Instructions to use Thomas-lemoullec/mistral_7b_vertexQandA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Thomas-lemoullec/mistral_7b_vertexQandA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1") model = PeftModel.from_pretrained(base_model, "Thomas-lemoullec/mistral_7b_vertexQandA") - Notebooks
- Google Colab
- Kaggle
Commit ·
91f82a0
1
Parent(s): 02d3ee7
Upload model
Browse files- README.md +1 -1
- adapter_config.json +6 -6
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -215,4 +215,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 215 |
|
| 216 |
### Framework versions
|
| 217 |
|
| 218 |
-
- PEFT 0.
|
|
|
|
| 215 |
|
| 216 |
### Framework versions
|
| 217 |
|
| 218 |
+
- PEFT 0.7.0
|
adapter_config.json
CHANGED
|
@@ -19,13 +19,13 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"
|
| 23 |
-
"o_proj",
|
| 24 |
-
"k_proj",
|
| 25 |
-
"v_proj",
|
| 26 |
-
"up_proj",
|
| 27 |
"q_proj",
|
| 28 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"down_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"q_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"v_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b8869facad254aef50f4f58df105c2b709ac169228d7caf7b8337a7e90b40a0
|
| 3 |
size 83945296
|