Training in progress, epoch 1
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: google/gemma-3-1b-
|
| 3 |
library_name: transformers
|
| 4 |
model_name: gemma-ft-GUIDANCE
|
| 5 |
tags:
|
|
@@ -11,7 +11,7 @@ licence: license
|
|
| 11 |
|
| 12 |
# Model Card for gemma-ft-GUIDANCE
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [google/gemma-3-1b-
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: google/gemma-3-1b-it
|
| 3 |
library_name: transformers
|
| 4 |
model_name: gemma-ft-GUIDANCE
|
| 5 |
tags:
|
|
|
|
| 11 |
|
| 12 |
# Model Card for gemma-ft-GUIDANCE
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "google/gemma-3-1b-
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
| 7 |
"eva_config": null,
|
|
@@ -27,13 +27,13 @@
|
|
| 27 |
"rank_pattern": {},
|
| 28 |
"revision": null,
|
| 29 |
"target_modules": [
|
| 30 |
-
"down_proj",
|
| 31 |
"o_proj",
|
|
|
|
|
|
|
| 32 |
"q_proj",
|
| 33 |
"v_proj",
|
| 34 |
"gate_proj",
|
| 35 |
-
"k_proj"
|
| 36 |
-
"up_proj"
|
| 37 |
],
|
| 38 |
"task_type": "CAUSAL_LM",
|
| 39 |
"trainable_token_indices": null,
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-1b-it",
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
| 7 |
"eva_config": null,
|
|
|
|
| 27 |
"rank_pattern": {},
|
| 28 |
"revision": null,
|
| 29 |
"target_modules": [
|
|
|
|
| 30 |
"o_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"up_proj",
|
| 33 |
"q_proj",
|
| 34 |
"v_proj",
|
| 35 |
"gate_proj",
|
| 36 |
+
"k_proj"
|
|
|
|
| 37 |
],
|
| 38 |
"task_type": "CAUSAL_LM",
|
| 39 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1260191096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:514ec13f1f516d4726bfeee5bd591c3a790df4afdd74d1499988474084341832
|
| 3 |
size 1260191096
|
runs/Aug20_18-56-45_PC-RJ/events.out.tfevents.1755709010.PC-RJ.8280.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74519b9a266f6f73f1ddfaf8d6bd803b4e18f73710501c74a712b293b6896b03
|
| 3 |
+
size 6909
|
runs/Aug20_19-09-36_PC-RJ/events.out.tfevents.1755709782.PC-RJ.14744.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7594f64b6d264f7969206cb4686df786c464a8d4fc1a64882cc61b665f13567
|
| 3 |
+
size 7557
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a99c8fe6ad75317edc6f5a5b52167679ec3c462319f951d76cb3c40f582384b
|
| 3 |
size 5816
|