Instructions to use VictorDCh/Llama-3-8B-Instruct-spider-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use VictorDCh/Llama-3-8B-Instruct-spider-4 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct") model = PeftModel.from_pretrained(base_model, "VictorDCh/Llama-3-8B-Instruct-spider-4") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 2
Browse files
adapter_config.json
CHANGED
|
@@ -20,12 +20,12 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"q_proj",
|
|
|
|
|
|
|
| 24 |
"v_proj",
|
| 25 |
-
"down_proj",
|
| 26 |
"up_proj",
|
| 27 |
-
"k_proj",
|
| 28 |
-
"gate_proj",
|
| 29 |
"o_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
"q_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
"v_proj",
|
|
|
|
| 28 |
"up_proj",
|
|
|
|
|
|
|
| 29 |
"o_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3443619040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd344a87affae0eeda818e6f1af80fed0f617ef394a69486c2c2ac7bcdec8eb7
|
| 3 |
size 3443619040
|
runs/Jul09_09-56-59_0168cc42f06b/events.out.tfevents.1720511838.0168cc42f06b.12363.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53800c9de47df6655a7b9498388553e6b2b5e2669078ef48eacb677c89c7856d
|
| 3 |
+
size 48880
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1a7ba62e8ddcb84f11a4a618f8e2012f1467169230ed3126bd65ea81b0105b4
|
| 3 |
size 5048
|