Hugging Face's logo

dobleuber
/
gemma-2-2B-it-thinking-function_calling-V0

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
sft
Model card Files
xet
 Metrics Community
dobleuber commited on
Commit
5564233
·
verified ·
1 Parent(s): 19225b0

dobleuber/gemma-2-2B-it-thinking-function_calling-V0

Browse files
Files changed (9) hide show
  1. README.md +3 -3
  2. adapter_config.json +38 -38
  3. adapter_model.safetensors +1 -1
  4. added_tokens.json +10 -0
  5. runs/Feb23_12-38-32_3d7aca86abae/events.out.tfevents.1740314333.3d7aca86abae.7058.0 +3 -0
  6. special_tokens_map.json +42 -36
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +0 -0
  9. training_args.bin +1 -1
README.md CHANGED
@@ -35,8 +35,8 @@ This model was trained with SFT.
35
  ### Framework versions
36
 
37
  - TRL: 0.15.1
38
- - Transformers: 4.49.0
39
- - Pytorch: 2.5.1+cu121
40
  - Datasets: 3.3.2
41
  - Tokenizers: 0.21.0
42
 
@@ -49,7 +49,7 @@ Cite TRL as:
49
  ```bibtex
50
  @misc{vonwerra2022trl,
51
  title = {{TRL: Transformer Reinforcement Learning}},
52
- author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
53
  year = 2020,
54
  journal = {GitHub repository},
55
  publisher = {GitHub},
 
35
  ### Framework versions
36
 
37
  - TRL: 0.15.1
38
+ - Transformers: 4.48.3
39
+ - Pytorch: 2.5.1+cu124
40
  - Datasets: 3.3.2
41
  - Tokenizers: 0.21.0
42
 
 
49
  ```bibtex
50
  @misc{vonwerra2022trl,
51
  title = {{TRL: Transformer Reinforcement Learning}},
52
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
53
  year = 2020,
54
  journal = {GitHub repository},
55
  publisher = {GitHub},
adapter_config.json CHANGED
@@ -1,39 +1,39 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "google/gemma-2-2b-it",
5
- "bias": "none",
6
- "eva_config": null,
7
- "exclude_modules": null,
8
- "fan_in_fan_out": false,
9
- "inference_mode": true,
10
- "init_lora_weights": true,
11
- "layer_replication": null,
12
- "layers_pattern": null,
13
- "layers_to_transform": null,
14
- "loftq_config": {},
15
- "lora_alpha": 64,
16
- "lora_bias": false,
17
- "lora_dropout": 0.05,
18
- "megatron_config": null,
19
- "megatron_core": "megatron.core",
20
- "modules_to_save": null,
21
- "peft_type": "LORA",
22
- "r": 16,
23
- "rank_pattern": {},
24
- "revision": null,
25
- "target_modules": [
26
- "k_proj",
27
- "up_proj",
28
- "lm_head",
29
- "o_proj",
30
- "embed_tokens",
31
- "v_proj",
32
- "down_proj",
33
- "gate_proj",
34
- "q_proj"
35
- ],
36
- "task_type": "CAUSAL_LM",
37
- "use_dora": false,
38
- "use_rslora": false
39
  }
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2-2b-it",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "up_proj",
28
+ "k_proj",
29
+ "gate_proj",
30
+ "o_proj",
31
+ "v_proj",
32
+ "embed_tokens",
33
+ "lm_head",
34
+ "down_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "use_dora": false,
38
+ "use_rslora": false
39
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddace51a63b7a489cbb83ca16d3587f81992e1329171c2d20063305a9f536215
3
  size 2475549872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ac146acd21f54248f045ac12d50e4f1265afeb00901719a4740bcb1c2fc8e68
3
  size 2475549872
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 256003,
3
+ "</tool_call>": 256005,
4
+ "</tool_reponse>": 256007,
5
+ "</tools>": 256001,
6
+ "<think>": 256002,
7
+ "<tool_call>": 256004,
8
+ "<tool_reponse>": 256006,
9
+ "<tools>": 256000
10
+ }
runs/Feb23_12-38-32_3d7aca86abae/events.out.tfevents.1740314333.3d7aca86abae.7058.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c82c09eb08c19dbbf89a3602ae4de6f821270333b9a93e40677f4986a096d0cf
3
+ size 35396
special_tokens_map.json CHANGED
@@ -1,36 +1,42 @@
1
- {
2
- "additional_special_tokens": [
3
- "<tools>",
4
- "</tools>",
5
- "<think>",
6
- "</think>",
7
- "<tool_call>",
8
- "</tool_call>",
9
- "<tool_reponse>",
10
- "</tool_reponse>",
11
- "<pad>",
12
- "<eos>"
13
- ],
14
- "bos_token": {
15
- "content": "<bos>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "eos_token": "<eos>",
22
- "pad_token": {
23
- "content": "<pad>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false
28
- },
29
- "unk_token": {
30
- "content": "<unk>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false
35
- }
36
- }
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<tools>",
4
+ "</tools>",
5
+ "<think>",
6
+ "</think>",
7
+ "<tool_call>",
8
+ "</tool_call>",
9
+ "<tool_reponse>",
10
+ "</tool_reponse>",
11
+ "<pad>",
12
+ "<eos>"
13
+ ],
14
+ "bos_token": {
15
+ "content": "<bos>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "eos_token": {
22
+ "content": "<eos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "unk_token": {
36
+ "content": "<unk>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1774757858e0c499e39fa4c416ade7156d60bf4b8e60ebd171c95315e0baefd4
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b538fff7a5733741d3bc4d0994afe87e9722405c08948a52c3400bbde79dfe
3
  size 5624