Hugging Face's logo

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

Text Generation
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
sft
trl
conversational
Model card Files
xet
Metrics Community
naifenn commited on
Commit
5cc81f1
·
verified ·
1 Parent(s): 20d02cf

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

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. adapter_config.json +11 -10
  3. adapter_model.safetensors +2 -2
  4. runs/Dec22_20-56-17_05d86f460e4c/events.out.tfevents.1766436985.05d86f460e4c.1008.0 +3 -0
  5. special_tokens_map.json +7 -1
  6. training_args.bin +1 -1
README.md CHANGED
@@ -4,8 +4,8 @@ library_name: transformers
4
  model_name: gemma-2-2B-it-thinking-function_calling-V0
5
  tags:
6
  - generated_from_trainer
7
- - trl
8
  - sft
 
9
  licence: license
10
  ---
11
 
 
4
  model_name: gemma-2-2B-it-thinking-function_calling-V0
5
  tags:
6
  - generated_from_trainer
 
7
  - sft
8
+ - trl
9
  licence: license
10
  ---
11
 
adapter_config.json CHANGED
@@ -16,28 +16,29 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 64,
20
  "lora_bias": false,
21
- "lora_dropout": 0.05,
22
  "megatron_config": null,
23
  "megatron_core": "megatron.core",
24
- "modules_to_save": null,
 
 
 
25
  "peft_type": "LORA",
26
  "peft_version": "0.18.0",
27
  "qalora_group_size": 16,
28
- "r": 32,
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
- "gate_proj",
33
- "lm_head",
34
  "k_proj",
35
- "embed_tokens",
36
  "down_proj",
37
- "q_proj",
38
- "up_proj",
39
  "v_proj",
40
- "o_proj"
 
 
41
  ],
42
  "target_parameters": null,
43
  "task_type": "CAUSAL_LM",
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 128,
20
  "lora_bias": false,
21
+ "lora_dropout": 0.1,
22
  "megatron_config": null,
23
  "megatron_core": "megatron.core",
24
+ "modules_to_save": [
25
+ "embed_tokens",
26
+ "lm_head"
27
+ ],
28
  "peft_type": "LORA",
29
  "peft_version": "0.18.0",
30
  "qalora_group_size": 16,
31
+ "r": 64,
32
  "rank_pattern": {},
33
  "revision": null,
34
  "target_modules": [
 
 
35
  "k_proj",
36
+ "gate_proj",
37
  "down_proj",
 
 
38
  "v_proj",
39
+ "q_proj",
40
+ "o_proj",
41
+ "up_proj"
42
  ],
43
  "target_parameters": null,
44
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd169e867d30f21cfcdc10c9fbcdddce1acfdd55917309ab7bc819bdf9429b77
3
- size 2591681128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd13107f641042fc5247f8a585fc533196c6fad2774948e210eb1c4286c3a94
3
+ size 7410426432
runs/Dec22_20-56-17_05d86f460e4c/events.out.tfevents.1766436985.05d86f460e4c.1008.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79fbed87f3ec47c59f61964be684be121d6c169edd1d762051a23f5cbb16304a
3
+ size 16790
special_tokens_map.json CHANGED
@@ -18,7 +18,13 @@
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
- "eos_token": "<eos>",
 
 
 
 
 
 
22
  "pad_token": {
23
  "content": "<pad>",
24
  "lstrip": 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,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5183ce04dc244f9580e7e7fae05efba4c7d45dc75871de4b891fc3811d8f0e
3
  size 6353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037b21a4fd6521ee4b5557d28f3395641d6e861fbcec4bcf2864818164bac9ea
3
  size 6353