Hugging Face's logo

oytunistrator
/
AquaLLM

Question Answering
Safetensors
GGUF
Turkish
English
gpt2
aquarium
aqua
biology
text-generation-inference
Model card Files
xet
oytunistrator commited on
Commit
b3c1989
·
verified ·
1 Parent(s): 55cda38

Upload model

Browse files
Files changed (3) hide show
  1. config.json +38 -30
  2. generation_config.json +6 -6
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,30 +1,38 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151643,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 1024,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "max_position_embeddings": 32768,
15
- "max_window_layers": 28,
16
- "model_type": "qwen3",
17
- "num_attention_heads": 16,
18
- "num_hidden_layers": 28,
19
- "num_key_value_heads": 8,
20
- "rms_norm_eps": 1e-06,
21
- "rope_scaling": null,
22
- "rope_theta": 1000000,
23
- "sliding_window": null,
24
- "tie_word_embeddings": true,
25
- "torch_dtype": "float32",
26
- "transformers_version": "4.52.4",
27
- "use_cache": true,
28
- "use_sliding_window": false,
29
- "vocab_size": 151669
30
- }
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.52.4",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "bos_token_id": 151643,
3
- "eos_token_id": 151643,
4
- "max_new_tokens": 2048,
5
- "transformers_version": "4.52.4"
6
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.52.4"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebea91157f9d630ec08ed49f1067ba2a066e7da1098a7317bf761e3463ca901d
3
- size 2383141336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b541cb526a7f9fc7316f17f68207587f694cfa805f44617a5587d9e5ef2f5ba3
3
+ size 497774208