Commit
·
e9501ec
1
Parent(s):
f5c999a
Training in progress, step 371
Browse files- README.md +38 -0
- adapter_config.json +5 -5
- adapter_model.bin +1 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -217,4 +217,42 @@ The following `bitsandbytes` quantization config was used during training:
|
|
217 |
### Framework versions
|
218 |
|
219 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
- PEFT 0.6.0
|
|
|
217 |
### Framework versions
|
218 |
|
219 |
|
220 |
+
- PEFT 0.6.0
|
221 |
+
## Training procedure
|
222 |
+
|
223 |
+
|
224 |
+
The following `bitsandbytes` quantization config was used during training:
|
225 |
+
- quant_method: bitsandbytes
|
226 |
+
- load_in_8bit: False
|
227 |
+
- load_in_4bit: True
|
228 |
+
- llm_int8_threshold: 6.0
|
229 |
+
- llm_int8_skip_modules: None
|
230 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
231 |
+
- llm_int8_has_fp16_weight: False
|
232 |
+
- bnb_4bit_quant_type: nf4
|
233 |
+
- bnb_4bit_use_double_quant: True
|
234 |
+
- bnb_4bit_compute_dtype: bfloat16
|
235 |
+
|
236 |
+
### Framework versions
|
237 |
+
|
238 |
+
|
239 |
+
- PEFT 0.6.0
|
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 0.6.0
|
adapter_config.json
CHANGED
@@ -16,13 +16,13 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"v_proj",
|
20 |
-
"o_proj",
|
21 |
"up_proj",
|
22 |
-
"k_proj",
|
23 |
-
"q_proj",
|
24 |
"gate_proj",
|
25 |
-
"
|
|
|
|
|
|
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
|
|
19 |
"up_proj",
|
|
|
|
|
20 |
"gate_proj",
|
21 |
+
"q_proj",
|
22 |
+
"down_proj",
|
23 |
+
"o_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2684516749
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a78838c8b8d7eb10dfddd5ef0b7ecea3e62942a47463197ed003ce0731ec042a
|
3 |
size 2684516749
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2684416208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64608642dd16d637ef0402115413379b846dd17bd41744a36caf0c1ff87226fd
|
3 |
size 2684416208
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4667
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1273686c877ee721e9b6516eb7c7c2b5556db8850f8fc880a665322b14dae18
|
3 |
size 4667
|