Text Generation
MLX
Safetensors
Rust
qwen3_5_text
27b
agentic-coding
alloy-backfilled
android
apple-silicon
attested
bash
c
chain-of-custody
chinese
code
code-completion
code-generation
code-infill
coder
coding
compacted
consumer-gpu
cpp
cryptographically-verified
css
defragged
derivative
edge-inference
efficient
embedded
english
forge-alloy
function-calling
go
head-pruning
html
iphone
java
javascript
kotlin
llama-cpp
lm-studio
local-inference
macbook
mobile
multilingual
ollama
on-device
optimized
php
programming
pruned
python
qwen
qwen3
qwen3.5
raspberry-pi
reproducible
ruby
software-engineering
sql
swift
typescript
conversational
Upload config.json with huggingface_hub
Browse files- config.json +115 -0
config.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_output_gate": true,
|
| 8 |
+
"bos_token_id": null,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 248044,
|
| 11 |
+
"full_attention_interval": 4,
|
| 12 |
+
"head_dim": 256,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 5120,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 17408,
|
| 17 |
+
"layer_types": [
|
| 18 |
+
"linear_attention",
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"linear_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"linear_attention",
|
| 67 |
+
"linear_attention",
|
| 68 |
+
"linear_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"linear_attention",
|
| 71 |
+
"linear_attention",
|
| 72 |
+
"linear_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"linear_attention",
|
| 75 |
+
"linear_attention",
|
| 76 |
+
"linear_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"linear_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"full_attention"
|
| 82 |
+
],
|
| 83 |
+
"linear_conv_kernel_dim": 4,
|
| 84 |
+
"linear_key_head_dim": 128,
|
| 85 |
+
"linear_num_key_heads": 16,
|
| 86 |
+
"linear_num_value_heads": 48,
|
| 87 |
+
"linear_value_head_dim": 128,
|
| 88 |
+
"mamba_ssm_dtype": "float32",
|
| 89 |
+
"max_position_embeddings": 262144,
|
| 90 |
+
"mlp_only_layers": [],
|
| 91 |
+
"model_type": "qwen3_5_text",
|
| 92 |
+
"mtp_num_hidden_layers": 1,
|
| 93 |
+
"mtp_use_dedicated_embeddings": false,
|
| 94 |
+
"num_attention_heads": 18,
|
| 95 |
+
"num_hidden_layers": 64,
|
| 96 |
+
"num_key_value_heads": 3,
|
| 97 |
+
"pad_token_id": null,
|
| 98 |
+
"partial_rotary_factor": 0.25,
|
| 99 |
+
"rms_norm_eps": 1e-06,
|
| 100 |
+
"rope_parameters": {
|
| 101 |
+
"mrope_interleaved": true,
|
| 102 |
+
"mrope_section": [
|
| 103 |
+
11,
|
| 104 |
+
11,
|
| 105 |
+
10
|
| 106 |
+
],
|
| 107 |
+
"partial_rotary_factor": 0.25,
|
| 108 |
+
"rope_theta": 10000000,
|
| 109 |
+
"rope_type": "default"
|
| 110 |
+
},
|
| 111 |
+
"tie_word_embeddings": false,
|
| 112 |
+
"transformers_version": "5.3.0",
|
| 113 |
+
"use_cache": true,
|
| 114 |
+
"vocab_size": 248320
|
| 115 |
+
}
|