Upload model
Browse files- README.md +36 -0
- adapter_config.json +2 -2
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -233,4 +233,40 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 233 |
### Framework versions
|
| 234 |
|
| 235 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 236 |
- PEFT 0.7.0.dev0
|
|
|
|
| 233 |
### Framework versions
|
| 234 |
|
| 235 |
|
| 236 |
+
- PEFT 0.7.0.dev0
|
| 237 |
+
## Training procedure
|
| 238 |
+
|
| 239 |
+
|
| 240 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 241 |
+
- load_in_8bit: False
|
| 242 |
+
- load_in_4bit: True
|
| 243 |
+
- llm_int8_threshold: 6.0
|
| 244 |
+
- llm_int8_skip_modules: None
|
| 245 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 246 |
+
- llm_int8_has_fp16_weight: False
|
| 247 |
+
- bnb_4bit_quant_type: nf4
|
| 248 |
+
- bnb_4bit_use_double_quant: True
|
| 249 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 250 |
+
|
| 251 |
+
### Framework versions
|
| 252 |
+
|
| 253 |
+
|
| 254 |
+
- PEFT 0.7.0.dev0
|
| 255 |
+
## Training procedure
|
| 256 |
+
|
| 257 |
+
|
| 258 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 259 |
+
- load_in_8bit: False
|
| 260 |
+
- load_in_4bit: True
|
| 261 |
+
- llm_int8_threshold: 6.0
|
| 262 |
+
- llm_int8_skip_modules: None
|
| 263 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 264 |
+
- llm_int8_has_fp16_weight: False
|
| 265 |
+
- bnb_4bit_quant_type: nf4
|
| 266 |
+
- bnb_4bit_use_double_quant: True
|
| 267 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 268 |
+
|
| 269 |
+
### Framework versions
|
| 270 |
+
|
| 271 |
+
|
| 272 |
- PEFT 0.7.0.dev0
|
adapter_config.json
CHANGED
|
@@ -16,10 +16,10 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"self_attn.k_proj",
|
| 20 |
"self_attn.v_proj",
|
| 21 |
"self_attn.o_proj",
|
| 22 |
-
"self_attn.q_proj"
|
|
|
|
| 23 |
],
|
| 24 |
"task_type": "CAUSAL_LM"
|
| 25 |
}
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
|
|
|
| 19 |
"self_attn.v_proj",
|
| 20 |
"self_attn.o_proj",
|
| 21 |
+
"self_attn.q_proj",
|
| 22 |
+
"self_attn.k_proj"
|
| 23 |
],
|
| 24 |
"task_type": "CAUSAL_LM"
|
| 25 |
}
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18085517
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42b1c7a14732eee1b06ec99315f1287d693d4fb552c023705dacec18ce445e2e
|
| 3 |
size 18085517
|