Upload folder using huggingface_hub
Browse files- chat_template.jinja +5 -0
- config.json +53 -0
- generation_config.json +9 -0
- model-00001-of-00019.safetensors +3 -0
- model-00002-of-00019.safetensors +3 -0
- model-00003-of-00019.safetensors +3 -0
- model-00004-of-00019.safetensors +3 -0
- model-00005-of-00019.safetensors +3 -0
- model-00006-of-00019.safetensors +3 -0
- model-00007-of-00019.safetensors +3 -0
- model-00008-of-00019.safetensors +3 -0
- model-00009-of-00019.safetensors +3 -0
- model-00010-of-00019.safetensors +3 -0
- model-00011-of-00019.safetensors +3 -0
- model-00012-of-00019.safetensors +3 -0
- model-00013-of-00019.safetensors +3 -0
- model-00014-of-00019.safetensors +3 -0
- model-00015-of-00019.safetensors +3 -0
- model-00016-of-00019.safetensors +3 -0
- model-00017-of-00019.safetensors +3 -0
- model-00018-of-00019.safetensors +3 -0
- model-00019-of-00019.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quant_log.csv +666 -0
- quantize_config.json +24 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +138 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '
|
| 2 |
+
|
| 3 |
+
' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '
|
| 4 |
+
|
| 5 |
+
' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100000,
|
| 8 |
+
"eos_token_id": 100001,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 8192,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 22016,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 64,
|
| 18 |
+
"num_hidden_layers": 95,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"quantization_config": {
|
| 22 |
+
"bits": 8,
|
| 23 |
+
"checkpoint_format": "gptq",
|
| 24 |
+
"desc_act": true,
|
| 25 |
+
"group_size": 128,
|
| 26 |
+
"hyb_act": false,
|
| 27 |
+
"lm_head": false,
|
| 28 |
+
"meta": {
|
| 29 |
+
"damp_auto_increment": 0.01,
|
| 30 |
+
"damp_percent": 0.05,
|
| 31 |
+
"mse": 0.0,
|
| 32 |
+
"quantizer": [
|
| 33 |
+
"gptqmodel:4.0.0"
|
| 34 |
+
],
|
| 35 |
+
"static_groups": false,
|
| 36 |
+
"true_sequential": true,
|
| 37 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 38 |
+
"v2": false,
|
| 39 |
+
"v2_alpha": 0.25
|
| 40 |
+
},
|
| 41 |
+
"pack_dtype": "int32",
|
| 42 |
+
"quant_method": "gptq",
|
| 43 |
+
"sym": true
|
| 44 |
+
},
|
| 45 |
+
"rms_norm_eps": 1e-06,
|
| 46 |
+
"rope_scaling": null,
|
| 47 |
+
"rope_theta": 10000.0,
|
| 48 |
+
"tie_word_embeddings": false,
|
| 49 |
+
"torch_dtype": "bfloat16",
|
| 50 |
+
"transformers_version": "4.55.4",
|
| 51 |
+
"use_cache": true,
|
| 52 |
+
"vocab_size": 102400
|
| 53 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 100001,
|
| 6 |
+
"temperature": 0.7,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.55.4"
|
| 9 |
+
}
|
model-00001-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a2e5e421ed8d82fd2caba3562a150c4b8e36bbcf0b439ac6a10abd6376bf2d2
|
| 3 |
+
size 3958191872
|
model-00002-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88d4b6a73a574247f3cc378d2f2e522564e44af2461b8fe3928bfd879605d4cd
|
| 3 |
+
size 3912236384
|
model-00003-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dcdd3f0a2d76a8f39f9d6d484aa5dede28745a0473ea4ed91133f4eec7ff410
|
| 3 |
+
size 3882376232
|
model-00004-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b295d4b306eaf009ed738a59466012ff790b9a87067d9d87512e7d99c7b406c5
|
| 3 |
+
size 3912236544
|
model-00005-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17e1201055528e4242aa8aa8906987530d5e89658024efb9d3fc1bfb3e7acee7
|
| 3 |
+
size 3882376264
|
model-00006-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf325e8fa2000993b667205c0d11f4aebd5687576afc986efdc0138fdd4db2ac
|
| 3 |
+
size 3912236544
|
model-00007-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aab2fbec2208f741f00c0b5924486169e99ceb81ab14bbf24b06298cd35a6549
|
| 3 |
+
size 3882376264
|
model-00008-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b524e97a2cf956400d27bc41d4e72ef42e720214c8e796abfd5ba83c70a7089c
|
| 3 |
+
size 3912236544
|
model-00009-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5419eb2f7929b7d6e3c50c556922ffb6e0c84e711042ec725cfbbd8b1905de7
|
| 3 |
+
size 3882376264
|
model-00010-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b8fc53e8a7e4908e71ebcdce9937064b5026554a6c4acc3ad215bcbc7ab39bd
|
| 3 |
+
size 3912236544
|
model-00011-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5630fd54a5fea051daafb5d03e0d1c5c5d20275cd2c893365d3ee59cd493fe2c
|
| 3 |
+
size 3882376264
|
model-00012-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99fe4a8a99821a63225f5ca21f5850a35708c5e0e9ddb477eba030a4be9f1467
|
| 3 |
+
size 3912236544
|
model-00013-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d54be5a324cb1f11c5b86ebd92fd4f56bb2909b857b0950e622262bafe74b96
|
| 3 |
+
size 3882376264
|
model-00014-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14b2391ece2abe2f56fc898ff19c69b830d8550afbe9fbc33164922cedfcbf3b
|
| 3 |
+
size 3912236544
|
model-00015-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40e4ecbf7e5109e4cc8b6488cce38c3952115a5b2d4a919de580ced79ef9b6b1
|
| 3 |
+
size 3882376264
|
model-00016-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f9ca56f7df5bba906bde4eb3add3c598b979c2a72afd1264004f23884837079
|
| 3 |
+
size 3912236544
|
model-00017-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67aeca45eef8e785aaec9485e7fb92d8d947546b9b6519bde41d1bb1a9631109
|
| 3 |
+
size 3882376264
|
model-00018-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62879250521d991ac5df5c44e9facfd3d5b77c7f4de521513be6ae8cd00778ce
|
| 3 |
+
size 2679754344
|
model-00019-of-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4e7c7e6d59012ab070e69ec0bec078c8e02f7155f989d0281d37179d196d41f
|
| 3 |
+
size 1677721728
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quant_log.csv
ADDED
|
@@ -0,0 +1,666 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.0000000002,0.05000,1.487
|
| 3 |
+
0,self_attn.v_proj,0.0000000000,0.05000,1.316
|
| 4 |
+
0,self_attn.q_proj,0.0000000002,0.05000,1.331
|
| 5 |
+
0,self_attn.o_proj,0.0000000000,0.05000,1.339
|
| 6 |
+
0,mlp.gate_proj,0.0000000007,0.05000,1.370
|
| 7 |
+
0,mlp.up_proj,0.0000000002,0.05000,1.360
|
| 8 |
+
0,mlp.down_proj,0.0000000001,0.05000,4.459
|
| 9 |
+
1,self_attn.k_proj,0.0000000002,0.05000,1.372
|
| 10 |
+
1,self_attn.v_proj,0.0000000000,0.05000,1.356
|
| 11 |
+
1,self_attn.q_proj,0.0000000004,0.05000,1.365
|
| 12 |
+
1,self_attn.o_proj,0.0000000000,0.05000,1.377
|
| 13 |
+
1,mlp.gate_proj,0.0000000003,0.05000,1.415
|
| 14 |
+
1,mlp.up_proj,0.0000000003,0.05000,1.396
|
| 15 |
+
1,mlp.down_proj,0.0000000002,0.05000,4.535
|
| 16 |
+
2,self_attn.k_proj,0.0000000002,0.05000,1.352
|
| 17 |
+
2,self_attn.v_proj,0.0000000000,0.05000,1.336
|
| 18 |
+
2,self_attn.q_proj,0.0000000004,0.05000,1.348
|
| 19 |
+
2,self_attn.o_proj,0.0000000000,0.05000,1.372
|
| 20 |
+
2,mlp.gate_proj,0.0000000010,0.05000,1.399
|
| 21 |
+
2,mlp.up_proj,0.0000000010,0.05000,1.382
|
| 22 |
+
2,mlp.down_proj,0.0000000414,0.05000,4.496
|
| 23 |
+
3,self_attn.k_proj,0.0000000006,0.05000,1.363
|
| 24 |
+
3,self_attn.v_proj,0.0000000001,0.05000,1.351
|
| 25 |
+
3,self_attn.q_proj,0.0000000017,0.05000,1.364
|
| 26 |
+
3,self_attn.o_proj,0.0000000001,0.05000,1.373
|
| 27 |
+
3,mlp.gate_proj,0.0000000021,0.05000,1.417
|
| 28 |
+
3,mlp.up_proj,0.0000000020,0.05000,1.406
|
| 29 |
+
3,mlp.down_proj,0.0000000022,0.05000,4.515
|
| 30 |
+
4,self_attn.k_proj,0.0000000009,0.05000,1.351
|
| 31 |
+
4,self_attn.v_proj,0.0000000003,0.05000,1.340
|
| 32 |
+
4,self_attn.q_proj,0.0000000026,0.05000,1.353
|
| 33 |
+
4,self_attn.o_proj,0.0000000003,0.05000,1.373
|
| 34 |
+
4,mlp.gate_proj,0.0000000032,0.05000,1.412
|
| 35 |
+
4,mlp.up_proj,0.0000000030,0.05000,1.390
|
| 36 |
+
4,mlp.down_proj,0.0000000009,0.05000,4.518
|
| 37 |
+
5,self_attn.k_proj,0.0000000010,0.05000,1.341
|
| 38 |
+
5,self_attn.v_proj,0.0000000003,0.05000,1.327
|
| 39 |
+
5,self_attn.q_proj,0.0000000036,0.05000,1.347
|
| 40 |
+
5,self_attn.o_proj,0.0000000004,0.05000,1.361
|
| 41 |
+
5,mlp.gate_proj,0.0000000039,0.05000,1.399
|
| 42 |
+
5,mlp.up_proj,0.0000000037,0.05000,1.384
|
| 43 |
+
5,mlp.down_proj,0.0000000011,0.05000,4.519
|
| 44 |
+
6,self_attn.k_proj,0.0000000015,0.05000,1.351
|
| 45 |
+
6,self_attn.v_proj,0.0000000005,0.05000,1.333
|
| 46 |
+
6,self_attn.q_proj,0.0000000059,0.05000,1.346
|
| 47 |
+
6,self_attn.o_proj,0.0000000005,0.05000,1.366
|
| 48 |
+
6,mlp.gate_proj,0.0000000061,0.05000,1.411
|
| 49 |
+
6,mlp.up_proj,0.0000000056,0.05000,1.391
|
| 50 |
+
6,mlp.down_proj,0.0000000018,0.05000,4.525
|
| 51 |
+
7,self_attn.k_proj,0.0000000010,0.05000,1.346
|
| 52 |
+
7,self_attn.v_proj,0.0000000004,0.05000,1.334
|
| 53 |
+
7,self_attn.q_proj,0.0000000033,0.05000,1.353
|
| 54 |
+
7,self_attn.o_proj,0.0000000005,0.05000,1.365
|
| 55 |
+
7,mlp.gate_proj,0.0000000074,0.05000,1.403
|
| 56 |
+
7,mlp.up_proj,0.0000000068,0.05000,1.390
|
| 57 |
+
7,mlp.down_proj,0.0000000023,0.05000,4.516
|
| 58 |
+
8,self_attn.k_proj,0.0000000021,0.05000,1.350
|
| 59 |
+
8,self_attn.v_proj,0.0000000007,0.05000,1.340
|
| 60 |
+
8,self_attn.q_proj,0.0000000080,0.05000,1.349
|
| 61 |
+
8,self_attn.o_proj,0.0000000008,0.05000,1.367
|
| 62 |
+
8,mlp.gate_proj,0.0000000090,0.05000,1.401
|
| 63 |
+
8,mlp.up_proj,0.0000000083,0.05000,1.389
|
| 64 |
+
8,mlp.down_proj,0.0000000029,0.05000,4.502
|
| 65 |
+
9,self_attn.k_proj,0.0000000018,0.05000,1.349
|
| 66 |
+
9,self_attn.v_proj,0.0000000006,0.05000,1.334
|
| 67 |
+
9,self_attn.q_proj,0.0000000066,0.05000,1.349
|
| 68 |
+
9,self_attn.o_proj,0.0000000011,0.05000,1.361
|
| 69 |
+
9,mlp.gate_proj,0.0000000100,0.05000,1.398
|
| 70 |
+
9,mlp.up_proj,0.0000000090,0.05000,1.384
|
| 71 |
+
9,mlp.down_proj,0.0000000037,0.05000,4.501
|
| 72 |
+
10,self_attn.k_proj,0.0000000024,0.05000,1.343
|
| 73 |
+
10,self_attn.v_proj,0.0000000009,0.05000,1.331
|
| 74 |
+
10,self_attn.q_proj,0.0000000096,0.05000,1.349
|
| 75 |
+
10,self_attn.o_proj,0.0000000012,0.05000,1.364
|
| 76 |
+
10,mlp.gate_proj,0.0000000119,0.05000,1.397
|
| 77 |
+
10,mlp.up_proj,0.0000000109,0.05000,1.382
|
| 78 |
+
10,mlp.down_proj,0.0000000047,0.05000,4.524
|
| 79 |
+
11,self_attn.k_proj,0.0000000029,0.05000,1.344
|
| 80 |
+
11,self_attn.v_proj,0.0000000010,0.05000,1.331
|
| 81 |
+
11,self_attn.q_proj,0.0000000119,0.05000,1.344
|
| 82 |
+
11,self_attn.o_proj,0.0000000019,0.05000,1.359
|
| 83 |
+
11,mlp.gate_proj,0.0000000138,0.05000,1.394
|
| 84 |
+
11,mlp.up_proj,0.0000000129,0.05000,1.380
|
| 85 |
+
11,mlp.down_proj,0.0000000663,0.05000,4.508
|
| 86 |
+
12,self_attn.k_proj,0.0000000027,0.05000,1.351
|
| 87 |
+
12,self_attn.v_proj,0.0000000012,0.05000,1.340
|
| 88 |
+
12,self_attn.q_proj,0.0000000112,0.05000,1.350
|
| 89 |
+
12,self_attn.o_proj,0.0000000019,0.05000,1.369
|
| 90 |
+
12,mlp.gate_proj,0.0000000164,0.05000,1.403
|
| 91 |
+
12,mlp.up_proj,0.0000000153,0.05000,1.390
|
| 92 |
+
12,mlp.down_proj,0.0000000074,0.05000,4.548
|
| 93 |
+
13,self_attn.k_proj,0.0000000027,0.05000,1.352
|
| 94 |
+
13,self_attn.v_proj,0.0000000012,0.05000,1.341
|
| 95 |
+
13,self_attn.q_proj,0.0000000106,0.05000,1.348
|
| 96 |
+
13,self_attn.o_proj,0.0000000028,0.05000,1.364
|
| 97 |
+
13,mlp.gate_proj,0.0000000193,0.05000,1.397
|
| 98 |
+
13,mlp.up_proj,0.0000000180,0.05000,1.384
|
| 99 |
+
13,mlp.down_proj,0.0000000088,0.05000,4.492
|
| 100 |
+
14,self_attn.k_proj,0.0000000029,0.05000,1.344
|
| 101 |
+
14,self_attn.v_proj,0.0000000014,0.05000,1.332
|
| 102 |
+
14,self_attn.q_proj,0.0000000107,0.05000,1.336
|
| 103 |
+
14,self_attn.o_proj,0.0000000032,0.05000,1.361
|
| 104 |
+
14,mlp.gate_proj,0.0000000219,0.05000,1.405
|
| 105 |
+
14,mlp.up_proj,0.0000000203,0.05000,1.394
|
| 106 |
+
14,mlp.down_proj,0.0000000102,0.05000,4.510
|
| 107 |
+
15,self_attn.k_proj,0.0000000034,0.05000,1.349
|
| 108 |
+
15,self_attn.v_proj,0.0000000016,0.05000,1.335
|
| 109 |
+
15,self_attn.q_proj,0.0000000131,0.05000,1.349
|
| 110 |
+
15,self_attn.o_proj,0.0000000026,0.05000,1.362
|
| 111 |
+
15,mlp.gate_proj,0.0000000257,0.05000,1.403
|
| 112 |
+
15,mlp.up_proj,0.0000000235,0.05000,1.383
|
| 113 |
+
15,mlp.down_proj,0.0000000114,0.05000,4.479
|
| 114 |
+
16,self_attn.k_proj,0.0000000035,0.05000,1.343
|
| 115 |
+
16,self_attn.v_proj,0.0000000017,0.05000,1.325
|
| 116 |
+
16,self_attn.q_proj,0.0000000142,0.05000,1.348
|
| 117 |
+
16,self_attn.o_proj,0.0000000032,0.05000,1.364
|
| 118 |
+
16,mlp.gate_proj,0.0000000293,0.05000,1.402
|
| 119 |
+
16,mlp.up_proj,0.0000000264,0.05000,1.392
|
| 120 |
+
16,mlp.down_proj,0.0000000123,0.05000,4.503
|
| 121 |
+
17,self_attn.k_proj,0.0000000038,0.05000,1.359
|
| 122 |
+
17,self_attn.v_proj,0.0000000019,0.05000,1.342
|
| 123 |
+
17,self_attn.q_proj,0.0000000146,0.05000,1.351
|
| 124 |
+
17,self_attn.o_proj,0.0000000030,0.05000,1.364
|
| 125 |
+
17,mlp.gate_proj,0.0000000319,0.05000,1.400
|
| 126 |
+
17,mlp.up_proj,0.0000000289,0.05000,1.383
|
| 127 |
+
17,mlp.down_proj,0.0000000126,0.05000,4.507
|
| 128 |
+
18,self_attn.k_proj,0.0000000034,0.05000,1.350
|
| 129 |
+
18,self_attn.v_proj,0.0000000021,0.05000,1.339
|
| 130 |
+
18,self_attn.q_proj,0.0000000136,0.05000,1.351
|
| 131 |
+
18,self_attn.o_proj,0.0000000034,0.05000,1.372
|
| 132 |
+
18,mlp.gate_proj,0.0000000330,0.05000,1.402
|
| 133 |
+
18,mlp.up_proj,0.0000000301,0.05000,1.387
|
| 134 |
+
18,mlp.down_proj,0.0000000137,0.05000,4.544
|
| 135 |
+
19,self_attn.k_proj,0.0000000035,0.05000,1.351
|
| 136 |
+
19,self_attn.v_proj,0.0000000018,0.05000,1.337
|
| 137 |
+
19,self_attn.q_proj,0.0000000122,0.05000,1.352
|
| 138 |
+
19,self_attn.o_proj,0.0000000030,0.05000,1.361
|
| 139 |
+
19,mlp.gate_proj,0.0000000352,0.05000,1.395
|
| 140 |
+
19,mlp.up_proj,0.0000000317,0.05000,1.383
|
| 141 |
+
19,mlp.down_proj,0.0000000153,0.05000,4.485
|
| 142 |
+
20,self_attn.k_proj,0.0000000046,0.05000,1.349
|
| 143 |
+
20,self_attn.v_proj,0.0000000025,0.05000,1.333
|
| 144 |
+
20,self_attn.q_proj,0.0000000171,0.05000,1.350
|
| 145 |
+
20,self_attn.o_proj,0.0000000032,0.05000,1.361
|
| 146 |
+
20,mlp.gate_proj,0.0000000386,0.05000,1.394
|
| 147 |
+
20,mlp.up_proj,0.0000000345,0.05000,1.382
|
| 148 |
+
20,mlp.down_proj,0.0000000162,0.05000,4.496
|
| 149 |
+
21,self_attn.k_proj,0.0000000032,0.05000,1.355
|
| 150 |
+
21,self_attn.v_proj,0.0000000019,0.05000,1.339
|
| 151 |
+
21,self_attn.q_proj,0.0000000107,0.05000,1.352
|
| 152 |
+
21,self_attn.o_proj,0.0000000031,0.05000,1.369
|
| 153 |
+
21,mlp.gate_proj,0.0000000395,0.05000,1.408
|
| 154 |
+
21,mlp.up_proj,0.0000000353,0.05000,1.393
|
| 155 |
+
21,mlp.down_proj,0.0000000173,0.05000,4.499
|
| 156 |
+
22,self_attn.k_proj,0.0000000043,0.05000,1.348
|
| 157 |
+
22,self_attn.v_proj,0.0000000025,0.05000,1.337
|
| 158 |
+
22,self_attn.q_proj,0.0000000142,0.05000,1.345
|
| 159 |
+
22,self_attn.o_proj,0.0000000037,0.05000,1.360
|
| 160 |
+
22,mlp.gate_proj,0.0000000419,0.05000,1.400
|
| 161 |
+
22,mlp.up_proj,0.0000000373,0.05000,1.386
|
| 162 |
+
22,mlp.down_proj,0.0000000178,0.05000,4.501
|
| 163 |
+
23,self_attn.k_proj,0.0000000037,0.05000,1.350
|
| 164 |
+
23,self_attn.v_proj,0.0000000027,0.05000,1.341
|
| 165 |
+
23,self_attn.q_proj,0.0000000133,0.05000,1.346
|
| 166 |
+
23,self_attn.o_proj,0.0000000022,0.05000,1.365
|
| 167 |
+
23,mlp.gate_proj,0.0000000436,0.05000,1.403
|
| 168 |
+
23,mlp.up_proj,0.0000000390,0.05000,1.386
|
| 169 |
+
23,mlp.down_proj,0.0000000180,0.05000,4.532
|
| 170 |
+
24,self_attn.k_proj,0.0000000041,0.05000,1.349
|
| 171 |
+
24,self_attn.v_proj,0.0000000027,0.05000,1.342
|
| 172 |
+
24,self_attn.q_proj,0.0000000143,0.05000,1.350
|
| 173 |
+
24,self_attn.o_proj,0.0000000032,0.05000,1.364
|
| 174 |
+
24,mlp.gate_proj,0.0000000445,0.05000,1.396
|
| 175 |
+
24,mlp.up_proj,0.0000000400,0.05000,1.385
|
| 176 |
+
24,mlp.down_proj,0.0000000182,0.05000,4.504
|
| 177 |
+
25,self_attn.k_proj,0.0000000035,0.05000,1.351
|
| 178 |
+
25,self_attn.v_proj,0.0000000027,0.05000,1.336
|
| 179 |
+
25,self_attn.q_proj,0.0000000128,0.05000,1.344
|
| 180 |
+
25,self_attn.o_proj,0.0000000028,0.05000,1.360
|
| 181 |
+
25,mlp.gate_proj,0.0000000453,0.05000,1.400
|
| 182 |
+
25,mlp.up_proj,0.0000000412,0.05000,1.388
|
| 183 |
+
25,mlp.down_proj,0.0000000180,0.05000,4.499
|
| 184 |
+
26,self_attn.k_proj,0.0000000027,0.05000,1.348
|
| 185 |
+
26,self_attn.v_proj,0.0000000022,0.05000,1.339
|
| 186 |
+
26,self_attn.q_proj,0.0000000091,0.05000,1.352
|
| 187 |
+
26,self_attn.o_proj,0.0000000020,0.05000,1.366
|
| 188 |
+
26,mlp.gate_proj,0.0000000470,0.05000,1.394
|
| 189 |
+
26,mlp.up_proj,0.0000000429,0.05000,1.381
|
| 190 |
+
26,mlp.down_proj,0.0000000181,0.05000,4.487
|
| 191 |
+
27,self_attn.k_proj,0.0000000040,0.05000,1.355
|
| 192 |
+
27,self_attn.v_proj,0.0000000027,0.05000,1.340
|
| 193 |
+
27,self_attn.q_proj,0.0000000128,0.05000,1.357
|
| 194 |
+
27,self_attn.o_proj,0.0000000028,0.05000,1.369
|
| 195 |
+
27,mlp.gate_proj,0.0000000481,0.05000,1.406
|
| 196 |
+
27,mlp.up_proj,0.0000000443,0.05000,1.397
|
| 197 |
+
27,mlp.down_proj,0.0000000185,0.05000,4.499
|
| 198 |
+
28,self_attn.k_proj,0.0000000032,0.05000,1.351
|
| 199 |
+
28,self_attn.v_proj,0.0000000020,0.05000,1.338
|
| 200 |
+
28,self_attn.q_proj,0.0000000106,0.05000,1.355
|
| 201 |
+
28,self_attn.o_proj,0.0000000031,0.05000,1.364
|
| 202 |
+
28,mlp.gate_proj,0.0000000477,0.05000,1.398
|
| 203 |
+
28,mlp.up_proj,0.0000000448,0.05000,1.387
|
| 204 |
+
28,mlp.down_proj,0.0000000185,0.05000,4.518
|
| 205 |
+
29,self_attn.k_proj,0.0000000054,0.05000,1.346
|
| 206 |
+
29,self_attn.v_proj,0.0000000026,0.05000,1.333
|
| 207 |
+
29,self_attn.q_proj,0.0000000197,0.05000,1.356
|
| 208 |
+
29,self_attn.o_proj,0.0000000056,0.05000,1.365
|
| 209 |
+
29,mlp.gate_proj,0.0000000487,0.05000,1.399
|
| 210 |
+
29,mlp.up_proj,0.0000000462,0.05000,1.384
|
| 211 |
+
29,mlp.down_proj,0.0000000201,0.05000,4.501
|
| 212 |
+
30,self_attn.k_proj,0.0000000041,0.05000,1.359
|
| 213 |
+
30,self_attn.v_proj,0.0000000029,0.05000,1.342
|
| 214 |
+
30,self_attn.q_proj,0.0000000157,0.05000,1.358
|
| 215 |
+
30,self_attn.o_proj,0.0000000041,0.05000,1.360
|
| 216 |
+
30,mlp.gate_proj,0.0000000488,0.05000,1.401
|
| 217 |
+
30,mlp.up_proj,0.0000000469,0.05000,1.382
|
| 218 |
+
30,mlp.down_proj,0.0000000215,0.05000,4.481
|
| 219 |
+
31,self_attn.k_proj,0.0000000053,0.05000,1.351
|
| 220 |
+
31,self_attn.v_proj,0.0000000029,0.05000,1.331
|
| 221 |
+
31,self_attn.q_proj,0.0000000194,0.05000,1.355
|
| 222 |
+
31,self_attn.o_proj,0.0000000055,0.05000,1.370
|
| 223 |
+
31,mlp.gate_proj,0.0000000478,0.05000,1.401
|
| 224 |
+
31,mlp.up_proj,0.0000000469,0.05000,1.390
|
| 225 |
+
31,mlp.down_proj,0.0000000240,0.05000,4.493
|
| 226 |
+
32,self_attn.k_proj,0.0000000049,0.05000,1.346
|
| 227 |
+
32,self_attn.v_proj,0.0000000027,0.05000,1.337
|
| 228 |
+
32,self_attn.q_proj,0.0000000189,0.05000,1.358
|
| 229 |
+
32,self_attn.o_proj,0.0000000068,0.05000,1.363
|
| 230 |
+
32,mlp.gate_proj,0.0000000460,0.05000,1.397
|
| 231 |
+
32,mlp.up_proj,0.0000000459,0.05000,1.384
|
| 232 |
+
32,mlp.down_proj,0.0000000247,0.05000,4.497
|
| 233 |
+
33,self_attn.k_proj,0.0000000060,0.05000,1.356
|
| 234 |
+
33,self_attn.v_proj,0.0000000030,0.05000,1.340
|
| 235 |
+
33,self_attn.q_proj,0.0000000258,0.05000,1.359
|
| 236 |
+
33,self_attn.o_proj,0.0000000100,0.05000,1.365
|
| 237 |
+
33,mlp.gate_proj,0.0000000455,0.05000,1.399
|
| 238 |
+
33,mlp.up_proj,0.0000000461,0.05000,1.388
|
| 239 |
+
33,mlp.down_proj,0.0000000266,0.05000,4.497
|
| 240 |
+
34,self_attn.k_proj,0.0000000060,0.05000,1.345
|
| 241 |
+
34,self_attn.v_proj,0.0000000030,0.05000,1.332
|
| 242 |
+
34,self_attn.q_proj,0.0000000254,0.05000,1.357
|
| 243 |
+
34,self_attn.o_proj,0.0000000115,0.05000,1.364
|
| 244 |
+
34,mlp.gate_proj,0.0000000454,0.05000,1.392
|
| 245 |
+
34,mlp.up_proj,0.0000000467,0.05000,1.377
|
| 246 |
+
34,mlp.down_proj,0.0000000284,0.05000,4.500
|
| 247 |
+
35,self_attn.k_proj,0.0000000056,0.05000,1.349
|
| 248 |
+
35,self_attn.v_proj,0.0000000035,0.05000,1.336
|
| 249 |
+
35,self_attn.q_proj,0.0000000236,0.05000,1.354
|
| 250 |
+
35,self_attn.o_proj,0.0000000134,0.05000,1.364
|
| 251 |
+
35,mlp.gate_proj,0.0000000470,0.05000,1.400
|
| 252 |
+
35,mlp.up_proj,0.0000000485,0.05000,1.387
|
| 253 |
+
35,mlp.down_proj,0.0000000294,0.05000,4.503
|
| 254 |
+
36,self_attn.k_proj,0.0000000065,0.05000,1.341
|
| 255 |
+
36,self_attn.v_proj,0.0000000036,0.05000,1.331
|
| 256 |
+
36,self_attn.q_proj,0.0000000281,0.05000,1.352
|
| 257 |
+
36,self_attn.o_proj,0.0000000161,0.05000,1.366
|
| 258 |
+
36,mlp.gate_proj,0.0000000474,0.05000,1.389
|
| 259 |
+
36,mlp.up_proj,0.0000000491,0.05000,1.382
|
| 260 |
+
36,mlp.down_proj,0.0000000326,0.05000,4.487
|
| 261 |
+
37,self_attn.k_proj,0.0000000066,0.05000,1.344
|
| 262 |
+
37,self_attn.v_proj,0.0000000037,0.05000,1.335
|
| 263 |
+
37,self_attn.q_proj,0.0000000289,0.05000,1.360
|
| 264 |
+
37,self_attn.o_proj,0.0000000198,0.05000,1.369
|
| 265 |
+
37,mlp.gate_proj,0.0000000486,0.05000,1.403
|
| 266 |
+
37,mlp.up_proj,0.0000000508,0.05000,1.391
|
| 267 |
+
37,mlp.down_proj,0.0000000351,0.05000,4.493
|
| 268 |
+
38,self_attn.k_proj,0.0000000064,0.05000,1.347
|
| 269 |
+
38,self_attn.v_proj,0.0000000033,0.05000,1.336
|
| 270 |
+
38,self_attn.q_proj,0.0000000270,0.05000,1.356
|
| 271 |
+
38,self_attn.o_proj,0.0000000156,0.05000,1.370
|
| 272 |
+
38,mlp.gate_proj,0.0000000507,0.05000,1.398
|
| 273 |
+
38,mlp.up_proj,0.0000000531,0.05000,1.385
|
| 274 |
+
38,mlp.down_proj,0.0000000366,0.05000,4.498
|
| 275 |
+
39,self_attn.k_proj,0.0000000070,0.05000,1.354
|
| 276 |
+
39,self_attn.v_proj,0.0000000048,0.05000,1.340
|
| 277 |
+
39,self_attn.q_proj,0.0000000312,0.05000,1.361
|
| 278 |
+
39,self_attn.o_proj,0.0000000152,0.05000,1.376
|
| 279 |
+
39,mlp.gate_proj,0.0000000533,0.05000,1.403
|
| 280 |
+
39,mlp.up_proj,0.0000000560,0.05000,1.391
|
| 281 |
+
39,mlp.down_proj,0.0000000397,0.05000,4.521
|
| 282 |
+
40,self_attn.k_proj,0.0000000068,0.05000,1.348
|
| 283 |
+
40,self_attn.v_proj,0.0000000043,0.05000,1.336
|
| 284 |
+
40,self_attn.q_proj,0.0000000299,0.05000,1.354
|
| 285 |
+
40,self_attn.o_proj,0.0000000181,0.05000,1.363
|
| 286 |
+
40,mlp.gate_proj,0.0000000557,0.05000,1.399
|
| 287 |
+
40,mlp.up_proj,0.0000000582,0.05000,1.390
|
| 288 |
+
40,mlp.down_proj,0.0000000429,0.05000,4.502
|
| 289 |
+
41,self_attn.k_proj,0.0000000069,0.05000,1.353
|
| 290 |
+
41,self_attn.v_proj,0.0000000045,0.05000,1.332
|
| 291 |
+
41,self_attn.q_proj,0.0000000314,0.05000,1.350
|
| 292 |
+
41,self_attn.o_proj,0.0000000169,0.05000,1.364
|
| 293 |
+
41,mlp.gate_proj,0.0000000567,0.05000,1.395
|
| 294 |
+
41,mlp.up_proj,0.0000000594,0.05000,1.380
|
| 295 |
+
41,mlp.down_proj,0.0000000467,0.05000,4.494
|
| 296 |
+
42,self_attn.k_proj,0.0000000067,0.05000,1.349
|
| 297 |
+
42,self_attn.v_proj,0.0000000043,0.05000,1.338
|
| 298 |
+
42,self_attn.q_proj,0.0000000300,0.05000,1.356
|
| 299 |
+
42,self_attn.o_proj,0.0000000194,0.05000,1.366
|
| 300 |
+
42,mlp.gate_proj,0.0000000577,0.05000,1.399
|
| 301 |
+
42,mlp.up_proj,0.0000000604,0.05000,1.383
|
| 302 |
+
42,mlp.down_proj,0.0000000501,0.05000,4.504
|
| 303 |
+
43,self_attn.k_proj,0.0000000065,0.05000,1.353
|
| 304 |
+
43,self_attn.v_proj,0.0000000047,0.05000,1.336
|
| 305 |
+
43,self_attn.q_proj,0.0000000308,0.05000,1.360
|
| 306 |
+
43,self_attn.o_proj,0.0000000179,0.05000,1.371
|
| 307 |
+
43,mlp.gate_proj,0.0000000587,0.05000,1.405
|
| 308 |
+
43,mlp.up_proj,0.0000000615,0.05000,1.394
|
| 309 |
+
43,mlp.down_proj,0.0000000540,0.05000,4.509
|
| 310 |
+
44,self_attn.k_proj,0.0000000076,0.05000,1.350
|
| 311 |
+
44,self_attn.v_proj,0.0000000051,0.05000,1.337
|
| 312 |
+
44,self_attn.q_proj,0.0000000357,0.05000,1.356
|
| 313 |
+
44,self_attn.o_proj,0.0000000250,0.05000,1.374
|
| 314 |
+
44,mlp.gate_proj,0.0000000619,0.05000,1.406
|
| 315 |
+
44,mlp.up_proj,0.0000000648,0.05000,1.387
|
| 316 |
+
44,mlp.down_proj,0.0000000589,0.05000,4.498
|
| 317 |
+
45,self_attn.k_proj,0.0000000069,0.05000,1.354
|
| 318 |
+
45,self_attn.v_proj,0.0000000056,0.05000,1.341
|
| 319 |
+
45,self_attn.q_proj,0.0000000313,0.05000,1.354
|
| 320 |
+
45,self_attn.o_proj,0.0000000182,0.05000,1.372
|
| 321 |
+
45,mlp.gate_proj,0.0000000663,0.05000,1.402
|
| 322 |
+
45,mlp.up_proj,0.0000000690,0.05000,1.392
|
| 323 |
+
45,mlp.down_proj,0.0000000656,0.05000,4.512
|
| 324 |
+
46,self_attn.k_proj,0.0000000071,0.05000,1.354
|
| 325 |
+
46,self_attn.v_proj,0.0000000053,0.05000,1.339
|
| 326 |
+
46,self_attn.q_proj,0.0000000322,0.05000,1.351
|
| 327 |
+
46,self_attn.o_proj,0.0000000247,0.05000,1.366
|
| 328 |
+
46,mlp.gate_proj,0.0000000700,0.05000,1.403
|
| 329 |
+
46,mlp.up_proj,0.0000000722,0.05000,1.387
|
| 330 |
+
46,mlp.down_proj,0.0000000712,0.05000,4.514
|
| 331 |
+
47,self_attn.k_proj,0.0000000071,0.05000,1.353
|
| 332 |
+
47,self_attn.v_proj,0.0000000062,0.05000,1.338
|
| 333 |
+
47,self_attn.q_proj,0.0000000352,0.05000,1.357
|
| 334 |
+
47,self_attn.o_proj,0.0000000202,0.05000,1.376
|
| 335 |
+
47,mlp.gate_proj,0.0000000723,0.05000,1.405
|
| 336 |
+
47,mlp.up_proj,0.0000000745,0.05000,1.391
|
| 337 |
+
47,mlp.down_proj,0.0000000768,0.05000,4.497
|
| 338 |
+
48,self_attn.k_proj,0.0000000056,0.05000,1.352
|
| 339 |
+
48,self_attn.v_proj,0.0000000052,0.05000,1.339
|
| 340 |
+
48,self_attn.q_proj,0.0000000255,0.05000,1.360
|
| 341 |
+
48,self_attn.o_proj,0.0000000224,0.05000,1.372
|
| 342 |
+
48,mlp.gate_proj,0.0000000738,0.05000,1.408
|
| 343 |
+
48,mlp.up_proj,0.0000000757,0.05000,1.391
|
| 344 |
+
48,mlp.down_proj,0.0000000830,0.05000,4.489
|
| 345 |
+
49,self_attn.k_proj,0.0000000075,0.05000,1.346
|
| 346 |
+
49,self_attn.v_proj,0.0000000062,0.05000,1.334
|
| 347 |
+
49,self_attn.q_proj,0.0000000371,0.05000,1.356
|
| 348 |
+
49,self_attn.o_proj,0.0000000286,0.05000,1.375
|
| 349 |
+
49,mlp.gate_proj,0.0000000765,0.05000,1.405
|
| 350 |
+
49,mlp.up_proj,0.0000000783,0.05000,1.393
|
| 351 |
+
49,mlp.down_proj,0.0000000932,0.05000,4.500
|
| 352 |
+
50,self_attn.k_proj,0.0000000070,0.05000,1.355
|
| 353 |
+
50,self_attn.v_proj,0.0000000065,0.05000,1.340
|
| 354 |
+
50,self_attn.q_proj,0.0000000330,0.05000,1.354
|
| 355 |
+
50,self_attn.o_proj,0.0000000273,0.05000,1.373
|
| 356 |
+
50,mlp.gate_proj,0.0000000832,0.05000,1.398
|
| 357 |
+
50,mlp.up_proj,0.0000000840,0.05000,1.387
|
| 358 |
+
50,mlp.down_proj,0.0000001034,0.05000,4.527
|
| 359 |
+
51,self_attn.k_proj,0.0000000074,0.05000,1.358
|
| 360 |
+
51,self_attn.v_proj,0.0000000071,0.05000,1.344
|
| 361 |
+
51,self_attn.q_proj,0.0000000339,0.05000,1.366
|
| 362 |
+
51,self_attn.o_proj,0.0000000302,0.05000,1.376
|
| 363 |
+
51,mlp.gate_proj,0.0000000861,0.05000,1.409
|
| 364 |
+
51,mlp.up_proj,0.0000000864,0.05000,1.393
|
| 365 |
+
51,mlp.down_proj,0.0000001112,0.05000,4.509
|
| 366 |
+
52,self_attn.k_proj,0.0000000063,0.05000,1.348
|
| 367 |
+
52,self_attn.v_proj,0.0000000054,0.05000,1.336
|
| 368 |
+
52,self_attn.q_proj,0.0000000278,0.05000,1.354
|
| 369 |
+
52,self_attn.o_proj,0.0000000400,0.05000,1.370
|
| 370 |
+
52,mlp.gate_proj,0.0000000918,0.05000,1.404
|
| 371 |
+
52,mlp.up_proj,0.0000000911,0.05000,1.392
|
| 372 |
+
52,mlp.down_proj,0.0000001244,0.05000,4.512
|
| 373 |
+
53,self_attn.k_proj,0.0000000073,0.05000,1.353
|
| 374 |
+
53,self_attn.v_proj,0.0000000066,0.05000,1.336
|
| 375 |
+
53,self_attn.q_proj,0.0000000352,0.05000,1.354
|
| 376 |
+
53,self_attn.o_proj,0.0000000331,0.05000,1.370
|
| 377 |
+
53,mlp.gate_proj,0.0000000984,0.05000,1.399
|
| 378 |
+
53,mlp.up_proj,0.0000000970,0.05000,1.386
|
| 379 |
+
53,mlp.down_proj,0.0000001370,0.05000,4.511
|
| 380 |
+
54,self_attn.k_proj,0.0000000067,0.05000,1.343
|
| 381 |
+
54,self_attn.v_proj,0.0000000075,0.05000,1.331
|
| 382 |
+
54,self_attn.q_proj,0.0000000306,0.05000,1.359
|
| 383 |
+
54,self_attn.o_proj,0.0000000324,0.05000,1.367
|
| 384 |
+
54,mlp.gate_proj,0.0000001049,0.05000,1.397
|
| 385 |
+
54,mlp.up_proj,0.0000001019,0.05000,1.384
|
| 386 |
+
54,mlp.down_proj,0.0000001481,0.05000,4.507
|
| 387 |
+
55,self_attn.k_proj,0.0000000073,0.05000,1.350
|
| 388 |
+
55,self_attn.v_proj,0.0000000077,0.05000,1.337
|
| 389 |
+
55,self_attn.q_proj,0.0000000342,0.05000,1.356
|
| 390 |
+
55,self_attn.o_proj,0.0000000322,0.05000,1.369
|
| 391 |
+
55,mlp.gate_proj,0.0000001114,0.05000,1.402
|
| 392 |
+
55,mlp.up_proj,0.0000001073,0.05000,1.391
|
| 393 |
+
55,mlp.down_proj,0.0000001589,0.05000,4.507
|
| 394 |
+
56,self_attn.k_proj,0.0000000066,0.05000,1.348
|
| 395 |
+
56,self_attn.v_proj,0.0000000074,0.05000,1.333
|
| 396 |
+
56,self_attn.q_proj,0.0000000302,0.05000,1.355
|
| 397 |
+
56,self_attn.o_proj,0.0000000195,0.05000,1.367
|
| 398 |
+
56,mlp.gate_proj,0.0000001161,0.05000,1.398
|
| 399 |
+
56,mlp.up_proj,0.0000001107,0.05000,1.388
|
| 400 |
+
56,mlp.down_proj,0.0000001599,0.05000,4.496
|
| 401 |
+
57,self_attn.k_proj,0.0000000079,0.05000,1.349
|
| 402 |
+
57,self_attn.v_proj,0.0000000083,0.05000,1.336
|
| 403 |
+
57,self_attn.q_proj,0.0000000399,0.05000,1.355
|
| 404 |
+
57,self_attn.o_proj,0.0000000423,0.05000,1.367
|
| 405 |
+
57,mlp.gate_proj,0.0000001222,0.05000,1.404
|
| 406 |
+
57,mlp.up_proj,0.0000001159,0.05000,1.389
|
| 407 |
+
57,mlp.down_proj,0.0000001722,0.05000,4.499
|
| 408 |
+
58,self_attn.k_proj,0.0000000076,0.05000,1.349
|
| 409 |
+
58,self_attn.v_proj,0.0000000090,0.05000,1.338
|
| 410 |
+
58,self_attn.q_proj,0.0000000390,0.05000,1.353
|
| 411 |
+
58,self_attn.o_proj,0.0000000216,0.05000,1.370
|
| 412 |
+
58,mlp.gate_proj,0.0000001274,0.05000,1.405
|
| 413 |
+
58,mlp.up_proj,0.0000001205,0.05000,1.392
|
| 414 |
+
58,mlp.down_proj,0.0000001786,0.05000,4.503
|
| 415 |
+
59,self_attn.k_proj,0.0000000078,0.05000,1.356
|
| 416 |
+
59,self_attn.v_proj,0.0000000097,0.05000,1.345
|
| 417 |
+
59,self_attn.q_proj,0.0000000377,0.05000,1.359
|
| 418 |
+
59,self_attn.o_proj,0.0000000335,0.05000,1.377
|
| 419 |
+
59,mlp.gate_proj,0.0000001335,0.05000,1.404
|
| 420 |
+
59,mlp.up_proj,0.0000001255,0.05000,1.390
|
| 421 |
+
59,mlp.down_proj,0.0000001906,0.05000,4.523
|
| 422 |
+
60,self_attn.k_proj,0.0000000075,0.05000,1.351
|
| 423 |
+
60,self_attn.v_proj,0.0000000090,0.05000,1.336
|
| 424 |
+
60,self_attn.q_proj,0.0000000360,0.05000,1.351
|
| 425 |
+
60,self_attn.o_proj,0.0000000316,0.05000,1.371
|
| 426 |
+
60,mlp.gate_proj,0.0000001386,0.05000,1.398
|
| 427 |
+
60,mlp.up_proj,0.0000001294,0.05000,1.383
|
| 428 |
+
60,mlp.down_proj,0.0000002003,0.05000,4.489
|
| 429 |
+
61,self_attn.k_proj,0.0000000076,0.05000,1.348
|
| 430 |
+
61,self_attn.v_proj,0.0000000088,0.05000,1.340
|
| 431 |
+
61,self_attn.q_proj,0.0000000352,0.05000,1.354
|
| 432 |
+
61,self_attn.o_proj,0.0000000220,0.05000,1.369
|
| 433 |
+
61,mlp.gate_proj,0.0000001432,0.05000,1.408
|
| 434 |
+
61,mlp.up_proj,0.0000001329,0.05000,1.389
|
| 435 |
+
61,mlp.down_proj,0.0000002049,0.05000,4.506
|
| 436 |
+
62,self_attn.k_proj,0.0000000079,0.05000,1.354
|
| 437 |
+
62,self_attn.v_proj,0.0000000102,0.05000,1.337
|
| 438 |
+
62,self_attn.q_proj,0.0000000381,0.05000,1.360
|
| 439 |
+
62,self_attn.o_proj,0.0000000246,0.05000,1.370
|
| 440 |
+
62,mlp.gate_proj,0.0000001485,0.05000,1.407
|
| 441 |
+
62,mlp.up_proj,0.0000001374,0.05000,1.391
|
| 442 |
+
62,mlp.down_proj,0.0000002145,0.05000,4.514
|
| 443 |
+
63,self_attn.k_proj,0.0000000080,0.05000,1.349
|
| 444 |
+
63,self_attn.v_proj,0.0000000100,0.05000,1.337
|
| 445 |
+
63,self_attn.q_proj,0.0000000372,0.05000,1.354
|
| 446 |
+
63,self_attn.o_proj,0.0000000186,0.05000,1.371
|
| 447 |
+
63,mlp.gate_proj,0.0000001515,0.05000,1.399
|
| 448 |
+
63,mlp.up_proj,0.0000001404,0.05000,1.387
|
| 449 |
+
63,mlp.down_proj,0.0000002196,0.05000,4.497
|
| 450 |
+
64,self_attn.k_proj,0.0000000080,0.05000,1.352
|
| 451 |
+
64,self_attn.v_proj,0.0000000107,0.05000,1.346
|
| 452 |
+
64,self_attn.q_proj,0.0000000390,0.05000,1.361
|
| 453 |
+
64,self_attn.o_proj,0.0000000267,0.05000,1.372
|
| 454 |
+
64,mlp.gate_proj,0.0000001574,0.05000,1.408
|
| 455 |
+
64,mlp.up_proj,0.0000001457,0.05000,1.387
|
| 456 |
+
64,mlp.down_proj,0.0000002252,0.05000,4.513
|
| 457 |
+
65,self_attn.k_proj,0.0000000078,0.05000,1.352
|
| 458 |
+
65,self_attn.v_proj,0.0000000113,0.05000,1.337
|
| 459 |
+
65,self_attn.q_proj,0.0000000374,0.05000,1.363
|
| 460 |
+
65,self_attn.o_proj,0.0000000382,0.05000,1.372
|
| 461 |
+
65,mlp.gate_proj,0.0000001605,0.05000,1.403
|
| 462 |
+
65,mlp.up_proj,0.0000001483,0.05000,1.393
|
| 463 |
+
65,mlp.down_proj,0.0000002409,0.05000,4.499
|
| 464 |
+
66,self_attn.k_proj,0.0000000082,0.05000,1.351
|
| 465 |
+
66,self_attn.v_proj,0.0000000104,0.05000,1.336
|
| 466 |
+
66,self_attn.q_proj,0.0000000401,0.05000,1.358
|
| 467 |
+
66,self_attn.o_proj,0.0000000350,0.05000,1.363
|
| 468 |
+
66,mlp.gate_proj,0.0000001648,0.05000,1.405
|
| 469 |
+
66,mlp.up_proj,0.0000001520,0.05000,1.390
|
| 470 |
+
66,mlp.down_proj,0.0000002435,0.05000,4.482
|
| 471 |
+
67,self_attn.k_proj,0.0000000077,0.05000,1.348
|
| 472 |
+
67,self_attn.v_proj,0.0000000106,0.05000,1.338
|
| 473 |
+
67,self_attn.q_proj,0.0000000369,0.05000,1.354
|
| 474 |
+
67,self_attn.o_proj,0.0000000381,0.05000,1.374
|
| 475 |
+
67,mlp.gate_proj,0.0000001704,0.05000,1.407
|
| 476 |
+
67,mlp.up_proj,0.0000001572,0.05000,1.393
|
| 477 |
+
67,mlp.down_proj,0.0000002554,0.05000,4.498
|
| 478 |
+
68,self_attn.k_proj,0.0000000078,0.05000,1.353
|
| 479 |
+
68,self_attn.v_proj,0.0000000114,0.05000,1.344
|
| 480 |
+
68,self_attn.q_proj,0.0000000379,0.05000,1.355
|
| 481 |
+
68,self_attn.o_proj,0.0000000318,0.05000,1.379
|
| 482 |
+
68,mlp.gate_proj,0.0000001744,0.05000,1.408
|
| 483 |
+
68,mlp.up_proj,0.0000001610,0.05000,1.394
|
| 484 |
+
68,mlp.down_proj,0.0000002689,0.05000,4.507
|
| 485 |
+
69,self_attn.k_proj,0.0000000080,0.05000,1.356
|
| 486 |
+
69,self_attn.v_proj,0.0000000103,0.05000,1.341
|
| 487 |
+
69,self_attn.q_proj,0.0000000354,0.05000,1.363
|
| 488 |
+
69,self_attn.o_proj,0.0000000330,0.05000,1.369
|
| 489 |
+
69,mlp.gate_proj,0.0000001782,0.05000,1.410
|
| 490 |
+
69,mlp.up_proj,0.0000001645,0.05000,1.399
|
| 491 |
+
69,mlp.down_proj,0.0000002735,0.05000,4.510
|
| 492 |
+
70,self_attn.k_proj,0.0000000088,0.05000,1.353
|
| 493 |
+
70,self_attn.v_proj,0.0000000123,0.05000,1.341
|
| 494 |
+
70,self_attn.q_proj,0.0000000445,0.05000,1.366
|
| 495 |
+
70,self_attn.o_proj,0.0000000549,0.05000,1.371
|
| 496 |
+
70,mlp.gate_proj,0.0000001840,0.05000,1.406
|
| 497 |
+
70,mlp.up_proj,0.0000001699,0.05000,1.394
|
| 498 |
+
70,mlp.down_proj,0.0000002902,0.05000,4.515
|
| 499 |
+
71,self_attn.k_proj,0.0000000080,0.05000,1.354
|
| 500 |
+
71,self_attn.v_proj,0.0000000115,0.05000,1.341
|
| 501 |
+
71,self_attn.q_proj,0.0000000381,0.05000,1.359
|
| 502 |
+
71,self_attn.o_proj,0.0000000341,0.05000,1.382
|
| 503 |
+
71,mlp.gate_proj,0.0000001862,0.05000,1.406
|
| 504 |
+
71,mlp.up_proj,0.0000001725,0.05000,1.395
|
| 505 |
+
71,mlp.down_proj,0.0000003089,0.05000,4.507
|
| 506 |
+
72,self_attn.k_proj,0.0000000088,0.05000,1.355
|
| 507 |
+
72,self_attn.v_proj,0.0000000100,0.05000,1.340
|
| 508 |
+
72,self_attn.q_proj,0.0000000404,0.05000,1.358
|
| 509 |
+
72,self_attn.o_proj,0.0000000419,0.05000,1.376
|
| 510 |
+
72,mlp.gate_proj,0.0000001917,0.05000,1.406
|
| 511 |
+
72,mlp.up_proj,0.0000001779,0.05000,1.391
|
| 512 |
+
72,mlp.down_proj,0.0000003177,0.05000,4.510
|
| 513 |
+
73,self_attn.k_proj,0.0000000074,0.05000,1.359
|
| 514 |
+
73,self_attn.v_proj,0.0000000145,0.05000,1.345
|
| 515 |
+
73,self_attn.q_proj,0.0000000387,0.05000,1.365
|
| 516 |
+
73,self_attn.o_proj,0.0000000371,0.05000,1.373
|
| 517 |
+
73,mlp.gate_proj,0.0000001982,0.05000,1.404
|
| 518 |
+
73,mlp.up_proj,0.0000001843,0.05000,1.395
|
| 519 |
+
73,mlp.down_proj,0.0000003323,0.05000,4.527
|
| 520 |
+
74,self_attn.k_proj,0.0000000082,0.05000,1.359
|
| 521 |
+
74,self_attn.v_proj,0.0000000111,0.05000,1.339
|
| 522 |
+
74,self_attn.q_proj,0.0000000377,0.05000,1.354
|
| 523 |
+
74,self_attn.o_proj,0.0000000385,0.05000,1.379
|
| 524 |
+
74,mlp.gate_proj,0.0000002020,0.05000,1.408
|
| 525 |
+
74,mlp.up_proj,0.0000001885,0.05000,1.391
|
| 526 |
+
74,mlp.down_proj,0.0000003429,0.05000,4.521
|
| 527 |
+
75,self_attn.k_proj,0.0000000080,0.05000,1.349
|
| 528 |
+
75,self_attn.v_proj,0.0000000112,0.05000,1.337
|
| 529 |
+
75,self_attn.q_proj,0.0000000361,0.05000,1.357
|
| 530 |
+
75,self_attn.o_proj,0.0000000393,0.05000,1.372
|
| 531 |
+
75,mlp.gate_proj,0.0000002045,0.05000,1.407
|
| 532 |
+
75,mlp.up_proj,0.0000001918,0.05000,1.391
|
| 533 |
+
75,mlp.down_proj,0.0000003541,0.05000,4.508
|
| 534 |
+
76,self_attn.k_proj,0.0000000084,0.05000,1.356
|
| 535 |
+
76,self_attn.v_proj,0.0000000135,0.05000,1.341
|
| 536 |
+
76,self_attn.q_proj,0.0000000419,0.05000,1.365
|
| 537 |
+
76,self_attn.o_proj,0.0000000293,0.05000,1.364
|
| 538 |
+
76,mlp.gate_proj,0.0000002095,0.05000,1.399
|
| 539 |
+
76,mlp.up_proj,0.0000001976,0.05000,1.387
|
| 540 |
+
76,mlp.down_proj,0.0000003716,0.05000,4.518
|
| 541 |
+
77,self_attn.k_proj,0.0000000092,0.05000,1.352
|
| 542 |
+
77,self_attn.v_proj,0.0000000140,0.05000,1.336
|
| 543 |
+
77,self_attn.q_proj,0.0000000448,0.05000,1.354
|
| 544 |
+
77,self_attn.o_proj,0.0000000546,0.05000,1.377
|
| 545 |
+
77,mlp.gate_proj,0.0000002122,0.05000,1.402
|
| 546 |
+
77,mlp.up_proj,0.0000002017,0.05000,1.389
|
| 547 |
+
77,mlp.down_proj,0.0000003881,0.05000,4.505
|
| 548 |
+
78,self_attn.k_proj,0.0000000089,0.05000,1.356
|
| 549 |
+
78,self_attn.v_proj,0.0000000114,0.05000,1.341
|
| 550 |
+
78,self_attn.q_proj,0.0000000424,0.05000,1.362
|
| 551 |
+
78,self_attn.o_proj,0.0000000497,0.05000,1.368
|
| 552 |
+
78,mlp.gate_proj,0.0000002191,0.05000,1.405
|
| 553 |
+
78,mlp.up_proj,0.0000002094,0.05000,1.392
|
| 554 |
+
78,mlp.down_proj,0.0000004267,0.05000,4.515
|
| 555 |
+
79,self_attn.k_proj,0.0000000089,0.05000,1.354
|
| 556 |
+
79,self_attn.v_proj,0.0000000148,0.05000,1.342
|
| 557 |
+
79,self_attn.q_proj,0.0000000444,0.05000,1.357
|
| 558 |
+
79,self_attn.o_proj,0.0000000638,0.05000,1.383
|
| 559 |
+
79,mlp.gate_proj,0.0000002229,0.05000,1.404
|
| 560 |
+
79,mlp.up_proj,0.0000002144,0.05000,1.390
|
| 561 |
+
79,mlp.down_proj,0.0000004498,0.05000,4.513
|
| 562 |
+
80,self_attn.k_proj,0.0000000086,0.05000,1.349
|
| 563 |
+
80,self_attn.v_proj,0.0000000145,0.05000,1.339
|
| 564 |
+
80,self_attn.q_proj,0.0000000430,0.05000,1.360
|
| 565 |
+
80,self_attn.o_proj,0.0000000688,0.05000,1.377
|
| 566 |
+
80,mlp.gate_proj,0.0000002290,0.05000,1.404
|
| 567 |
+
80,mlp.up_proj,0.0000002219,0.05000,1.388
|
| 568 |
+
80,mlp.down_proj,0.0000004906,0.05000,4.499
|
| 569 |
+
81,self_attn.k_proj,0.0000000083,0.05000,1.348
|
| 570 |
+
81,self_attn.v_proj,0.0000000118,0.05000,1.335
|
| 571 |
+
81,self_attn.q_proj,0.0000000395,0.05000,1.358
|
| 572 |
+
81,self_attn.o_proj,0.0000000549,0.05000,1.373
|
| 573 |
+
81,mlp.gate_proj,0.0000002332,0.05000,1.399
|
| 574 |
+
81,mlp.up_proj,0.0000002276,0.05000,1.389
|
| 575 |
+
81,mlp.down_proj,0.0000005138,0.05000,4.505
|
| 576 |
+
82,self_attn.k_proj,0.0000000088,0.05000,1.351
|
| 577 |
+
82,self_attn.v_proj,0.0000000145,0.05000,1.338
|
| 578 |
+
82,self_attn.q_proj,0.0000000448,0.05000,1.351
|
| 579 |
+
82,self_attn.o_proj,0.0000000578,0.05000,1.371
|
| 580 |
+
82,mlp.gate_proj,0.0000002393,0.05000,1.402
|
| 581 |
+
82,mlp.up_proj,0.0000002350,0.05000,1.391
|
| 582 |
+
82,mlp.down_proj,0.0000005590,0.05000,4.498
|
| 583 |
+
83,self_attn.k_proj,0.0000000091,0.05000,1.357
|
| 584 |
+
83,self_attn.v_proj,0.0000000129,0.05000,1.340
|
| 585 |
+
83,self_attn.q_proj,0.0000000398,0.05000,1.364
|
| 586 |
+
83,self_attn.o_proj,0.0000000452,0.05000,1.368
|
| 587 |
+
83,mlp.gate_proj,0.0000002434,0.05000,1.405
|
| 588 |
+
83,mlp.up_proj,0.0000002414,0.05000,1.397
|
| 589 |
+
83,mlp.down_proj,0.0000005971,0.05000,4.509
|
| 590 |
+
84,self_attn.k_proj,0.0000000086,0.05000,1.355
|
| 591 |
+
84,self_attn.v_proj,0.0000000150,0.05000,1.340
|
| 592 |
+
84,self_attn.q_proj,0.0000000403,0.05000,1.362
|
| 593 |
+
84,self_attn.o_proj,0.0000000724,0.05000,1.366
|
| 594 |
+
84,mlp.gate_proj,0.0000002464,0.05000,1.403
|
| 595 |
+
84,mlp.up_proj,0.0000002464,0.05000,1.392
|
| 596 |
+
84,mlp.down_proj,0.0000006380,0.05000,4.501
|
| 597 |
+
85,self_attn.k_proj,0.0000000083,0.05000,1.354
|
| 598 |
+
85,self_attn.v_proj,0.0000000137,0.05000,1.335
|
| 599 |
+
85,self_attn.q_proj,0.0000000388,0.05000,1.357
|
| 600 |
+
85,self_attn.o_proj,0.0000000753,0.05000,1.364
|
| 601 |
+
85,mlp.gate_proj,0.0000002500,0.05000,1.400
|
| 602 |
+
85,mlp.up_proj,0.0000002514,0.05000,1.388
|
| 603 |
+
85,mlp.down_proj,0.0000006779,0.05000,4.497
|
| 604 |
+
86,self_attn.k_proj,0.0000000085,0.05000,1.346
|
| 605 |
+
86,self_attn.v_proj,0.0000000142,0.05000,1.332
|
| 606 |
+
86,self_attn.q_proj,0.0000000418,0.05000,1.350
|
| 607 |
+
86,self_attn.o_proj,0.0000000506,0.05000,1.373
|
| 608 |
+
86,mlp.gate_proj,0.0000002518,0.05000,1.398
|
| 609 |
+
86,mlp.up_proj,0.0000002552,0.05000,1.383
|
| 610 |
+
86,mlp.down_proj,0.0000007231,0.05000,4.502
|
| 611 |
+
87,self_attn.k_proj,0.0000000088,0.05000,1.347
|
| 612 |
+
87,self_attn.v_proj,0.0000000164,0.05000,1.336
|
| 613 |
+
87,self_attn.q_proj,0.0000000458,0.05000,1.357
|
| 614 |
+
87,self_attn.o_proj,0.0000001070,0.05000,1.366
|
| 615 |
+
87,mlp.gate_proj,0.0000002530,0.05000,1.398
|
| 616 |
+
87,mlp.up_proj,0.0000002578,0.05000,1.382
|
| 617 |
+
87,mlp.down_proj,0.0000007759,0.05000,4.491
|
| 618 |
+
88,self_attn.k_proj,0.0000000082,0.05000,1.349
|
| 619 |
+
88,self_attn.v_proj,0.0000000157,0.05000,1.333
|
| 620 |
+
88,self_attn.q_proj,0.0000000425,0.05000,1.355
|
| 621 |
+
88,self_attn.o_proj,0.0000000738,0.05000,1.364
|
| 622 |
+
88,mlp.gate_proj,0.0000002547,0.05000,1.398
|
| 623 |
+
88,mlp.up_proj,0.0000002600,0.05000,1.390
|
| 624 |
+
88,mlp.down_proj,0.0000007922,0.05000,4.507
|
| 625 |
+
89,self_attn.k_proj,0.0000000081,0.05000,1.352
|
| 626 |
+
89,self_attn.v_proj,0.0000000103,0.05000,1.337
|
| 627 |
+
89,self_attn.q_proj,0.0000000351,0.05000,1.356
|
| 628 |
+
89,self_attn.o_proj,0.0000000466,0.05000,1.369
|
| 629 |
+
89,mlp.gate_proj,0.0000002523,0.05000,1.404
|
| 630 |
+
89,mlp.up_proj,0.0000002582,0.05000,1.391
|
| 631 |
+
89,mlp.down_proj,0.0000008086,0.05000,4.498
|
| 632 |
+
90,self_attn.k_proj,0.0000000078,0.05000,1.347
|
| 633 |
+
90,self_attn.v_proj,0.0000000129,0.05000,1.329
|
| 634 |
+
90,self_attn.q_proj,0.0000000379,0.05000,1.354
|
| 635 |
+
90,self_attn.o_proj,0.0000000356,0.05000,1.366
|
| 636 |
+
90,mlp.gate_proj,0.0000002513,0.05000,1.407
|
| 637 |
+
90,mlp.up_proj,0.0000002573,0.05000,1.391
|
| 638 |
+
90,mlp.down_proj,0.0000008941,0.05000,4.502
|
| 639 |
+
91,self_attn.k_proj,0.0000000076,0.05000,1.351
|
| 640 |
+
91,self_attn.v_proj,0.0000000128,0.05000,1.336
|
| 641 |
+
91,self_attn.q_proj,0.0000000359,0.05000,1.359
|
| 642 |
+
91,self_attn.o_proj,0.0000000547,0.05000,1.367
|
| 643 |
+
91,mlp.gate_proj,0.0000002482,0.05000,1.404
|
| 644 |
+
91,mlp.up_proj,0.0000002512,0.05000,1.392
|
| 645 |
+
91,mlp.down_proj,0.0000009248,0.05000,4.494
|
| 646 |
+
92,self_attn.k_proj,0.0000000069,0.05000,1.349
|
| 647 |
+
92,self_attn.v_proj,0.0000000069,0.05000,1.335
|
| 648 |
+
92,self_attn.q_proj,0.0000000289,0.05000,1.354
|
| 649 |
+
92,self_attn.o_proj,0.0000000258,0.05000,1.372
|
| 650 |
+
92,mlp.gate_proj,0.0000002384,0.05000,1.395
|
| 651 |
+
92,mlp.up_proj,0.0000002353,0.05000,1.385
|
| 652 |
+
92,mlp.down_proj,0.0000010233,0.05000,4.518
|
| 653 |
+
93,self_attn.k_proj,0.0000000050,0.05000,1.352
|
| 654 |
+
93,self_attn.v_proj,0.0000000056,0.05000,1.340
|
| 655 |
+
93,self_attn.q_proj,0.0000000175,0.05000,1.356
|
| 656 |
+
93,self_attn.o_proj,0.0000000306,0.05000,1.374
|
| 657 |
+
93,mlp.gate_proj,0.0000002094,0.05000,1.398
|
| 658 |
+
93,mlp.up_proj,0.0000001961,0.05000,1.388
|
| 659 |
+
93,mlp.down_proj,0.0000009967,0.05000,4.489
|
| 660 |
+
94,self_attn.k_proj,0.0000000035,0.05000,1.356
|
| 661 |
+
94,self_attn.v_proj,0.0000000031,0.05000,1.343
|
| 662 |
+
94,self_attn.q_proj,0.0000000120,0.05000,1.358
|
| 663 |
+
94,self_attn.o_proj,0.0000000069,0.05000,1.370
|
| 664 |
+
94,mlp.gate_proj,0.0000001272,0.05000,1.400
|
| 665 |
+
94,mlp.up_proj,0.0000001148,0.05000,1.385
|
| 666 |
+
94,mlp.down_proj,0.0000017983,0.05000,4.514
|
quantize_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 8,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"desc_act": true,
|
| 5 |
+
"hyb_act": false,
|
| 6 |
+
"sym": true,
|
| 7 |
+
"lm_head": false,
|
| 8 |
+
"quant_method": "gptq",
|
| 9 |
+
"checkpoint_format": "gptq",
|
| 10 |
+
"pack_dtype": "int32",
|
| 11 |
+
"meta": {
|
| 12 |
+
"quantizer": [
|
| 13 |
+
"gptqmodel:4.0.0"
|
| 14 |
+
],
|
| 15 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 16 |
+
"damp_percent": 0.05,
|
| 17 |
+
"damp_auto_increment": 0.01,
|
| 18 |
+
"static_groups": false,
|
| 19 |
+
"true_sequential": true,
|
| 20 |
+
"mse": 0.0,
|
| 21 |
+
"v2": false,
|
| 22 |
+
"v2_alpha": 0.25
|
| 23 |
+
}
|
| 24 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|end▁of▁sentence|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"100000": {
|
| 7 |
+
"content": "<|begin▁of▁sentence|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"100001": {
|
| 15 |
+
"content": "<|end▁of▁sentence|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"100002": {
|
| 23 |
+
"content": "ø",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"100003": {
|
| 31 |
+
"content": "ö",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"100004": {
|
| 39 |
+
"content": "ú",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"100005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"100006": {
|
| 55 |
+
"content": "õ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"100007": {
|
| 63 |
+
"content": "÷",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"100008": {
|
| 71 |
+
"content": "û",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"100009": {
|
| 79 |
+
"content": "ý",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"100010": {
|
| 87 |
+
"content": "À",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"100011": {
|
| 95 |
+
"content": "ù",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"100012": {
|
| 103 |
+
"content": "Á",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"100013": {
|
| 111 |
+
"content": "þ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"100014": {
|
| 119 |
+
"content": "ü",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
}
|
| 126 |
+
},
|
| 127 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
| 128 |
+
"clean_up_tokenization_spaces": false,
|
| 129 |
+
"eos_token": "<|end▁of▁sentence|>",
|
| 130 |
+
"extra_special_tokens": {},
|
| 131 |
+
"legacy": true,
|
| 132 |
+
"model_max_length": 4096,
|
| 133 |
+
"pad_token": "<|end▁of▁sentence|>",
|
| 134 |
+
"sp_model_kwargs": {},
|
| 135 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 136 |
+
"unk_token": null,
|
| 137 |
+
"use_default_system_prompt": false
|
| 138 |
+
}
|