Model save
Browse files- README.md +12 -6
- adapter_config.json +7 -3
- adapter_model.safetensors +1 -1
- runs/May18_14-29-11_d8da557e34ee/events.out.tfevents.1716042579.d8da557e34ee.10821.0 +3 -0
- step_0/README.md +4 -140
- step_0/adapter_config.json +7 -3
- step_0/adapter_model.safetensors +1 -1
- step_0/tokenizer_config.json +2 -0
- step_0/training_args.bin +2 -2
- tokenizer_config.json +2 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,8 +1,13 @@
|
|
1 |
---
|
2 |
license: llama2
|
3 |
-
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: llama2-7b-sft-lora
|
8 |
results: []
|
@@ -13,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# llama2-7b-sft-lora
|
15 |
|
16 |
-
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -47,7 +52,8 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
-
-
|
51 |
-
-
|
52 |
-
-
|
53 |
-
-
|
|
|
|
1 |
---
|
2 |
license: llama2
|
3 |
+
library_name: peft
|
4 |
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- generator
|
10 |
+
base_model: meta-llama/Llama-2-7b-chat-hf
|
11 |
model-index:
|
12 |
- name: llama2-7b-sft-lora
|
13 |
results: []
|
|
|
18 |
|
19 |
# llama2-7b-sft-lora
|
20 |
|
21 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
+
- PEFT 0.8.2
|
56 |
+
- Transformers 4.37.2
|
57 |
+
- Pytorch 2.2.0+cu121
|
58 |
+
- Datasets 2.16.1
|
59 |
+
- Tokenizers 0.15.1
|
adapter_config.json
CHANGED
@@ -8,20 +8,24 @@
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
|
|
11 |
"lora_alpha": 16,
|
12 |
"lora_dropout": 0.1,
|
|
|
|
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 64,
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"up_proj",
|
20 |
"q_proj",
|
|
|
|
|
21 |
"k_proj",
|
22 |
"v_proj",
|
23 |
-
"down_proj",
|
24 |
"o_proj"
|
25 |
],
|
26 |
-
"task_type": "CAUSAL_LM"
|
|
|
27 |
}
|
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
"lora_alpha": 16,
|
13 |
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"q_proj",
|
23 |
+
"down_proj",
|
24 |
+
"up_proj",
|
25 |
"k_proj",
|
26 |
"v_proj",
|
|
|
27 |
"o_proj"
|
28 |
],
|
29 |
+
"task_type": "CAUSAL_LM",
|
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 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
|
3 |
size 258001832
|
runs/May18_14-29-11_d8da557e34ee/events.out.tfevents.1716042579.d8da557e34ee.10821.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e74276703e85f640833475048a7ad0e68c08cf403eebfe0bf32e167ad855697
|
3 |
+
size 4477
|
step_0/README.md
CHANGED
@@ -18,6 +18,7 @@ base_model: meta-llama/Llama-2-7b-chat-hf
|
|
18 |
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
|
|
21 |
- **Shared by [optional]:** [More Information Needed]
|
22 |
- **Model type:** [More Information Needed]
|
23 |
- **Language(s) (NLP):** [More Information Needed]
|
@@ -76,7 +77,7 @@ Use the code below to get started with the model.
|
|
76 |
|
77 |
### Training Data
|
78 |
|
79 |
-
<!-- This should link to a
|
80 |
|
81 |
[More Information Needed]
|
82 |
|
@@ -107,7 +108,7 @@ Use the code below to get started with the model.
|
|
107 |
|
108 |
#### Testing Data
|
109 |
|
110 |
-
<!-- This should link to a
|
111 |
|
112 |
[More Information Needed]
|
113 |
|
@@ -198,143 +199,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
198 |
[More Information Needed]
|
199 |
|
200 |
|
201 |
-
## Training procedure
|
202 |
-
|
203 |
-
|
204 |
-
### Framework versions
|
205 |
-
|
206 |
-
|
207 |
-
- PEFT 0.6.1
|
208 |
-
## Training procedure
|
209 |
-
|
210 |
-
|
211 |
-
### Framework versions
|
212 |
-
|
213 |
-
|
214 |
-
- PEFT 0.6.1
|
215 |
-
## Training procedure
|
216 |
-
|
217 |
-
|
218 |
-
### Framework versions
|
219 |
-
|
220 |
-
|
221 |
-
- PEFT 0.6.1
|
222 |
-
## Training procedure
|
223 |
-
|
224 |
-
|
225 |
-
### Framework versions
|
226 |
-
|
227 |
-
|
228 |
-
- PEFT 0.6.1
|
229 |
-
## Training procedure
|
230 |
-
|
231 |
-
|
232 |
-
### Framework versions
|
233 |
-
|
234 |
-
|
235 |
-
- PEFT 0.6.1
|
236 |
-
## Training procedure
|
237 |
-
|
238 |
-
|
239 |
-
### Framework versions
|
240 |
-
|
241 |
-
|
242 |
-
- PEFT 0.6.1
|
243 |
-
## Training procedure
|
244 |
-
|
245 |
-
|
246 |
-
### Framework versions
|
247 |
-
|
248 |
-
|
249 |
-
- PEFT 0.6.1
|
250 |
-
## Training procedure
|
251 |
-
|
252 |
-
|
253 |
-
### Framework versions
|
254 |
-
|
255 |
-
|
256 |
-
- PEFT 0.6.1
|
257 |
-
## Training procedure
|
258 |
-
|
259 |
-
|
260 |
-
### Framework versions
|
261 |
-
|
262 |
-
|
263 |
-
- PEFT 0.6.1
|
264 |
-
## Training procedure
|
265 |
-
|
266 |
-
|
267 |
-
### Framework versions
|
268 |
-
|
269 |
-
|
270 |
-
- PEFT 0.6.1
|
271 |
-
## Training procedure
|
272 |
-
|
273 |
-
|
274 |
-
### Framework versions
|
275 |
-
|
276 |
-
|
277 |
-
- PEFT 0.6.1
|
278 |
-
## Training procedure
|
279 |
-
|
280 |
-
|
281 |
-
### Framework versions
|
282 |
-
|
283 |
-
|
284 |
-
- PEFT 0.6.1
|
285 |
-
## Training procedure
|
286 |
-
|
287 |
-
|
288 |
### Framework versions
|
289 |
|
290 |
-
|
291 |
-
- PEFT 0.6.1
|
292 |
-
## Training procedure
|
293 |
-
|
294 |
-
|
295 |
-
### Framework versions
|
296 |
-
|
297 |
-
|
298 |
-
- PEFT 0.6.1
|
299 |
-
## Training procedure
|
300 |
-
|
301 |
-
|
302 |
-
### Framework versions
|
303 |
-
|
304 |
-
|
305 |
-
- PEFT 0.6.1
|
306 |
-
## Training procedure
|
307 |
-
|
308 |
-
|
309 |
-
### Framework versions
|
310 |
-
|
311 |
-
|
312 |
-
- PEFT 0.6.1
|
313 |
-
## Training procedure
|
314 |
-
|
315 |
-
|
316 |
-
### Framework versions
|
317 |
-
|
318 |
-
|
319 |
-
- PEFT 0.6.1
|
320 |
-
## Training procedure
|
321 |
-
|
322 |
-
|
323 |
-
### Framework versions
|
324 |
-
|
325 |
-
|
326 |
-
- PEFT 0.6.1
|
327 |
-
## Training procedure
|
328 |
-
|
329 |
-
|
330 |
-
### Framework versions
|
331 |
-
|
332 |
-
|
333 |
-
- PEFT 0.6.1
|
334 |
-
## Training procedure
|
335 |
-
|
336 |
-
|
337 |
-
### Framework versions
|
338 |
-
|
339 |
-
|
340 |
-
- PEFT 0.6.1
|
|
|
18 |
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
- **Shared by [optional]:** [More Information Needed]
|
23 |
- **Model type:** [More Information Needed]
|
24 |
- **Language(s) (NLP):** [More Information Needed]
|
|
|
77 |
|
78 |
### Training Data
|
79 |
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
|
|
108 |
|
109 |
#### Testing Data
|
110 |
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
|
113 |
[More Information Needed]
|
114 |
|
|
|
199 |
[More Information Needed]
|
200 |
|
201 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
202 |
### Framework versions
|
203 |
|
204 |
+
- PEFT 0.8.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
step_0/adapter_config.json
CHANGED
@@ -8,20 +8,24 @@
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
|
|
11 |
"lora_alpha": 16,
|
12 |
"lora_dropout": 0.1,
|
|
|
|
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 64,
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"up_proj",
|
20 |
"q_proj",
|
|
|
|
|
21 |
"k_proj",
|
22 |
"v_proj",
|
23 |
-
"down_proj",
|
24 |
"o_proj"
|
25 |
],
|
26 |
-
"task_type": "CAUSAL_LM"
|
|
|
27 |
}
|
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
"lora_alpha": 16,
|
13 |
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"q_proj",
|
23 |
+
"down_proj",
|
24 |
+
"up_proj",
|
25 |
"k_proj",
|
26 |
"v_proj",
|
|
|
27 |
"o_proj"
|
28 |
],
|
29 |
+
"task_type": "CAUSAL_LM",
|
30 |
+
"use_rslora": false
|
31 |
}
|
step_0/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
|
3 |
size 258001832
|
step_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>",
|
step_0/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 sha256:66fc9aef4095adcf1bc2468cd68db7d22e914d3e301405fc251afdb3b7a001d4
|
3 |
+
size 5688
|
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 sha256:66fc9aef4095adcf1bc2468cd68db7d22e914d3e301405fc251afdb3b7a001d4
|
3 |
+
size 5688
|