Commit
·
253da8a
1
Parent(s):
145bdf9
End of training
Browse files- README.md +19 -0
- adapter_config.json +2 -2
- adapter_model.bin +1 -1
- tokenizer.json +16 -2
README.md
CHANGED
@@ -236,4 +236,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
236 |
### Framework versions
|
237 |
|
238 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
239 |
- PEFT 0.6.2
|
|
|
236 |
### Framework versions
|
237 |
|
238 |
|
239 |
+
- PEFT 0.6.2
|
240 |
+
## Training procedure
|
241 |
+
|
242 |
+
|
243 |
+
The following `bitsandbytes` quantization config was used during training:
|
244 |
+
- quant_method: bitsandbytes
|
245 |
+
- load_in_8bit: False
|
246 |
+
- load_in_4bit: True
|
247 |
+
- llm_int8_threshold: 6.0
|
248 |
+
- llm_int8_skip_modules: None
|
249 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
250 |
+
- llm_int8_has_fp16_weight: False
|
251 |
+
- bnb_4bit_quant_type: nf4
|
252 |
+
- bnb_4bit_use_double_quant: True
|
253 |
+
- bnb_4bit_compute_dtype: bfloat16
|
254 |
+
|
255 |
+
### Framework versions
|
256 |
+
|
257 |
+
|
258 |
- PEFT 0.6.2
|
adapter_config.json
CHANGED
@@ -16,8 +16,8 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
20 |
-
"
|
21 |
],
|
22 |
"task_type": "CAUSAL_LM"
|
23 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
],
|
22 |
"task_type": "CAUSAL_LM"
|
23 |
}
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8434826
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2e2e4ae61fdda4ca22a3f0316bd17ed1f227df0b472f80b044adadbca845c94
|
3 |
size 8434826
|
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": 256,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 256
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 0,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "<unk>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|