Text Generation
Transformers
Safetensors
qwen2
thinking
reasoning
Gemini
Claude Opus
Gpt5.2
Distill
finetune
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prose
vivid writing
fiction
roleplaying
bfloat16
swearing
rp
horror
unsloth
context 1 million
conversational
text-generation-inference
Upload config.json with huggingface_hub
Browse files- config.json +66 -0
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"dual_chunk_attention_config": {
|
| 9 |
+
"chunk_size": 262144,
|
| 10 |
+
"local_size": 8192,
|
| 11 |
+
"original_max_position_embeddings": 262144
|
| 12 |
+
},
|
| 13 |
+
"eos_token_id": 151645,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 3584,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 18944,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention"
|
| 47 |
+
],
|
| 48 |
+
"max_position_embeddings": 1010000,
|
| 49 |
+
"max_window_layers": 28,
|
| 50 |
+
"model_type": "qwen2",
|
| 51 |
+
"num_attention_heads": 28,
|
| 52 |
+
"num_hidden_layers": 28,
|
| 53 |
+
"num_key_value_heads": 4,
|
| 54 |
+
"rms_norm_eps": 1e-05,
|
| 55 |
+
"rope_parameters": {
|
| 56 |
+
"rope_theta": 10000000.0,
|
| 57 |
+
"rope_type": "default"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 10000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": false,
|
| 62 |
+
"transformers_version": "5.0.0.dev0",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"vocab_size": 152064
|
| 66 |
+
}
|