TymofiiNasobko/Lapa-function-calling
Browse files- README.md +2 -2
- adapter_config.json +3 -11
- adapter_model.safetensors +2 -2
- chat_template.jinja +10 -3
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: transformers
|
|
| 4 |
model_name: Lapa-function-calling
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- sft
|
| 8 |
- trl
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
@@ -36,7 +36,7 @@ This model was trained with SFT.
|
|
| 36 |
|
| 37 |
- TRL: 0.25.1
|
| 38 |
- Transformers: 4.57.3
|
| 39 |
-
- Pytorch: 2.8.0+
|
| 40 |
- Datasets: 4.4.1
|
| 41 |
- Tokenizers: 0.22.1
|
| 42 |
|
|
|
|
| 4 |
model_name: Lapa-function-calling
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- trl
|
| 8 |
+
- sft
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
|
|
| 36 |
|
| 37 |
- TRL: 0.25.1
|
| 38 |
- Transformers: 4.57.3
|
| 39 |
+
- Pytorch: 2.8.0+cu129
|
| 40 |
- Datasets: 4.4.1
|
| 41 |
- Tokenizers: 0.22.1
|
| 42 |
|
adapter_config.json
CHANGED
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"layers_pattern": null,
|
| 17 |
"layers_to_transform": null,
|
| 18 |
"loftq_config": {},
|
| 19 |
-
"lora_alpha":
|
| 20 |
"lora_bias": false,
|
| 21 |
"lora_dropout": 0.05,
|
| 22 |
"megatron_config": null,
|
|
@@ -29,16 +29,8 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"k_proj",
|
| 35 |
-
"v_proj",
|
| 36 |
-
"fc2",
|
| 37 |
-
"o_proj",
|
| 38 |
-
"fc1",
|
| 39 |
-
"down_proj",
|
| 40 |
-
"q_proj",
|
| 41 |
-
"up_proj"
|
| 42 |
],
|
| 43 |
"target_parameters": null,
|
| 44 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 16 |
"layers_pattern": null,
|
| 17 |
"layers_to_transform": null,
|
| 18 |
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 512,
|
| 20 |
"lora_bias": false,
|
| 21 |
"lora_dropout": 0.05,
|
| 22 |
"megatron_config": null,
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"embed_tokens",
|
| 33 |
+
"all-linear"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
],
|
| 35 |
"target_parameters": null,
|
| 36 |
"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 sha256:88ab938ad02b9d0bf666276bc347973cc8d98529dbcadd31fd6481c56d8cc43b
|
| 3 |
+
size 2285694936
|
chat_template.jinja
CHANGED
|
@@ -23,7 +23,7 @@
|
|
| 23 |
' + (first_user_prefix if loop.first else "") }}
|
| 24 |
{%- if message['content'] is string -%}
|
| 25 |
{%- if role == "model" -%}
|
| 26 |
-
{% generation %}
|
| 27 |
{%- else -%}
|
| 28 |
{{ message['content'] | trim }}
|
| 29 |
{%- endif -%}
|
|
@@ -33,7 +33,7 @@
|
|
| 33 |
{{ '<start_of_image>' }}
|
| 34 |
{%- elif item['type'] == 'text' -%}
|
| 35 |
{%- if role == "model" -%}
|
| 36 |
-
{% generation %}
|
| 37 |
{%- else -%}
|
| 38 |
{{ item['text'] | trim }}
|
| 39 |
{%- endif -%}
|
|
@@ -42,9 +42,16 @@
|
|
| 42 |
{%- else -%}
|
| 43 |
{{ raise_exception("Invalid content type") }}
|
| 44 |
{%- endif -%}
|
| 45 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
' }}
|
|
|
|
| 47 |
{%- endfor -%}
|
|
|
|
| 48 |
{%- if add_generation_prompt -%}
|
| 49 |
{{'<start_of_turn>model
|
| 50 |
'}}
|
|
|
|
| 23 |
' + (first_user_prefix if loop.first else "") }}
|
| 24 |
{%- if message['content'] is string -%}
|
| 25 |
{%- if role == "model" -%}
|
| 26 |
+
{% generation %}{{ message['content'] | trim }}{% endgeneration %}
|
| 27 |
{%- else -%}
|
| 28 |
{{ message['content'] | trim }}
|
| 29 |
{%- endif -%}
|
|
|
|
| 33 |
{{ '<start_of_image>' }}
|
| 34 |
{%- elif item['type'] == 'text' -%}
|
| 35 |
{%- if role == "model" -%}
|
| 36 |
+
{% generation %}{{ item['text'] | trim }}{% endgeneration %}
|
| 37 |
{%- else -%}
|
| 38 |
{{ item['text'] | trim }}
|
| 39 |
{%- endif -%}
|
|
|
|
| 42 |
{%- else -%}
|
| 43 |
{{ raise_exception("Invalid content type") }}
|
| 44 |
{%- endif -%}
|
| 45 |
+
{%- if role == "model" -%}
|
| 46 |
+
{% generation %}
|
| 47 |
+
{{ '<end_of_turn>
|
| 48 |
+
' }}{% endgeneration %}
|
| 49 |
+
{%- else -%}
|
| 50 |
+
{{ '<end_of_turn>
|
| 51 |
' }}
|
| 52 |
+
{%- endif -%}
|
| 53 |
{%- endfor -%}
|
| 54 |
+
|
| 55 |
{%- if add_generation_prompt -%}
|
| 56 |
{{'<start_of_turn>model
|
| 57 |
'}}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6225
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:264c88be027ded39b70324149dbe1cf4b50e33e90c1a743861991a753109baff
|
| 3 |
size 6225
|