Upload 15 files
Browse files- .gitattributes +1 -0
- added_tokens.json +3 -0
- config.json +58 -0
- generation_config.json +11 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quant_log.csv +435 -0
- quantize_config.json +21 -0
- special_tokens_map.json +27 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_logit_softcapping": null,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"cache_implementation": "hybrid",
|
| 10 |
+
"eos_token_id": 1,
|
| 11 |
+
"final_logit_softcapping": null,
|
| 12 |
+
"head_dim": 128,
|
| 13 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 14 |
+
"hidden_size": 5376,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 21504,
|
| 17 |
+
"max_position_embeddings": 131072,
|
| 18 |
+
"model_type": "gemma3_text",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 62,
|
| 21 |
+
"num_key_value_heads": 16,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"quantization_config": {
|
| 24 |
+
"bits": 4,
|
| 25 |
+
"checkpoint_format": "gptq",
|
| 26 |
+
"desc_act": true,
|
| 27 |
+
"group_size": 128,
|
| 28 |
+
"lm_head": false,
|
| 29 |
+
"meta": {
|
| 30 |
+
"damp_auto_increment": 0.0025,
|
| 31 |
+
"damp_percent": 0.01,
|
| 32 |
+
"mse": 0.0,
|
| 33 |
+
"quantizer": [
|
| 34 |
+
"gptqmodel:2.1.0"
|
| 35 |
+
],
|
| 36 |
+
"static_groups": false,
|
| 37 |
+
"true_sequential": true,
|
| 38 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 39 |
+
},
|
| 40 |
+
"pack_dtype": "int32",
|
| 41 |
+
"quant_method": "gptq",
|
| 42 |
+
"sym": true
|
| 43 |
+
},
|
| 44 |
+
"query_pre_attn_scalar": 168,
|
| 45 |
+
"rms_norm_eps": 1e-06,
|
| 46 |
+
"rope_local_base_freq": 10000.0,
|
| 47 |
+
"rope_scaling": {
|
| 48 |
+
"factor": 8.0,
|
| 49 |
+
"rope_type": "linear"
|
| 50 |
+
},
|
| 51 |
+
"rope_theta": 1000000.0,
|
| 52 |
+
"sliding_window": 1024,
|
| 53 |
+
"sliding_window_pattern": 6,
|
| 54 |
+
"torch_dtype": "bfloat16",
|
| 55 |
+
"transformers_version": "4.51.0.dev0",
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 262208
|
| 58 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1,
|
| 7 |
+
106
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"transformers_version": "4.51.0.dev0"
|
| 11 |
+
}
|
model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f548f774bb7ed5eb2aeb423838eb947dba4b308c7b99e0b05502f3facff8d47f
|
| 3 |
+
size 3987545168
|
model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0252dd63b23411f15b80c3d6520a59b58a15241132e726829410b17f84b4210d
|
| 3 |
+
size 3997409744
|
model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f202f0d2d0a0411278592cb8295f8bf51785b3ea1a98d620143afc8f88f4f440
|
| 3 |
+
size 3948698944
|
model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42a0f7116c9008d43d3dfaab4fc1a8a9ae4d45d42364c2d4b52e0173a0952d29
|
| 3 |
+
size 3997409896
|
model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bd574bf63e34081e97536f2a0ade1c9785a4145eb0ce293ea3ca0fbdfae290e
|
| 3 |
+
size 203308424
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quant_log.csv
ADDED
|
@@ -0,0 +1,435 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,damp,time
|
| 2 |
+
0,self_attn.k_proj,228.61710,0.01000,1.859
|
| 3 |
+
0,self_attn.v_proj,253.19312,0.01000,1.604
|
| 4 |
+
0,self_attn.q_proj,141.86264,0.01000,1.590
|
| 5 |
+
0,self_attn.o_proj,343.01404,0.01000,1.226
|
| 6 |
+
0,mlp.up_proj,39.20745,0.01000,1.646
|
| 7 |
+
0,mlp.gate_proj,39.89334,0.01000,1.639
|
| 8 |
+
0,mlp.down_proj,58.10246,0.01000,8.292
|
| 9 |
+
1,self_attn.k_proj,68.73937,0.01000,1.606
|
| 10 |
+
1,self_attn.v_proj,64.62814,0.01000,1.597
|
| 11 |
+
1,self_attn.q_proj,9.89349,0.01000,1.620
|
| 12 |
+
1,self_attn.o_proj,12.42410,0.01000,1.223
|
| 13 |
+
1,mlp.up_proj,30.04769,0.01000,1.682
|
| 14 |
+
1,mlp.gate_proj,38.34677,0.01000,1.668
|
| 15 |
+
1,mlp.down_proj,4.29689,0.01000,8.273
|
| 16 |
+
2,self_attn.k_proj,16.71628,0.01000,1.604
|
| 17 |
+
2,self_attn.v_proj,17.16328,0.01000,1.583
|
| 18 |
+
2,self_attn.q_proj,30.74933,0.01000,1.609
|
| 19 |
+
2,self_attn.o_proj,7.20554,0.01000,1.218
|
| 20 |
+
2,mlp.up_proj,42.72074,0.01000,1.665
|
| 21 |
+
2,mlp.gate_proj,44.59277,0.01000,1.655
|
| 22 |
+
2,mlp.down_proj,8.48032,0.01000,8.256
|
| 23 |
+
3,self_attn.k_proj,35.89268,0.01000,1.604
|
| 24 |
+
3,self_attn.v_proj,35.70708,0.01000,1.593
|
| 25 |
+
3,self_attn.q_proj,41.87522,0.01000,1.603
|
| 26 |
+
3,self_attn.o_proj,17.80805,0.01000,1.227
|
| 27 |
+
3,mlp.up_proj,74.39162,0.01000,1.667
|
| 28 |
+
3,mlp.gate_proj,105.57904,0.01000,1.659
|
| 29 |
+
3,mlp.down_proj,2.80403,0.01000,8.299
|
| 30 |
+
4,self_attn.k_proj,18.24422,0.01000,1.595
|
| 31 |
+
4,self_attn.v_proj,21.32573,0.01000,1.584
|
| 32 |
+
4,self_attn.q_proj,4.11614,0.01000,1.602
|
| 33 |
+
4,self_attn.o_proj,28.03704,0.01000,1.216
|
| 34 |
+
4,mlp.up_proj,101.50375,0.01000,1.674
|
| 35 |
+
4,mlp.gate_proj,107.20500,0.01000,1.661
|
| 36 |
+
4,mlp.down_proj,9.10312,0.01000,8.271
|
| 37 |
+
5,self_attn.k_proj,39.42845,0.01000,1.594
|
| 38 |
+
5,self_attn.v_proj,42.69853,0.01000,1.586
|
| 39 |
+
5,self_attn.q_proj,34.36060,0.01000,1.605
|
| 40 |
+
5,self_attn.o_proj,3.56486,0.01000,1.218
|
| 41 |
+
5,mlp.up_proj,142.57787,0.01000,1.683
|
| 42 |
+
5,mlp.gate_proj,142.91211,0.01000,1.669
|
| 43 |
+
5,mlp.down_proj,25.05610,0.01000,8.347
|
| 44 |
+
6,self_attn.k_proj,20.35823,0.01000,1.608
|
| 45 |
+
6,self_attn.v_proj,19.73539,0.01000,1.600
|
| 46 |
+
6,self_attn.q_proj,23.32359,0.01000,1.631
|
| 47 |
+
6,self_attn.o_proj,6.24194,0.01000,1.233
|
| 48 |
+
6,mlp.up_proj,116.53198,0.01000,1.684
|
| 49 |
+
6,mlp.gate_proj,118.43733,0.01000,1.673
|
| 50 |
+
6,mlp.down_proj,25.87358,0.01000,8.363
|
| 51 |
+
7,self_attn.k_proj,17.67576,0.01000,1.622
|
| 52 |
+
7,self_attn.v_proj,18.29718,0.01000,1.627
|
| 53 |
+
7,self_attn.q_proj,23.04462,0.01000,1.657
|
| 54 |
+
7,self_attn.o_proj,9.27544,0.01000,1.239
|
| 55 |
+
7,mlp.up_proj,26.80667,0.01000,1.700
|
| 56 |
+
7,mlp.gate_proj,27.09825,0.01000,1.693
|
| 57 |
+
7,mlp.down_proj,4.54449,0.01000,8.431
|
| 58 |
+
8,self_attn.k_proj,26.21228,0.01000,1.630
|
| 59 |
+
8,self_attn.v_proj,28.40262,0.01000,1.619
|
| 60 |
+
8,self_attn.q_proj,10.82491,0.01000,1.639
|
| 61 |
+
8,self_attn.o_proj,7.82063,0.01000,1.236
|
| 62 |
+
8,mlp.up_proj,25.34582,0.01000,1.702
|
| 63 |
+
8,mlp.gate_proj,25.62141,0.01000,1.689
|
| 64 |
+
8,mlp.down_proj,2.88563,0.01000,8.396
|
| 65 |
+
9,self_attn.k_proj,33.19525,0.01000,1.626
|
| 66 |
+
9,self_attn.v_proj,35.50793,0.01000,1.629
|
| 67 |
+
9,self_attn.q_proj,13.00117,0.01000,1.654
|
| 68 |
+
9,self_attn.o_proj,14.80057,0.01000,1.235
|
| 69 |
+
9,mlp.up_proj,45.20444,0.01000,1.695
|
| 70 |
+
9,mlp.gate_proj,45.30681,0.01000,1.686
|
| 71 |
+
9,mlp.down_proj,6.37110,0.01000,8.395
|
| 72 |
+
10,self_attn.k_proj,49.76878,0.01000,1.633
|
| 73 |
+
10,self_attn.v_proj,50.40453,0.01000,1.619
|
| 74 |
+
10,self_attn.q_proj,14.66619,0.01000,1.636
|
| 75 |
+
10,self_attn.o_proj,27.18292,0.01000,1.240
|
| 76 |
+
10,mlp.up_proj,47.51447,0.01000,1.703
|
| 77 |
+
10,mlp.gate_proj,48.56642,0.01000,1.702
|
| 78 |
+
10,mlp.down_proj,5.15361,0.01000,8.418
|
| 79 |
+
11,self_attn.k_proj,38.24666,0.01000,1.637
|
| 80 |
+
11,self_attn.v_proj,30.07842,0.01000,1.634
|
| 81 |
+
11,self_attn.q_proj,58.60720,0.01000,1.659
|
| 82 |
+
11,self_attn.o_proj,7.89761,0.01000,1.251
|
| 83 |
+
11,mlp.up_proj,134.22287,0.01000,1.720
|
| 84 |
+
11,mlp.gate_proj,141.32153,0.01000,1.701
|
| 85 |
+
11,mlp.down_proj,9.60527,0.01000,8.469
|
| 86 |
+
12,self_attn.k_proj,92.23084,0.01000,1.626
|
| 87 |
+
12,self_attn.v_proj,82.09882,0.01000,1.612
|
| 88 |
+
12,self_attn.q_proj,127.59977,0.01000,1.631
|
| 89 |
+
12,self_attn.o_proj,14.53280,0.01000,1.243
|
| 90 |
+
12,mlp.up_proj,1531.11389,0.01000,1.708
|
| 91 |
+
12,mlp.gate_proj,1551.58765,0.01000,1.696
|
| 92 |
+
12,mlp.down_proj,178.51028,0.01000,8.401
|
| 93 |
+
13,self_attn.k_proj,279.33826,0.01000,1.625
|
| 94 |
+
13,self_attn.v_proj,253.20819,0.01000,1.642
|
| 95 |
+
13,self_attn.q_proj,83.87119,0.01000,1.653
|
| 96 |
+
13,self_attn.o_proj,123.21405,0.01000,1.242
|
| 97 |
+
13,mlp.up_proj,746.59186,0.01000,1.713
|
| 98 |
+
13,mlp.gate_proj,743.17670,0.01000,1.693
|
| 99 |
+
13,mlp.down_proj,145.95303,0.01000,8.420
|
| 100 |
+
14,self_attn.k_proj,107.20930,0.01000,1.625
|
| 101 |
+
14,self_attn.v_proj,97.85188,0.01000,1.616
|
| 102 |
+
14,self_attn.q_proj,124.41954,0.01000,1.640
|
| 103 |
+
14,self_attn.o_proj,63.05926,0.01000,1.241
|
| 104 |
+
14,mlp.up_proj,55.34809,0.01000,1.700
|
| 105 |
+
14,mlp.gate_proj,55.17800,0.01000,1.694
|
| 106 |
+
14,mlp.down_proj,1.47162,0.01000,8.401
|
| 107 |
+
15,self_attn.k_proj,21.91747,0.01000,1.631
|
| 108 |
+
15,self_attn.v_proj,21.43095,0.01000,1.618
|
| 109 |
+
15,self_attn.q_proj,39.50624,0.01000,1.635
|
| 110 |
+
15,self_attn.o_proj,4.70265,0.01000,1.244
|
| 111 |
+
15,mlp.up_proj,32.41655,0.01000,1.701
|
| 112 |
+
15,mlp.gate_proj,32.51458,0.01000,1.697
|
| 113 |
+
15,mlp.down_proj,0.56551,0.01000,8.405
|
| 114 |
+
16,self_attn.k_proj,19.90011,0.01000,1.624
|
| 115 |
+
16,self_attn.v_proj,21.37067,0.01000,1.613
|
| 116 |
+
16,self_attn.q_proj,13.31114,0.01000,1.648
|
| 117 |
+
16,self_attn.o_proj,15.69799,0.01000,1.235
|
| 118 |
+
16,mlp.up_proj,27.74037,0.01000,1.710
|
| 119 |
+
16,mlp.gate_proj,27.70950,0.01000,1.701
|
| 120 |
+
16,mlp.down_proj,0.52529,0.01000,8.395
|
| 121 |
+
17,self_attn.k_proj,38.53021,0.01000,1.633
|
| 122 |
+
17,self_attn.v_proj,27.09827,0.01000,1.627
|
| 123 |
+
17,self_attn.q_proj,6.20501,0.01000,1.634
|
| 124 |
+
17,self_attn.o_proj,7.87432,0.01000,1.246
|
| 125 |
+
17,mlp.up_proj,17.71177,0.01000,1.698
|
| 126 |
+
17,mlp.gate_proj,17.88526,0.01000,1.693
|
| 127 |
+
17,mlp.down_proj,0.71275,0.01000,8.404
|
| 128 |
+
18,self_attn.k_proj,12.09626,0.01000,1.618
|
| 129 |
+
18,self_attn.v_proj,10.76769,0.01000,1.612
|
| 130 |
+
18,self_attn.q_proj,8.02076,0.01000,1.642
|
| 131 |
+
18,self_attn.o_proj,7.45883,0.01000,1.239
|
| 132 |
+
18,mlp.up_proj,21.86592,0.01000,1.699
|
| 133 |
+
18,mlp.gate_proj,21.87827,0.01000,1.692
|
| 134 |
+
18,mlp.down_proj,0.34997,0.01000,8.380
|
| 135 |
+
19,self_attn.k_proj,25.55136,0.01000,1.627
|
| 136 |
+
19,self_attn.v_proj,23.27475,0.01000,1.615
|
| 137 |
+
19,self_attn.q_proj,3.79012,0.01000,1.634
|
| 138 |
+
19,self_attn.o_proj,7.35642,0.01000,1.243
|
| 139 |
+
19,mlp.up_proj,23.84431,0.01000,1.705
|
| 140 |
+
19,mlp.gate_proj,23.71142,0.01000,1.699
|
| 141 |
+
19,mlp.down_proj,0.39274,0.01000,8.410
|
| 142 |
+
20,self_attn.k_proj,6.90577,0.01000,1.628
|
| 143 |
+
20,self_attn.v_proj,6.13503,0.01000,1.616
|
| 144 |
+
20,self_attn.q_proj,11.11080,0.01000,1.630
|
| 145 |
+
20,self_attn.o_proj,2.09453,0.01000,1.247
|
| 146 |
+
20,mlp.up_proj,11.84045,0.01000,1.699
|
| 147 |
+
20,mlp.gate_proj,11.80899,0.01000,1.689
|
| 148 |
+
20,mlp.down_proj,0.15950,0.01000,8.389
|
| 149 |
+
21,self_attn.k_proj,6.40497,0.01000,1.631
|
| 150 |
+
21,self_attn.v_proj,5.66493,0.01000,1.617
|
| 151 |
+
21,self_attn.q_proj,4.97676,0.01000,1.641
|
| 152 |
+
21,self_attn.o_proj,3.06990,0.01000,1.253
|
| 153 |
+
21,mlp.up_proj,11.49875,0.01000,1.709
|
| 154 |
+
21,mlp.gate_proj,11.48977,0.01000,1.702
|
| 155 |
+
21,mlp.down_proj,0.07881,0.01000,8.394
|
| 156 |
+
22,self_attn.k_proj,11.57931,0.01000,1.621
|
| 157 |
+
22,self_attn.v_proj,11.31033,0.01000,1.615
|
| 158 |
+
22,self_attn.q_proj,1.74686,0.01000,1.637
|
| 159 |
+
22,self_attn.o_proj,3.35387,0.01000,1.239
|
| 160 |
+
22,mlp.up_proj,8.66117,0.01000,1.707
|
| 161 |
+
22,mlp.gate_proj,8.55637,0.01000,1.695
|
| 162 |
+
22,mlp.down_proj,0.10522,0.01000,8.410
|
| 163 |
+
23,self_attn.k_proj,2.13826,0.01000,1.631
|
| 164 |
+
23,self_attn.v_proj,1.46145,0.01000,1.619
|
| 165 |
+
23,self_attn.q_proj,3.14328,0.01000,1.638
|
| 166 |
+
23,self_attn.o_proj,0.28105,0.01000,1.248
|
| 167 |
+
23,mlp.up_proj,9.16744,0.01000,1.704
|
| 168 |
+
23,mlp.gate_proj,9.11455,0.01000,1.697
|
| 169 |
+
23,mlp.down_proj,0.11369,0.01000,8.412
|
| 170 |
+
24,self_attn.k_proj,3.20562,0.01000,1.625
|
| 171 |
+
24,self_attn.v_proj,2.95845,0.01000,1.618
|
| 172 |
+
24,self_attn.q_proj,2.61312,0.01000,1.637
|
| 173 |
+
24,self_attn.o_proj,0.32490,0.01000,1.245
|
| 174 |
+
24,mlp.up_proj,5.22255,0.01000,1.701
|
| 175 |
+
24,mlp.gate_proj,5.14847,0.01000,1.691
|
| 176 |
+
24,mlp.down_proj,0.05143,0.01000,8.429
|
| 177 |
+
25,self_attn.k_proj,5.18417,0.01000,1.635
|
| 178 |
+
25,self_attn.v_proj,4.22279,0.01000,1.627
|
| 179 |
+
25,self_attn.q_proj,3.39733,0.01000,1.643
|
| 180 |
+
25,self_attn.o_proj,0.90181,0.01000,1.249
|
| 181 |
+
25,mlp.up_proj,3.69477,0.01000,1.709
|
| 182 |
+
25,mlp.gate_proj,3.65683,0.01000,1.711
|
| 183 |
+
25,mlp.down_proj,0.02214,0.01000,8.414
|
| 184 |
+
26,self_attn.k_proj,5.50272,0.01000,1.625
|
| 185 |
+
26,self_attn.v_proj,4.46497,0.01000,1.617
|
| 186 |
+
26,self_attn.q_proj,1.94561,0.01000,1.635
|
| 187 |
+
26,self_attn.o_proj,0.76609,0.01000,1.246
|
| 188 |
+
26,mlp.up_proj,4.93344,0.01000,1.705
|
| 189 |
+
26,mlp.gate_proj,4.96636,0.01000,1.698
|
| 190 |
+
26,mlp.down_proj,0.02780,0.01000,8.426
|
| 191 |
+
27,self_attn.k_proj,3.87448,0.01000,1.635
|
| 192 |
+
27,self_attn.v_proj,3.50186,0.01000,1.645
|
| 193 |
+
27,self_attn.q_proj,1.99635,0.01000,1.665
|
| 194 |
+
27,self_attn.o_proj,0.70769,0.01000,1.245
|
| 195 |
+
27,mlp.up_proj,5.56347,0.01000,1.700
|
| 196 |
+
27,mlp.gate_proj,5.74508,0.01000,1.695
|
| 197 |
+
27,mlp.down_proj,0.04068,0.01000,8.433
|
| 198 |
+
28,self_attn.k_proj,5.33674,0.01000,1.641
|
| 199 |
+
28,self_attn.v_proj,5.66915,0.01000,1.633
|
| 200 |
+
28,self_attn.q_proj,3.14792,0.01000,1.639
|
| 201 |
+
28,self_attn.o_proj,0.59076,0.01000,1.243
|
| 202 |
+
28,mlp.up_proj,7.30727,0.01000,1.723
|
| 203 |
+
28,mlp.gate_proj,7.44583,0.01000,1.702
|
| 204 |
+
28,mlp.down_proj,0.05279,0.01000,8.420
|
| 205 |
+
29,self_attn.k_proj,2.30108,0.01000,1.646
|
| 206 |
+
29,self_attn.v_proj,1.99803,0.01000,1.633
|
| 207 |
+
29,self_attn.q_proj,1.18276,0.01000,1.651
|
| 208 |
+
29,self_attn.o_proj,0.18813,0.01000,1.243
|
| 209 |
+
29,mlp.up_proj,2.44259,0.01000,1.712
|
| 210 |
+
29,mlp.gate_proj,2.46862,0.01000,1.702
|
| 211 |
+
29,mlp.down_proj,0.00356,0.01000,8.403
|
| 212 |
+
30,self_attn.k_proj,7.56893,0.01000,1.629
|
| 213 |
+
30,self_attn.v_proj,6.63914,0.01000,1.623
|
| 214 |
+
30,self_attn.q_proj,5.64964,0.01000,1.640
|
| 215 |
+
30,self_attn.o_proj,0.91798,0.01000,1.243
|
| 216 |
+
30,mlp.up_proj,10.99388,0.01000,1.715
|
| 217 |
+
30,mlp.gate_proj,11.44204,0.01000,1.705
|
| 218 |
+
30,mlp.down_proj,0.04197,0.01000,8.420
|
| 219 |
+
31,self_attn.k_proj,27.32435,0.01000,1.636
|
| 220 |
+
31,self_attn.v_proj,25.26109,0.01000,1.621
|
| 221 |
+
31,self_attn.q_proj,4.12010,0.01000,1.638
|
| 222 |
+
31,self_attn.o_proj,4.92093,0.01000,1.238
|
| 223 |
+
31,mlp.up_proj,18.09216,0.01000,1.706
|
| 224 |
+
31,mlp.gate_proj,18.92633,0.01000,1.699
|
| 225 |
+
31,mlp.down_proj,0.08796,0.01000,8.404
|
| 226 |
+
32,self_attn.k_proj,17.63780,0.01000,1.633
|
| 227 |
+
32,self_attn.v_proj,14.50406,0.01000,1.623
|
| 228 |
+
32,self_attn.q_proj,4.68514,0.01000,1.638
|
| 229 |
+
32,self_attn.o_proj,2.07737,0.01000,1.244
|
| 230 |
+
32,mlp.up_proj,22.74578,0.01000,1.700
|
| 231 |
+
32,mlp.gate_proj,23.43541,0.01000,1.700
|
| 232 |
+
32,mlp.down_proj,0.27088,0.01000,8.420
|
| 233 |
+
33,self_attn.k_proj,43.51965,0.01000,1.635
|
| 234 |
+
33,self_attn.v_proj,35.21978,0.01000,1.622
|
| 235 |
+
33,self_attn.q_proj,4.97384,0.01000,1.638
|
| 236 |
+
33,self_attn.o_proj,7.17438,0.01000,1.248
|
| 237 |
+
33,mlp.up_proj,43.77799,0.01000,1.709
|
| 238 |
+
33,mlp.gate_proj,44.57782,0.01000,1.700
|
| 239 |
+
33,mlp.down_proj,0.19801,0.01000,8.433
|
| 240 |
+
34,self_attn.k_proj,12.86186,0.01000,1.617
|
| 241 |
+
34,self_attn.v_proj,13.76353,0.01000,1.606
|
| 242 |
+
34,self_attn.q_proj,15.68283,0.01000,1.628
|
| 243 |
+
34,self_attn.o_proj,2.71512,0.01000,1.244
|
| 244 |
+
34,mlp.up_proj,31.24583,0.01000,1.702
|
| 245 |
+
34,mlp.gate_proj,31.97413,0.01000,1.691
|
| 246 |
+
34,mlp.down_proj,0.34339,0.01000,8.391
|
| 247 |
+
35,self_attn.k_proj,5.05635,0.01000,1.620
|
| 248 |
+
35,self_attn.v_proj,4.47835,0.01000,1.607
|
| 249 |
+
35,self_attn.q_proj,2.86904,0.01000,1.628
|
| 250 |
+
35,self_attn.o_proj,0.32139,0.01000,1.244
|
| 251 |
+
35,mlp.up_proj,18.41906,0.01000,1.693
|
| 252 |
+
35,mlp.gate_proj,19.39206,0.01000,1.689
|
| 253 |
+
35,mlp.down_proj,0.19236,0.01000,8.396
|
| 254 |
+
36,self_attn.k_proj,14.36123,0.01000,1.619
|
| 255 |
+
36,self_attn.v_proj,12.41433,0.01000,1.612
|
| 256 |
+
36,self_attn.q_proj,10.97218,0.01000,1.626
|
| 257 |
+
36,self_attn.o_proj,3.00873,0.01000,1.240
|
| 258 |
+
36,mlp.up_proj,13.00223,0.01000,1.692
|
| 259 |
+
36,mlp.gate_proj,14.43905,0.01000,1.691
|
| 260 |
+
36,mlp.down_proj,0.05659,0.01000,8.409
|
| 261 |
+
37,self_attn.k_proj,17.05149,0.01000,1.637
|
| 262 |
+
37,self_attn.v_proj,14.10710,0.01000,1.621
|
| 263 |
+
37,self_attn.q_proj,26.26060,0.01000,1.638
|
| 264 |
+
37,self_attn.o_proj,0.74077,0.01000,1.248
|
| 265 |
+
37,mlp.up_proj,35.04345,0.01000,1.709
|
| 266 |
+
37,mlp.gate_proj,36.27655,0.01000,1.698
|
| 267 |
+
37,mlp.down_proj,0.29616,0.01000,8.425
|
| 268 |
+
38,self_attn.k_proj,21.28798,0.01000,1.632
|
| 269 |
+
38,self_attn.v_proj,20.35888,0.01000,1.627
|
| 270 |
+
38,self_attn.q_proj,11.64089,0.01000,1.656
|
| 271 |
+
38,self_attn.o_proj,3.13686,0.01000,1.248
|
| 272 |
+
38,mlp.up_proj,32.37619,0.01000,1.707
|
| 273 |
+
38,mlp.gate_proj,33.53392,0.01000,1.699
|
| 274 |
+
38,mlp.down_proj,0.26396,0.01000,8.413
|
| 275 |
+
39,self_attn.k_proj,16.45259,0.01000,1.628
|
| 276 |
+
39,self_attn.v_proj,15.78872,0.01000,1.627
|
| 277 |
+
39,self_attn.q_proj,23.90717,0.01000,1.649
|
| 278 |
+
39,self_attn.o_proj,1.45637,0.01000,1.236
|
| 279 |
+
39,mlp.up_proj,15.36781,0.01000,1.744
|
| 280 |
+
39,mlp.gate_proj,15.91610,0.01000,1.736
|
| 281 |
+
39,mlp.down_proj,0.18938,0.01000,8.589
|
| 282 |
+
40,self_attn.k_proj,50.10992,0.01000,1.665
|
| 283 |
+
40,self_attn.v_proj,47.26633,0.01000,1.655
|
| 284 |
+
40,self_attn.q_proj,40.49951,0.01000,1.686
|
| 285 |
+
40,self_attn.o_proj,1.08072,0.01000,1.270
|
| 286 |
+
40,mlp.up_proj,34.10712,0.01000,1.675
|
| 287 |
+
40,mlp.gate_proj,35.48123,0.01000,1.666
|
| 288 |
+
40,mlp.down_proj,0.33496,0.01000,8.315
|
| 289 |
+
41,self_attn.k_proj,24.13440,0.01000,1.613
|
| 290 |
+
41,self_attn.v_proj,22.26254,0.01000,1.607
|
| 291 |
+
41,self_attn.q_proj,10.29479,0.01000,1.630
|
| 292 |
+
41,self_attn.o_proj,0.37990,0.01000,1.227
|
| 293 |
+
41,mlp.up_proj,58.37737,0.01000,1.689
|
| 294 |
+
41,mlp.gate_proj,58.85928,0.01000,1.682
|
| 295 |
+
41,mlp.down_proj,0.33492,0.01000,8.348
|
| 296 |
+
42,self_attn.k_proj,71.86662,0.01000,1.602
|
| 297 |
+
42,self_attn.v_proj,70.38354,0.01000,1.596
|
| 298 |
+
42,self_attn.q_proj,11.22902,0.01000,1.627
|
| 299 |
+
42,self_attn.o_proj,6.18760,0.01000,1.229
|
| 300 |
+
42,mlp.up_proj,50.17612,0.01000,1.694
|
| 301 |
+
42,mlp.gate_proj,51.98317,0.01000,1.677
|
| 302 |
+
42,mlp.down_proj,0.22622,0.01000,8.321
|
| 303 |
+
43,self_attn.k_proj,24.16352,0.01000,1.613
|
| 304 |
+
43,self_attn.v_proj,28.41705,0.01000,1.608
|
| 305 |
+
43,self_attn.q_proj,32.22251,0.01000,1.628
|
| 306 |
+
43,self_attn.o_proj,1.04317,0.01000,1.233
|
| 307 |
+
43,mlp.up_proj,53.42929,0.01000,1.690
|
| 308 |
+
43,mlp.gate_proj,55.53038,0.01000,1.685
|
| 309 |
+
43,mlp.down_proj,0.36819,0.01000,8.335
|
| 310 |
+
44,self_attn.k_proj,46.85324,0.01000,1.603
|
| 311 |
+
44,self_attn.v_proj,41.58362,0.01000,1.596
|
| 312 |
+
44,self_attn.q_proj,51.17185,0.01000,1.627
|
| 313 |
+
44,self_attn.o_proj,3.43868,0.01000,1.230
|
| 314 |
+
44,mlp.up_proj,47.37805,0.01000,1.671
|
| 315 |
+
44,mlp.gate_proj,49.59990,0.01000,1.678
|
| 316 |
+
44,mlp.down_proj,0.15065,0.01000,8.347
|
| 317 |
+
45,self_attn.k_proj,22.02085,0.01000,1.606
|
| 318 |
+
45,self_attn.v_proj,20.08329,0.01000,1.593
|
| 319 |
+
45,self_attn.q_proj,39.96657,0.01000,1.637
|
| 320 |
+
45,self_attn.o_proj,0.83174,0.01000,1.231
|
| 321 |
+
45,mlp.up_proj,38.94197,0.01000,1.681
|
| 322 |
+
45,mlp.gate_proj,40.51783,0.01000,1.684
|
| 323 |
+
45,mlp.down_proj,0.52019,0.01000,8.337
|
| 324 |
+
46,self_attn.k_proj,11.95531,0.01000,1.614
|
| 325 |
+
46,self_attn.v_proj,12.26899,0.01000,1.598
|
| 326 |
+
46,self_attn.q_proj,22.65367,0.01000,1.616
|
| 327 |
+
46,self_attn.o_proj,0.35513,0.01000,1.234
|
| 328 |
+
46,mlp.up_proj,32.64047,0.01000,1.688
|
| 329 |
+
46,mlp.gate_proj,34.08441,0.01000,1.673
|
| 330 |
+
46,mlp.down_proj,0.53210,0.01000,8.343
|
| 331 |
+
47,self_attn.k_proj,14.22702,0.01000,1.612
|
| 332 |
+
47,self_attn.v_proj,12.20604,0.01000,1.612
|
| 333 |
+
47,self_attn.q_proj,2.20028,0.01000,1.628
|
| 334 |
+
47,self_attn.o_proj,0.31628,0.01000,1.232
|
| 335 |
+
47,mlp.up_proj,47.62271,0.01000,1.691
|
| 336 |
+
47,mlp.gate_proj,49.25999,0.01000,1.680
|
| 337 |
+
47,mlp.down_proj,0.17228,0.01000,8.329
|
| 338 |
+
48,self_attn.k_proj,69.72502,0.01000,1.638
|
| 339 |
+
48,self_attn.v_proj,66.82695,0.01000,1.628
|
| 340 |
+
48,self_attn.q_proj,53.00145,0.01000,1.634
|
| 341 |
+
48,self_attn.o_proj,0.38267,0.01000,1.232
|
| 342 |
+
48,mlp.up_proj,39.56243,0.01000,1.691
|
| 343 |
+
48,mlp.gate_proj,40.98708,0.01000,1.684
|
| 344 |
+
48,mlp.down_proj,0.37443,0.01000,8.364
|
| 345 |
+
49,self_attn.k_proj,48.89702,0.01000,1.622
|
| 346 |
+
49,self_attn.v_proj,47.90273,0.01000,1.613
|
| 347 |
+
49,self_attn.q_proj,30.51980,0.01000,1.629
|
| 348 |
+
49,self_attn.o_proj,1.08022,0.01000,1.242
|
| 349 |
+
49,mlp.up_proj,35.45297,0.01000,1.705
|
| 350 |
+
49,mlp.gate_proj,36.89193,0.01000,1.694
|
| 351 |
+
49,mlp.down_proj,0.40299,0.01000,8.395
|
| 352 |
+
50,self_attn.k_proj,25.64360,0.01000,1.623
|
| 353 |
+
50,self_attn.v_proj,23.66824,0.01000,1.628
|
| 354 |
+
50,self_attn.q_proj,29.76320,0.01000,1.634
|
| 355 |
+
50,self_attn.o_proj,0.26762,0.01000,1.246
|
| 356 |
+
50,mlp.up_proj,55.41055,0.01000,1.703
|
| 357 |
+
50,mlp.gate_proj,57.46595,0.01000,1.693
|
| 358 |
+
50,mlp.down_proj,0.30881,0.01000,8.392
|
| 359 |
+
51,self_attn.k_proj,24.91245,0.01000,1.618
|
| 360 |
+
51,self_attn.v_proj,23.78001,0.01000,1.611
|
| 361 |
+
51,self_attn.q_proj,11.26177,0.01000,1.627
|
| 362 |
+
51,self_attn.o_proj,0.35665,0.01000,1.236
|
| 363 |
+
51,mlp.up_proj,66.81348,0.01000,1.699
|
| 364 |
+
51,mlp.gate_proj,70.68529,0.01000,1.694
|
| 365 |
+
51,mlp.down_proj,0.18631,0.01000,8.390
|
| 366 |
+
52,self_attn.k_proj,76.72678,0.01000,1.626
|
| 367 |
+
52,self_attn.v_proj,65.61713,0.01000,1.618
|
| 368 |
+
52,self_attn.q_proj,17.33953,0.01000,1.651
|
| 369 |
+
52,self_attn.o_proj,3.57008,0.01000,1.239
|
| 370 |
+
52,mlp.up_proj,33.83653,0.01000,1.698
|
| 371 |
+
52,mlp.gate_proj,35.52644,0.01000,1.689
|
| 372 |
+
52,mlp.down_proj,0.14117,0.01000,8.390
|
| 373 |
+
53,self_attn.k_proj,6.02739,0.01000,1.635
|
| 374 |
+
53,self_attn.v_proj,4.99095,0.01000,1.605
|
| 375 |
+
53,self_attn.q_proj,2.38112,0.01000,1.634
|
| 376 |
+
53,self_attn.o_proj,0.13655,0.01000,1.236
|
| 377 |
+
53,mlp.up_proj,54.88012,0.01000,1.702
|
| 378 |
+
53,mlp.gate_proj,56.61061,0.01000,1.696
|
| 379 |
+
53,mlp.down_proj,0.22378,0.01000,8.387
|
| 380 |
+
54,self_attn.k_proj,62.40906,0.01000,1.631
|
| 381 |
+
54,self_attn.v_proj,44.34687,0.01000,1.613
|
| 382 |
+
54,self_attn.q_proj,9.88544,0.01000,1.629
|
| 383 |
+
54,self_attn.o_proj,5.96977,0.01000,1.235
|
| 384 |
+
54,mlp.up_proj,41.97146,0.01000,1.704
|
| 385 |
+
54,mlp.gate_proj,44.11252,0.01000,1.691
|
| 386 |
+
54,mlp.down_proj,0.15743,0.01000,8.381
|
| 387 |
+
55,self_attn.k_proj,20.18746,0.01000,1.623
|
| 388 |
+
55,self_attn.v_proj,16.57866,0.01000,1.611
|
| 389 |
+
55,self_attn.q_proj,11.99167,0.01000,1.628
|
| 390 |
+
55,self_attn.o_proj,1.03882,0.01000,1.240
|
| 391 |
+
55,mlp.up_proj,22.49954,0.01000,1.698
|
| 392 |
+
55,mlp.gate_proj,24.16374,0.01000,1.684
|
| 393 |
+
55,mlp.down_proj,0.32182,0.01000,8.374
|
| 394 |
+
56,self_attn.k_proj,25.27939,0.01000,1.640
|
| 395 |
+
56,self_attn.v_proj,19.44360,0.01000,1.627
|
| 396 |
+
56,self_attn.q_proj,4.47221,0.01000,1.646
|
| 397 |
+
56,self_attn.o_proj,1.72548,0.01000,1.235
|
| 398 |
+
56,mlp.up_proj,35.78206,0.01000,1.697
|
| 399 |
+
56,mlp.gate_proj,37.53625,0.01000,1.691
|
| 400 |
+
56,mlp.down_proj,0.65465,0.01000,8.370
|
| 401 |
+
57,self_attn.k_proj,78.86345,0.01000,1.628
|
| 402 |
+
57,self_attn.v_proj,71.02533,0.01000,1.625
|
| 403 |
+
57,self_attn.q_proj,10.98545,0.01000,1.646
|
| 404 |
+
57,self_attn.o_proj,2.36102,0.01000,1.240
|
| 405 |
+
57,mlp.up_proj,29.29268,0.01000,1.700
|
| 406 |
+
57,mlp.gate_proj,30.41135,0.01000,1.688
|
| 407 |
+
57,mlp.down_proj,0.14196,0.01000,8.404
|
| 408 |
+
58,self_attn.k_proj,17.03829,0.01000,1.626
|
| 409 |
+
58,self_attn.v_proj,14.34860,0.01000,1.630
|
| 410 |
+
58,self_attn.q_proj,3.87453,0.01000,1.657
|
| 411 |
+
58,self_attn.o_proj,1.55878,0.01000,1.231
|
| 412 |
+
58,mlp.up_proj,28.00947,0.01000,1.699
|
| 413 |
+
58,mlp.gate_proj,29.39889,0.01000,1.696
|
| 414 |
+
58,mlp.down_proj,0.36589,0.01000,8.406
|
| 415 |
+
59,self_attn.k_proj,2.70538,0.01000,1.623
|
| 416 |
+
59,self_attn.v_proj,3.59334,0.01000,1.617
|
| 417 |
+
59,self_attn.q_proj,0.40994,0.01000,1.655
|
| 418 |
+
59,self_attn.o_proj,0.10198,0.01000,1.245
|
| 419 |
+
59,mlp.up_proj,32.59032,0.01000,1.701
|
| 420 |
+
59,mlp.gate_proj,33.59875,0.01000,1.692
|
| 421 |
+
59,mlp.down_proj,0.70942,0.01000,8.394
|
| 422 |
+
60,self_attn.k_proj,25.07774,0.01000,1.632
|
| 423 |
+
60,self_attn.v_proj,23.43358,0.01000,1.630
|
| 424 |
+
60,self_attn.q_proj,8.01662,0.01000,1.648
|
| 425 |
+
60,self_attn.o_proj,3.67056,0.01000,1.243
|
| 426 |
+
60,mlp.up_proj,45.98669,0.01000,1.693
|
| 427 |
+
60,mlp.gate_proj,47.14082,0.01000,1.681
|
| 428 |
+
60,mlp.down_proj,0.84004,0.01000,8.378
|
| 429 |
+
61,self_attn.k_proj,5.30617,0.01000,1.627
|
| 430 |
+
61,self_attn.v_proj,4.88027,0.01000,1.611
|
| 431 |
+
61,self_attn.q_proj,6.98521,0.01000,1.631
|
| 432 |
+
61,self_attn.o_proj,0.35971,0.01000,1.246
|
| 433 |
+
61,mlp.up_proj,26.23523,0.01000,1.693
|
| 434 |
+
61,mlp.gate_proj,27.52951,0.01000,1.684
|
| 435 |
+
61,mlp.down_proj,0.14450,0.01000,8.433
|
quantize_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"desc_act": true,
|
| 5 |
+
"sym": true,
|
| 6 |
+
"lm_head": false,
|
| 7 |
+
"quant_method": "gptq",
|
| 8 |
+
"checkpoint_format": "gptq",
|
| 9 |
+
"pack_dtype": "int32",
|
| 10 |
+
"meta": {
|
| 11 |
+
"quantizer": [
|
| 12 |
+
"gptqmodel:2.1.0"
|
| 13 |
+
],
|
| 14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
+
"damp_percent": 0.01,
|
| 16 |
+
"damp_auto_increment": 0.0025,
|
| 17 |
+
"static_groups": false,
|
| 18 |
+
"true_sequential": true,
|
| 19 |
+
"mse": 0.0
|
| 20 |
+
}
|
| 21 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<end_of_turn>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": "<pad>",
|
| 20 |
+
"unk_token": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
}
|
| 27 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|