Text Generation
Transformers
Safetensors
GGUF
gemma3_text
turkish
türkiye
english
ai
lamapi
gemma3
next
next-x1
efficient
open-source
1b
huggingface
large-language-model
llm
causal
transformer
artificial-intelligence
machine-learning
ai-research
natural-language-processing
nlp
finetuned
lightweight
creative
summarization
question-answering
chat-model
generative-ai
optimized-model
unsloth
trl
sft
chemistry
biology
finance
legal
music
art
code
climate
medical
agent
text-generation-inference
conversational
Delete config.json
Browse files- config.json +0 -64
config.json
DELETED
|
@@ -1,64 +0,0 @@
|
|
| 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": 106,
|
| 12 |
-
"final_logit_softcapping": null,
|
| 13 |
-
"head_dim": 256,
|
| 14 |
-
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
-
"hidden_size": 1152,
|
| 16 |
-
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size": 6912,
|
| 18 |
-
"layer_types": [
|
| 19 |
-
"sliding_attention",
|
| 20 |
-
"sliding_attention",
|
| 21 |
-
"sliding_attention",
|
| 22 |
-
"sliding_attention",
|
| 23 |
-
"sliding_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"sliding_attention",
|
| 26 |
-
"sliding_attention",
|
| 27 |
-
"sliding_attention",
|
| 28 |
-
"sliding_attention",
|
| 29 |
-
"sliding_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"sliding_attention",
|
| 32 |
-
"sliding_attention",
|
| 33 |
-
"sliding_attention",
|
| 34 |
-
"sliding_attention",
|
| 35 |
-
"sliding_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"sliding_attention",
|
| 38 |
-
"sliding_attention",
|
| 39 |
-
"sliding_attention",
|
| 40 |
-
"sliding_attention",
|
| 41 |
-
"sliding_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"sliding_attention",
|
| 44 |
-
"sliding_attention"
|
| 45 |
-
],
|
| 46 |
-
"max_position_embeddings": 32768,
|
| 47 |
-
"model_type": "gemma3_text",
|
| 48 |
-
"num_attention_heads": 4,
|
| 49 |
-
"num_hidden_layers": 26,
|
| 50 |
-
"num_key_value_heads": 1,
|
| 51 |
-
"pad_token_id": 0,
|
| 52 |
-
"query_pre_attn_scalar": 256,
|
| 53 |
-
"rms_norm_eps": 1e-06,
|
| 54 |
-
"rope_local_base_freq": 10000,
|
| 55 |
-
"rope_scaling": null,
|
| 56 |
-
"rope_theta": 1000000,
|
| 57 |
-
"sliding_window": 512,
|
| 58 |
-
"torch_dtype": "bfloat16",
|
| 59 |
-
"transformers_version": "4.55.4",
|
| 60 |
-
"unsloth_fixed": true,
|
| 61 |
-
"unsloth_version": "2025.10.3",
|
| 62 |
-
"use_cache": true,
|
| 63 |
-
"vocab_size": 262144
|
| 64 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|