Hugging Face's logo

Laterr
/
gemma-3-1B-thinking-function_calling-V0

Text Generation
Transformers
TensorBoard
Safetensors
gemma3_text
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
Metrics Community
Laterr commited on
Commit
919bae8
·
verified ·
1 Parent(s): a8f1b58

Laterr/gemma-3-1B-thinking-function_calling-V0

Browse files
Files changed (7) hide show
  1. README.md +1 -1
  2. adapter_config.json +6 -6
  3. config.json +65 -0
  4. generation_config.json +13 -0
  5. runs/Aug11_11-01-23_1ecb313fc451/events.out.tfevents.1754910085.1ecb313fc451.45305.0 +3 -0
  6. special_tokens_map.json +7 -1
  7. training_args.bin +1 -1
README.md CHANGED
@@ -4,8 +4,8 @@ library_name: transformers
4
  model_name: gemma-3-1B-thinking-function_calling-V0
5
  tags:
6
  - generated_from_trainer
7
- - sft
8
  - trl
 
9
  licence: license
10
  ---
11
 
 
4
  model_name: gemma-3-1B-thinking-function_calling-V0
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
+ - sft
9
  licence: license
10
  ---
11
 
adapter_config.json CHANGED
@@ -25,15 +25,15 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "up_proj",
30
- "o_proj",
31
- "gate_proj",
32
  "lm_head",
33
- "embed_tokens",
 
34
  "k_proj",
35
  "down_proj",
36
- "q_proj"
 
 
37
  ],
38
  "target_parameters": null,
39
  "task_type": "CAUSAL_LM",
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "q_proj",
 
 
 
29
  "lm_head",
30
+ "gate_proj",
31
+ "o_proj",
32
  "k_proj",
33
  "down_proj",
34
+ "embed_tokens",
35
+ "up_proj",
36
+ "v_proj"
37
  ],
38
  "target_parameters": null,
39
  "task_type": "CAUSAL_LM",
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": [
12
+ 1,
13
+ 106
14
+ ],
15
+ "final_logit_softcapping": null,
16
+ "head_dim": 256,
17
+ "hidden_activation": "gelu_pytorch_tanh",
18
+ "hidden_size": 1152,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 6912,
21
+ "layer_types": [
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention"
48
+ ],
49
+ "max_position_embeddings": 32768,
50
+ "model_type": "gemma3_text",
51
+ "num_attention_heads": 4,
52
+ "num_hidden_layers": 26,
53
+ "num_key_value_heads": 1,
54
+ "pad_token_id": 0,
55
+ "query_pre_attn_scalar": 256,
56
+ "rms_norm_eps": 1e-06,
57
+ "rope_local_base_freq": 10000,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000,
60
+ "sliding_window": 512,
61
+ "torch_dtype": "bfloat16",
62
+ "transformers_version": "4.55.0",
63
+ "use_cache": true,
64
+ "vocab_size": 262153
65
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.55.0"
13
+ }
runs/Aug11_11-01-23_1ecb313fc451/events.out.tfevents.1754910085.1ecb313fc451.45305.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80dcfdad43c5e75950ceada409088716c30842a1727ec349cb844fa0b5e1fde8
3
+ size 8743
special_tokens_map.json CHANGED
@@ -20,7 +20,13 @@
20
  "single_word": false
21
  },
22
  "eoi_token": "<end_of_image>",
23
- "eos_token": "<eos>",
 
 
 
 
 
 
24
  "image_token": "<image_soft_token>",
25
  "pad_token": {
26
  "content": "<pad>",
 
20
  "single_word": false
21
  },
22
  "eoi_token": "<end_of_image>",
23
+ "eos_token": {
24
+ "content": "<eos>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
  "image_token": "<image_soft_token>",
31
  "pad_token": {
32
  "content": "<pad>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aafa1fa41dc7df682cac36159fb77e3c37a88fc3ebcc92f8aaa275d520455738
3
  size 6225
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096e589928385add888fbd183b0286b2fb589a4b030451d946fa14ce84fa7b0c
3
  size 6225