Upload model
Browse files- README.md +0 -38
- adapter_config.json +8 -5
- adapter_model.safetensors +2 -2
README.md
CHANGED
@@ -217,42 +217,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
217 |
### Framework versions
|
218 |
|
219 |
|
220 |
-
- PEFT 0.6.2
|
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: False
|
234 |
-
- bnb_4bit_compute_dtype: bfloat16
|
235 |
-
|
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: False
|
253 |
-
- bnb_4bit_compute_dtype: bfloat16
|
254 |
-
|
255 |
-
### Framework versions
|
256 |
-
|
257 |
-
|
258 |
- PEFT 0.6.2
|
|
|
217 |
### Framework versions
|
218 |
|
219 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
- PEFT 0.6.2
|
adapter_config.json
CHANGED
@@ -9,18 +9,21 @@
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"lora_alpha": 16,
|
12 |
-
"lora_dropout": 0.
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
-
"r":
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
|
|
|
|
|
|
20 |
"v_proj",
|
21 |
-
"o_proj",
|
22 |
"gate_proj",
|
23 |
-
"
|
|
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"lm_head",
|
20 |
+
"q_proj",
|
21 |
+
"up_proj",
|
22 |
+
"down_proj",
|
23 |
"v_proj",
|
|
|
24 |
"gate_proj",
|
25 |
+
"k_proj",
|
26 |
+
"o_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM"
|
29 |
}
|
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:b53fa764a5c88813feac666935cc4d8e7f2bd00acd92327b7b3084081ab091ac
|
3 |
+
size 85100592
|