Add files using upload-large-folder tool
Browse files- README.md +31 -0
- config.json +149 -0
- manifest.json +15 -0
- model-00003-of-00108.safetensors +3 -0
- model-00005-of-00108.safetensors +3 -0
- model-00009-of-00108.safetensors +3 -0
- model-00013-of-00108.safetensors +3 -0
- model-00016-of-00108.safetensors +3 -0
- model-00017-of-00108.safetensors +3 -0
- model-00018-of-00108.safetensors +3 -0
- model-00019-of-00108.safetensors +3 -0
- model-00020-of-00108.safetensors +3 -0
- model-00023-of-00108.safetensors +3 -0
- model-00026-of-00108.safetensors +3 -0
- model-00027-of-00108.safetensors +3 -0
- model-00028-of-00108.safetensors +3 -0
- model-00030-of-00108.safetensors +3 -0
- model-00038-of-00108.safetensors +3 -0
- model-00040-of-00108.safetensors +3 -0
- model-00043-of-00108.safetensors +3 -0
- model-00047-of-00108.safetensors +3 -0
- model-00049-of-00108.safetensors +3 -0
- model-00051-of-00108.safetensors +3 -0
- model-00052-of-00108.safetensors +3 -0
- model-00056-of-00108.safetensors +3 -0
- model-00058-of-00108.safetensors +3 -0
- model-00059-of-00108.safetensors +3 -0
- model-00061-of-00108.safetensors +3 -0
- model-00062-of-00108.safetensors +3 -0
- model-00066-of-00108.safetensors +3 -0
- model-00070-of-00108.safetensors +3 -0
- model-00074-of-00108.safetensors +3 -0
- model-00075-of-00108.safetensors +3 -0
- model-00077-of-00108.safetensors +3 -0
- model-00079-of-00108.safetensors +3 -0
- model-00084-of-00108.safetensors +3 -0
- model-00086-of-00108.safetensors +3 -0
- model-00087-of-00108.safetensors +3 -0
- model-00090-of-00108.safetensors +3 -0
- model-00092-of-00108.safetensors +3 -0
- model-00093-of-00108.safetensors +3 -0
- model-00094-of-00108.safetensors +3 -0
- model-00096-of-00108.safetensors +3 -0
- model-00097-of-00108.safetensors +3 -0
- model-00099-of-00108.safetensors +3 -0
- model-00101-of-00108.safetensors +3 -0
- model-00106-of-00108.safetensors +3 -0
- model.safetensors.index.json +0 -0
- processor_config.json +46 -0
- tokenizer_config.json +508 -0
README.md
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: thinkingmachines/Inkling
|
| 4 |
+
tags: [linear-attention, gated-deltanet, hybrid, distillation, taylor-calibrate, moe]
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# Inkling-975B, 6 layers linearized to Gated DeltaNet (fused checkpoint)
|
| 8 |
+
|
| 9 |
+
Derivative of [thinkingmachines/Inkling](https://huggingface.co/thinkingmachines/Inkling)
|
| 10 |
+
(Apache-2.0): the attention of layers **[56, 58, 61, 62, 64, 65]** (including full-attention
|
| 11 |
+
layer 65) is replaced with **GatedDeltaNet** (64 heads × 128, gated, short-conv), trained by
|
| 12 |
+
end-to-end KL distillation against the frozen base as teacher (1 800 steps, seq-128,
|
| 13 |
+
64×H100 EP). Layers were selected by zero-ablation importance ranking (least important first).
|
| 14 |
+
All other weights are byte-identical to the base model.
|
| 15 |
+
|
| 16 |
+
| eval (Inkling-tokenized wikitext) | teacher (base) | this model | gap |
|
| 17 |
+
|---|---|---|---|
|
| 18 |
+
| PPL @seq-128 | 7.15 | **7.288** | +1.9% |
|
| 19 |
+
| PPL @seq-2048 (16× the training length) | 2.478 | **2.526** | +1.9% |
|
| 20 |
+
|
| 21 |
+
## Format
|
| 22 |
+
Self-contained: the 109 original shards (native naming, unchanged) + `model-gdn-linearized.safetensors`
|
| 23 |
+
(keys `model.layers.{L}.linear_attn.*`) + patched `model.safetensors.index.json`.
|
| 24 |
+
`config.json` carries an `xorl_linearization` section describing the spliced layers.
|
| 25 |
+
|
| 26 |
+
## Usage
|
| 27 |
+
Loadable with the xorl in-tree Inkling implementation
|
| 28 |
+
(`xorl/models/transformers/inkling/`, togethercomputer/xorl-internal PR #511):
|
| 29 |
+
build `InklingConfig` with `linear_attn_layers=[56,58,61,62,64,65], linear_attn_type="gdn",
|
| 30 |
+
kda_num_heads=64` and point `weights_path` at this repo — the bundled `InklingCheckpointHandler`
|
| 31 |
+
maps native keys (incl. gate/up de-interleave and expert EP-sharding) and passes the GDN keys through.
|
config.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"InklingForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "inkling_mm_model",
|
| 6 |
+
"eos_token_id": 200006,
|
| 7 |
+
"text_config": {
|
| 8 |
+
"model_max_length": 1048576,
|
| 9 |
+
"torch_dtype": "bfloat16",
|
| 10 |
+
"hidden_size": 6144,
|
| 11 |
+
"num_hidden_layers": 66,
|
| 12 |
+
"vocab_size": 201024,
|
| 13 |
+
"num_attention_heads": 64,
|
| 14 |
+
"num_key_value_heads": 8,
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"d_rel": 16,
|
| 17 |
+
"rel_extent": 1024,
|
| 18 |
+
"q_bias": false,
|
| 19 |
+
"o_bias": false,
|
| 20 |
+
"log_scaling_n_floor": 128000,
|
| 21 |
+
"log_scaling_alpha": 0.1,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"use_embed_norm": true,
|
| 24 |
+
"local_layer_ids": [
|
| 25 |
+
0,
|
| 26 |
+
1,
|
| 27 |
+
2,
|
| 28 |
+
3,
|
| 29 |
+
4,
|
| 30 |
+
6,
|
| 31 |
+
7,
|
| 32 |
+
8,
|
| 33 |
+
9,
|
| 34 |
+
10,
|
| 35 |
+
12,
|
| 36 |
+
13,
|
| 37 |
+
14,
|
| 38 |
+
15,
|
| 39 |
+
16,
|
| 40 |
+
18,
|
| 41 |
+
19,
|
| 42 |
+
20,
|
| 43 |
+
21,
|
| 44 |
+
22,
|
| 45 |
+
24,
|
| 46 |
+
25,
|
| 47 |
+
26,
|
| 48 |
+
27,
|
| 49 |
+
28,
|
| 50 |
+
30,
|
| 51 |
+
31,
|
| 52 |
+
32,
|
| 53 |
+
33,
|
| 54 |
+
34,
|
| 55 |
+
36,
|
| 56 |
+
37,
|
| 57 |
+
38,
|
| 58 |
+
39,
|
| 59 |
+
40,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
48,
|
| 66 |
+
49,
|
| 67 |
+
50,
|
| 68 |
+
51,
|
| 69 |
+
52,
|
| 70 |
+
54,
|
| 71 |
+
55,
|
| 72 |
+
56,
|
| 73 |
+
57,
|
| 74 |
+
58,
|
| 75 |
+
60,
|
| 76 |
+
61,
|
| 77 |
+
62,
|
| 78 |
+
63,
|
| 79 |
+
64
|
| 80 |
+
],
|
| 81 |
+
"dense_mlp_idx": 2,
|
| 82 |
+
"use_sconv": true,
|
| 83 |
+
"sconv_kernel_size": 4,
|
| 84 |
+
"unpadded_vocab_size": 200058,
|
| 85 |
+
"logits_mup_width_multiplier": 24.0,
|
| 86 |
+
"final_logit_softcapping": null,
|
| 87 |
+
"swa_head_dim": 128,
|
| 88 |
+
"swa_num_attention_heads": 64,
|
| 89 |
+
"swa_num_key_value_heads": 16,
|
| 90 |
+
"sliding_window_size": 512,
|
| 91 |
+
"n_routed_experts": 256,
|
| 92 |
+
"num_experts_per_tok": 6,
|
| 93 |
+
"n_shared_experts": 2,
|
| 94 |
+
"shared_expert_sink": true,
|
| 95 |
+
"dense_intermediate_size": 24576,
|
| 96 |
+
"intermediate_size": 3072,
|
| 97 |
+
"route_scale": 8.0,
|
| 98 |
+
"use_gate_bias": true,
|
| 99 |
+
"gate_activation": "sigmoid",
|
| 100 |
+
"norm_after_topk": true,
|
| 101 |
+
"use_global_scale": true
|
| 102 |
+
},
|
| 103 |
+
"audio_config": {
|
| 104 |
+
"decoder_dmodel": 6144,
|
| 105 |
+
"n_mel_bins": 80,
|
| 106 |
+
"mel_vocab_size": 16,
|
| 107 |
+
"bias": false,
|
| 108 |
+
"dmel_min_value": -7.0,
|
| 109 |
+
"dmel_max_value": 2.0,
|
| 110 |
+
"use_audio_norm": true,
|
| 111 |
+
"audio_mode": "dmel"
|
| 112 |
+
},
|
| 113 |
+
"vision_config": {
|
| 114 |
+
"vision_encoder_type": "hmlp",
|
| 115 |
+
"decoder_dmodel": 6144,
|
| 116 |
+
"patch_size": 40,
|
| 117 |
+
"temporal_patch_size": 2,
|
| 118 |
+
"n_channels": 3,
|
| 119 |
+
"n_layers": 4,
|
| 120 |
+
"use_vision_norm": true
|
| 121 |
+
},
|
| 122 |
+
"mtp_config": {
|
| 123 |
+
"num_nextn_predict_layers": 8,
|
| 124 |
+
"chain_hidden_post_norm": false,
|
| 125 |
+
"local_layer_ids": [
|
| 126 |
+
0,
|
| 127 |
+
2,
|
| 128 |
+
4,
|
| 129 |
+
5,
|
| 130 |
+
6,
|
| 131 |
+
7
|
| 132 |
+
]
|
| 133 |
+
},
|
| 134 |
+
"xorl_linearization": {
|
| 135 |
+
"linear_attn_layers": [
|
| 136 |
+
56,
|
| 137 |
+
58,
|
| 138 |
+
61,
|
| 139 |
+
62,
|
| 140 |
+
64,
|
| 141 |
+
65
|
| 142 |
+
],
|
| 143 |
+
"linear_attn_type": "gdn",
|
| 144 |
+
"kda_num_heads": 64,
|
| 145 |
+
"kda_head_dim": 128,
|
| 146 |
+
"final_ppl_seq128": 7.287937641143799,
|
| 147 |
+
"teacher_ppl_seq128": 7.15
|
| 148 |
+
}
|
| 149 |
+
}
|
manifest.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"framework": "xorl",
|
| 3 |
+
"linear_attn_layers": [
|
| 4 |
+
56,
|
| 5 |
+
58,
|
| 6 |
+
61,
|
| 7 |
+
62,
|
| 8 |
+
64,
|
| 9 |
+
65
|
| 10 |
+
],
|
| 11 |
+
"kda_heads": 64,
|
| 12 |
+
"final_ppl": 7.287937641143799,
|
| 13 |
+
"start_ppl": 7.362730503082275,
|
| 14 |
+
"steps": 1500
|
| 15 |
+
}
|
model-00003-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06fdee46007c3f4ba74b29aad147e697e35dd0aeeb73240aa2cfb924e181b66f
|
| 3 |
+
size 19793037628
|
model-00005-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5be72f83b0e75b0efaa00eb529ee2326ec1338c9c007ac9344817b2d1a60a500
|
| 3 |
+
size 19402851712
|
model-00009-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99499011c6b4351d1605d81abce1b423e6da6dc419618fd27c0ef8ba3661e9db
|
| 3 |
+
size 9817920224
|
model-00013-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3bc3a53ea5c17f3b32db1878cbc9ae1cc2892985fd4cfb6f0782b3b9f64246a
|
| 3 |
+
size 9726673820
|
model-00016-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c25da56bd3bf2aeb8865fc6105c63d1ae4d7f5cbd7bc766ad6181dc75bd479e1
|
| 3 |
+
size 19657736184
|
model-00017-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9c9d7e1b787d8f3b795deaf7c5ed5b97b3c84ecac2f98093357e6fd8c2918e9
|
| 3 |
+
size 9776935416
|
model-00018-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34f31b3d31f635358faf23eeeeaf31464a838e1b621723553622acbdbe46d8dd
|
| 3 |
+
size 19692415768
|
model-00019-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3db4a1ba8d71dbebe42a05b026ccd541ddfb07325a6984a59ec483593537c9fc
|
| 3 |
+
size 9663676576
|
model-00020-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca12bcd167e668c4e622823b6e2096fb5d8e0829a26e911e56c13addcfe98b6f
|
| 3 |
+
size 19648395960
|
model-00023-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c07b7c008918c05acdee9ad11bb0af2c5bf559e84e2cb5101babf6e5486a46e
|
| 3 |
+
size 19758588104
|
model-00026-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05592903630c933518b18afdafd5af2f9508c41af90749d24daed8074b9be1bb
|
| 3 |
+
size 19997582112
|
model-00027-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e77b18cf34b4d82de562f8f3f4d6f3617fb1804c625a73eebd33b4cb18291104
|
| 3 |
+
size 19453251400
|
model-00028-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00f9a91b444a604ca48dcec947c35e86f16e8f89201e1a806c8570c56b193b53
|
| 3 |
+
size 19783587800
|
model-00030-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cce7322e73a13dd3122500f585651d832d67ddc0e0136657c8d7270e9213f384
|
| 3 |
+
size 19339952512
|
model-00038-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbcdc896300ee69280c65b751cbd652c7ed94e9f8091b3cd8d14fc8b07392202
|
| 3 |
+
size 19402851820
|
model-00040-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a50326d2a5e0dd6815d39e00d2e7e4edeb7eb9cf0cdd5ee85028668981b6097
|
| 3 |
+
size 19730060736
|
model-00043-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e0a1e4c835f2554426a8042202d2b579bce801b4dd69eb5a339acbb18213303
|
| 3 |
+
size 19569714552
|
model-00047-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:424a1d85c9f8782e3370dbec391359641503e31e9491de5e4938bae6c0c1f31b
|
| 3 |
+
size 19327369616
|
model-00049-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14c57a2db7c7877e2b258c22fa5c583918d9c23db20d36110bd4e00b333556f8
|
| 3 |
+
size 19975674272
|
model-00051-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b431ec843d5faf9ec40d58c89be38d33cf85a137465dac06345d07318d3dc93
|
| 3 |
+
size 19428083296
|
model-00052-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76466f8dc307369f430f015f8c017bdae71a31d351f91d3bf94d36a2baacb981
|
| 3 |
+
size 10733613256
|
model-00056-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c16e70640f42aabb95ac97bb92787520ec92eae76e94ff2545a93aeed9f03153
|
| 3 |
+
size 19443849476
|
model-00058-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5666651775980d18fbb96f02faaa612b73c8c059bce66b3815a9cd5ee739828
|
| 3 |
+
size 19641969048
|
model-00059-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba23d7a90e700e18150581d22c18a619f43cccbe9537a03a3b930cadd5427fc6
|
| 3 |
+
size 19956516872
|
model-00061-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d604321f1be9c8c535339fba2260532d621b427e86efe0dae4a3f723df0686f5
|
| 3 |
+
size 19569663352
|
model-00062-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e977b6b7eb309e4f14889c7d437fdbdf4499e3b471c76cfcceaacfbf1d4f2098
|
| 3 |
+
size 19445350904
|
model-00066-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84f39b631f42e13753d578c9a6e4078f8a9c3122f2af15d67fb4e26f2995e33c
|
| 3 |
+
size 19330536912
|
model-00070-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d139332348b57522513fa25f077886d8e2f45450bbf678069e52d19f8c09d28
|
| 3 |
+
size 19654789292
|
model-00074-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:850e48bdcdea4e2154de80182f2df856f952c17936bbfea9181b0170a0714524
|
| 3 |
+
size 19327352992
|
model-00075-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bbe1cf1e2600f1ba3201a0a3e0261b299d33ec123e366bf8296f279e660eb4e
|
| 3 |
+
size 9676285512
|
model-00077-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1182b941bed8d26ce976adbe82052e9041ab58c9ec0b5b215243d87a6c3a8e20
|
| 3 |
+
size 9663688968
|
model-00079-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3db23920d1ba6eab951fcb78b948902a220c0b34536663986f81006594e8949a
|
| 3 |
+
size 19670434480
|
model-00084-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51a845d968bef492f032e8169bc0567c0544e9ad7d6a0b2054b8d537d8a84d9d
|
| 3 |
+
size 9843052148
|
model-00086-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4925d4ac9f56bc37e704253320d863f828de8df566b47656aa6e6dfbb98f52a0
|
| 3 |
+
size 19330556784
|
model-00087-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9dd5583b90a14904b6fe5195539ff13751287ceb19f7fcfe621d0b0380296ed
|
| 3 |
+
size 19780417196
|
model-00090-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:604a1f065cc577461aa6214d84aa7178f60e48107fb3c63decfecfc83f4d73dc
|
| 3 |
+
size 10808908168
|
model-00092-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f675f5752f4596588b279f918dff248db35d7a182efbf2e0e673baca49424ad
|
| 3 |
+
size 19984888400
|
model-00093-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d7821d1cedb6595b661104308f1ace4b933134ec0106ff78318eacf552a35e5
|
| 3 |
+
size 19352518936
|
model-00094-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c91f417b5a5f79d62130e7fcddbdf74842d48bca56aabe66079114e86ff04cf2
|
| 3 |
+
size 19874990888
|
model-00096-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4308a7776edb271699b3696184b00db11264e85bdf0d0fd33d5637fb3789f6a2
|
| 3 |
+
size 19582331640
|
model-00097-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1248b3c61f9f2e16918f08a07b9fccb5656d3441ede718364a6fac82c63b68ec
|
| 3 |
+
size 19503526416
|
model-00099-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:212dcc5b5862a2439d926794172edc84c5a20d08e29cf1ac46e2841a759572b9
|
| 3 |
+
size 19582392128
|
model-00101-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea5c7c6dc75fea646fb2158312277dc22a154e4ac92e3f9ed9ca8513e00c9c65
|
| 3 |
+
size 19327352992
|
model-00106-of-00108.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfe952b9cf6afeaf668bb0a821fe39070d692a28abc2e5cd7922b546e34773fd
|
| 3 |
+
size 19516142912
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|unused_200053|>",
|
| 3 |
+
"audio_bos_token": "<|content_audio_input|>",
|
| 4 |
+
"dmel_max_value": 2.0,
|
| 5 |
+
"dmel_min_value": -7.0,
|
| 6 |
+
"feature_extractor": {
|
| 7 |
+
"audio_token_duration_s": 0.05,
|
| 8 |
+
"feature_extractor_type": "InklingFeatureExtractor",
|
| 9 |
+
"feature_size": 80,
|
| 10 |
+
"hop_length": 800,
|
| 11 |
+
"n_fft": 1600,
|
| 12 |
+
"padding_side": "right",
|
| 13 |
+
"padding_value": 0.0,
|
| 14 |
+
"return_attention_mask": true,
|
| 15 |
+
"sampling_rate": 16000,
|
| 16 |
+
"window_size": 1600,
|
| 17 |
+
"window_size_multiplier": 2.0
|
| 18 |
+
},
|
| 19 |
+
"image_processor": {
|
| 20 |
+
"do_convert_rgb": true,
|
| 21 |
+
"do_normalize": true,
|
| 22 |
+
"do_rescale": true,
|
| 23 |
+
"do_resize": true,
|
| 24 |
+
"image_mean": [
|
| 25 |
+
0.48145466,
|
| 26 |
+
0.4578275,
|
| 27 |
+
0.40821073
|
| 28 |
+
],
|
| 29 |
+
"image_processor_type": "InklingImageProcessor",
|
| 30 |
+
"image_std": [
|
| 31 |
+
0.26862954,
|
| 32 |
+
0.26130258,
|
| 33 |
+
0.27577711
|
| 34 |
+
],
|
| 35 |
+
"resample": 3,
|
| 36 |
+
"rescale_factor": 0.00392156862745098,
|
| 37 |
+
"size": {
|
| 38 |
+
"height": 40,
|
| 39 |
+
"width": 40
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"image_token": "<|unused_200054|>",
|
| 43 |
+
"image_bos_token": "<|content_image|>",
|
| 44 |
+
"num_dmel_bins": 16,
|
| 45 |
+
"processor_class": "InklingProcessor"
|
| 46 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"199998": {
|
| 4 |
+
"content": "<|unused|>",
|
| 5 |
+
"single_word": false,
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"199999": {
|
| 12 |
+
"content": "<|endoftext|>",
|
| 13 |
+
"single_word": false,
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"200000": {
|
| 20 |
+
"content": "<|message_user|>",
|
| 21 |
+
"single_word": false,
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"200001": {
|
| 28 |
+
"content": "<|message_model|>",
|
| 29 |
+
"single_word": false,
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"200002": {
|
| 36 |
+
"content": "<|message_system|>",
|
| 37 |
+
"single_word": false,
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"200003": {
|
| 44 |
+
"content": "<|message_tool|>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"200004": {
|
| 52 |
+
"content": "<|content_text|>",
|
| 53 |
+
"single_word": false,
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"200005": {
|
| 60 |
+
"content": "<|content_image|>",
|
| 61 |
+
"single_word": false,
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"200006": {
|
| 68 |
+
"content": "<|content_model_end_sampling|>",
|
| 69 |
+
"single_word": false,
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"200007": {
|
| 76 |
+
"content": "<|unused_200007|>",
|
| 77 |
+
"single_word": false,
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"200008": {
|
| 84 |
+
"content": "<|content_thinking|>",
|
| 85 |
+
"single_word": false,
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"200009": {
|
| 92 |
+
"content": "<|unused_200009|>",
|
| 93 |
+
"single_word": false,
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"200010": {
|
| 100 |
+
"content": "<|end_message|>",
|
| 101 |
+
"single_word": false,
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"200011": {
|
| 108 |
+
"content": "<|unused_200011|>",
|
| 109 |
+
"single_word": false,
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"200012": {
|
| 116 |
+
"content": "<|unused_200012|>",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"200013": {
|
| 124 |
+
"content": "<|unused_200013|>",
|
| 125 |
+
"single_word": false,
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"200014": {
|
| 132 |
+
"content": "<|unused_200014|>",
|
| 133 |
+
"single_word": false,
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"200015": {
|
| 140 |
+
"content": "<|unused_200015|>",
|
| 141 |
+
"single_word": false,
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"200016": {
|
| 148 |
+
"content": "<|unused_200016|>",
|
| 149 |
+
"single_word": false,
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"200017": {
|
| 156 |
+
"content": "<|unused_200017|>",
|
| 157 |
+
"single_word": false,
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"200018": {
|
| 164 |
+
"content": "<|unused_200018|>",
|
| 165 |
+
"single_word": false,
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"200019": {
|
| 172 |
+
"content": "<|unused_200019|>",
|
| 173 |
+
"single_word": false,
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"200020": {
|
| 180 |
+
"content": "<|content_audio_input|>",
|
| 181 |
+
"single_word": false,
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"200021": {
|
| 188 |
+
"content": "<|unused_200021|>",
|
| 189 |
+
"single_word": false,
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"200022": {
|
| 196 |
+
"content": "<|content_tool_error|>",
|
| 197 |
+
"single_word": false,
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"200023": {
|
| 204 |
+
"content": "<|audio|>",
|
| 205 |
+
"single_word": false,
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"200024": {
|
| 212 |
+
"content": "<|content_xml|>",
|
| 213 |
+
"single_word": false,
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"200025": {
|
| 220 |
+
"content": "<|unused_200025|>",
|
| 221 |
+
"single_word": false,
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"200026": {
|
| 228 |
+
"content": "<|unused_200026|>",
|
| 229 |
+
"single_word": false,
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"200027": {
|
| 236 |
+
"content": "<|unused_200027|>",
|
| 237 |
+
"single_word": false,
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"200028": {
|
| 244 |
+
"content": "<|begin_of_text|>",
|
| 245 |
+
"single_word": false,
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"200029": {
|
| 252 |
+
"content": "<|unused_200029|>",
|
| 253 |
+
"single_word": false,
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"200030": {
|
| 260 |
+
"content": "<|unused_200030|>",
|
| 261 |
+
"single_word": false,
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"200031": {
|
| 268 |
+
"content": "<|unused_200031|>",
|
| 269 |
+
"single_word": false,
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"200032": {
|
| 276 |
+
"content": "<|unused_200032|>",
|
| 277 |
+
"single_word": false,
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"200033": {
|
| 284 |
+
"content": "<|unused_200033|>",
|
| 285 |
+
"single_word": false,
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"200034": {
|
| 292 |
+
"content": "<|unused_200034|>",
|
| 293 |
+
"single_word": false,
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"200035": {
|
| 300 |
+
"content": "<|unused_200035|>",
|
| 301 |
+
"single_word": false,
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"200036": {
|
| 308 |
+
"content": "<|unused_200036|>",
|
| 309 |
+
"single_word": false,
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"200037": {
|
| 316 |
+
"content": "<|unused_200037|>",
|
| 317 |
+
"single_word": false,
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"200038": {
|
| 324 |
+
"content": "<|unused_200038|>",
|
| 325 |
+
"single_word": false,
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"200039": {
|
| 332 |
+
"content": "<|unused_200039|>",
|
| 333 |
+
"single_word": false,
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"200040": {
|
| 340 |
+
"content": "<|unused_200040|>",
|
| 341 |
+
"single_word": false,
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"200041": {
|
| 348 |
+
"content": "<|unused_200041|>",
|
| 349 |
+
"single_word": false,
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"200042": {
|
| 356 |
+
"content": "<|unused_200042|>",
|
| 357 |
+
"single_word": false,
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"200043": {
|
| 364 |
+
"content": "<|audio_end|>",
|
| 365 |
+
"single_word": false,
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"200044": {
|
| 372 |
+
"content": "<|unused_200044|>",
|
| 373 |
+
"single_word": false,
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"200045": {
|
| 380 |
+
"content": "<|unused_200045|>",
|
| 381 |
+
"single_word": false,
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"200046": {
|
| 388 |
+
"content": "<|unused_200046|>",
|
| 389 |
+
"single_word": false,
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"200047": {
|
| 396 |
+
"content": "<|unused_200047|>",
|
| 397 |
+
"single_word": false,
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"200048": {
|
| 404 |
+
"content": "<|unused_200048|>",
|
| 405 |
+
"single_word": false,
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"200049": {
|
| 412 |
+
"content": "<|content_invoke_tool_json|>",
|
| 413 |
+
"single_word": false,
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"200050": {
|
| 420 |
+
"content": "<|unused_200050|>",
|
| 421 |
+
"single_word": false,
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"200051": {
|
| 428 |
+
"content": "<|unused_200051|>",
|
| 429 |
+
"single_word": false,
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"200052": {
|
| 436 |
+
"content": "<|unused_200052|>",
|
| 437 |
+
"single_word": false,
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"200053": {
|
| 444 |
+
"content": "<|unused_200053|>",
|
| 445 |
+
"single_word": false,
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"200054": {
|
| 452 |
+
"content": "<|unused_200054|>",
|
| 453 |
+
"single_word": false,
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"200055": {
|
| 460 |
+
"content": "<|unused_200055|>",
|
| 461 |
+
"single_word": false,
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"200056": {
|
| 468 |
+
"content": "<|unused_200056|>",
|
| 469 |
+
"single_word": false,
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"200057": {
|
| 476 |
+
"content": "<|content_invoke_tool_text|>",
|
| 477 |
+
"single_word": false,
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"special": true
|
| 482 |
+
}
|
| 483 |
+
},
|
| 484 |
+
"clean_up_tokenization_spaces": false,
|
| 485 |
+
"fix_mistral_regex": false,
|
| 486 |
+
"extra_special_tokens": {
|
| 487 |
+
"endoftext": "<|endoftext|>",
|
| 488 |
+
"message_user": "<|message_user|>",
|
| 489 |
+
"message_model": "<|message_model|>",
|
| 490 |
+
"message_system": "<|message_system|>",
|
| 491 |
+
"message_tool": "<|message_tool|>",
|
| 492 |
+
"content_text": "<|content_text|>",
|
| 493 |
+
"content_image": "<|content_image|>",
|
| 494 |
+
"content_model_end_sampling": "<|content_model_end_sampling|>",
|
| 495 |
+
"content_thinking": "<|content_thinking|>",
|
| 496 |
+
"end_message": "<|end_message|>",
|
| 497 |
+
"content_audio_input": "<|content_audio_input|>",
|
| 498 |
+
"content_tool_error": "<|content_tool_error|>",
|
| 499 |
+
"audio": "<|audio|>",
|
| 500 |
+
"content_xml": "<|content_xml|>",
|
| 501 |
+
"begin_of_text": "<|begin_of_text|>",
|
| 502 |
+
"audio_end": "<|audio_end|>",
|
| 503 |
+
"content_invoke_tool_json": "<|content_invoke_tool_json|>",
|
| 504 |
+
"content_invoke_tool_text": "<|content_invoke_tool_text|>"
|
| 505 |
+
},
|
| 506 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 507 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 508 |
+
}
|