of [TheBloke/Llama-2-13b-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-13b-Chat-GPTQ) on
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -50,7 +51,8 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
-
-
|
54 |
-
-
|
55 |
-
-
|
56 |
-
-
|
|
|
|
1 |
---
|
2 |
license: llama2
|
3 |
+
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
base_model: TheBloke/Llama-2-13b-Chat-GPTQ
|
7 |
model-index:
|
8 |
- name: llama-2-13b-echelon-faq-GPTQ
|
9 |
results: []
|
|
|
14 |
|
15 |
# llama-2-13b-echelon-faq-GPTQ
|
16 |
|
17 |
+
This model is a fine-tuned version of [TheBloke/Llama-2-13b-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-13b-Chat-GPTQ) on the None dataset.
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
51 |
|
52 |
### Framework versions
|
53 |
|
54 |
+
- PEFT 0.10.0
|
55 |
+
- Transformers 4.38.2
|
56 |
+
- Pytorch 2.2.1+cu121
|
57 |
+
- Datasets 2.18.0
|
58 |
+
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path":
|
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 |
"loftq_config": {},
|
@@ -19,11 +20,12 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"q_proj",
|
23 |
"k_proj",
|
24 |
-
"
|
25 |
-
"
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
|
|
28 |
"use_rslora": false
|
29 |
}
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "TheBloke/Llama-2-13b-Chat-GPTQ",
|
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": {},
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"k_proj",
|
24 |
+
"o_proj",
|
25 |
+
"q_proj",
|
26 |
+
"v_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
+
"use_dora": false,
|
30 |
"use_rslora": false
|
31 |
}
|
adapter_model.safetensors
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:a898065722fe9005f47df2eabef7e75256678f0d3c535b51dd71cb807ad3871c
|
3 |
+
size 52471504
|
runs/Mar28_16-03-27_23480aaa79f7/events.out.tfevents.1711641832.23480aaa79f7.1647.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f65e30d11640be3257d6612ae5bc3ae1d6cf7d96b81f775b912f14c385dca2fd
|
3 |
+
size 38895
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 512
|
12 |
+
},
|
13 |
+
"direction": "Left",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 2,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "</s>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
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 sha256:7e43d2c301f97722de083bbe09f92ef6eef7e319f472cd73a2d0e55fe959edb6
|
3 |
+
size 4920
|