Instructions to use Ribin/medgemma-1.5-4b-it-sft-lora-crc100k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ribin/medgemma-1.5-4b-it-sft-lora-crc100k with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Ribin/medgemma-1.5-4b-it-sft-lora-crc100k", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1
Browse files
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: transformers
|
|
| 4 |
model_name: medgemma-1.5-4b-it-sft-lora-crc100k
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- trl
|
| 8 |
- sft
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
@@ -37,7 +37,7 @@ This model was trained with SFT.
|
|
| 37 |
|
| 38 |
- TRL: 0.29.0
|
| 39 |
- Transformers: 5.2.0
|
| 40 |
-
- Pytorch: 2.
|
| 41 |
- Datasets: 4.6.1
|
| 42 |
- Tokenizers: 0.22.2
|
| 43 |
|
|
|
|
| 4 |
model_name: medgemma-1.5-4b-it-sft-lora-crc100k
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- sft
|
| 8 |
+
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
|
|
| 37 |
|
| 38 |
- TRL: 0.29.0
|
| 39 |
- Transformers: 5.2.0
|
| 40 |
+
- Pytorch: 2.11.0+cu126
|
| 41 |
- Datasets: 4.6.1
|
| 42 |
- Tokenizers: 0.22.2
|
| 43 |
|
adapter_config.json
CHANGED
|
@@ -22,6 +22,7 @@
|
|
| 22 |
"megatron_config": null,
|
| 23 |
"megatron_core": "megatron.core",
|
| 24 |
"modules_to_save": [
|
|
|
|
| 25 |
"lm_head",
|
| 26 |
"embed_tokens"
|
| 27 |
],
|
|
@@ -32,16 +33,16 @@
|
|
| 32 |
"rank_pattern": {},
|
| 33 |
"revision": null,
|
| 34 |
"target_modules": [
|
| 35 |
-
"up_proj",
|
| 36 |
-
"o_proj",
|
| 37 |
-
"out_proj",
|
| 38 |
"gate_proj",
|
| 39 |
-
"
|
| 40 |
-
"v_proj",
|
| 41 |
-
"fc2",
|
| 42 |
"fc1",
|
|
|
|
| 43 |
"q_proj",
|
| 44 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
],
|
| 46 |
"target_parameters": null,
|
| 47 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 22 |
"megatron_config": null,
|
| 23 |
"megatron_core": "megatron.core",
|
| 24 |
"modules_to_save": [
|
| 25 |
+
"multi_modal_projector",
|
| 26 |
"lm_head",
|
| 27 |
"embed_tokens"
|
| 28 |
],
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 36 |
"gate_proj",
|
| 37 |
+
"down_proj",
|
|
|
|
|
|
|
| 38 |
"fc1",
|
| 39 |
+
"v_proj",
|
| 40 |
"q_proj",
|
| 41 |
+
"fc2",
|
| 42 |
+
"o_proj",
|
| 43 |
+
"out_proj",
|
| 44 |
+
"k_proj",
|
| 45 |
+
"up_proj"
|
| 46 |
],
|
| 47 |
"target_parameters": null,
|
| 48 |
"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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b07c2b8b8bb9aba69c37ac6c0dd787dc58b8188e45dbfad8caaa7b098b977c5
|
| 3 |
+
size 2768035008
|
runs/Apr30_11-32-09_scs10/events.out.tfevents.1777548729.scs10.3193433.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b0678acaf159dffdb6c63e294b7b205ee2cb72695ed391c508b490db3c02f74
|
| 3 |
+
size 15417
|