Commit
·
10677fc
1
Parent(s):
67a6122
Upload model
Browse files- README.md +24 -0
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -257,6 +257,28 @@ The following `bitsandbytes` quantization config was used during training:
|
|
257 |
- bnb_4bit_use_double_quant: False
|
258 |
- bnb_4bit_compute_dtype: float16
|
259 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
260 |
The following `bitsandbytes` quantization config was used during training:
|
261 |
- load_in_8bit: False
|
262 |
- load_in_4bit: True
|
@@ -292,5 +314,7 @@ The following `bitsandbytes` quantization config was used during training:
|
|
292 |
- PEFT 0.4.0
|
293 |
- PEFT 0.4.0
|
294 |
- PEFT 0.4.0
|
|
|
|
|
295 |
|
296 |
- PEFT 0.4.0
|
|
|
257 |
- bnb_4bit_use_double_quant: False
|
258 |
- bnb_4bit_compute_dtype: float16
|
259 |
|
260 |
+
The following `bitsandbytes` quantization config was used during training:
|
261 |
+
- load_in_8bit: False
|
262 |
+
- load_in_4bit: True
|
263 |
+
- llm_int8_threshold: 6.0
|
264 |
+
- llm_int8_skip_modules: None
|
265 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
266 |
+
- llm_int8_has_fp16_weight: False
|
267 |
+
- bnb_4bit_quant_type: nf4
|
268 |
+
- bnb_4bit_use_double_quant: False
|
269 |
+
- bnb_4bit_compute_dtype: float16
|
270 |
+
|
271 |
+
The following `bitsandbytes` quantization config was used during training:
|
272 |
+
- load_in_8bit: False
|
273 |
+
- load_in_4bit: True
|
274 |
+
- llm_int8_threshold: 6.0
|
275 |
+
- llm_int8_skip_modules: None
|
276 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
277 |
+
- llm_int8_has_fp16_weight: False
|
278 |
+
- bnb_4bit_quant_type: nf4
|
279 |
+
- bnb_4bit_use_double_quant: False
|
280 |
+
- bnb_4bit_compute_dtype: float16
|
281 |
+
|
282 |
The following `bitsandbytes` quantization config was used during training:
|
283 |
- load_in_8bit: False
|
284 |
- load_in_4bit: True
|
|
|
314 |
- PEFT 0.4.0
|
315 |
- PEFT 0.4.0
|
316 |
- PEFT 0.4.0
|
317 |
+
- PEFT 0.4.0
|
318 |
+
- PEFT 0.4.0
|
319 |
|
320 |
- PEFT 0.4.0
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 134263757
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79b64bf1d4757c70e4105eb044e2f2b8a8910b359cadeeb74f199a95feabaed1
|
3 |
size 134263757
|