Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +9 -0
- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- checkpoint-100-adapter/adapter_config.json +26 -0
- checkpoint-100-adapter/adapter_model.bin +3 -0
- checkpoint-100/README.md +21 -0
- checkpoint-100/added_tokens.json +6 -0
- checkpoint-100/config.json +28 -0
- checkpoint-100/pytorch_model-00001-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00002-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00003-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00004-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00005-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00006-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00007-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00008-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00009-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00010-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00011-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00012-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00013-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00014-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00015-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00016-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00017-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00018-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00019-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00020-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00021-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00022-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00023-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00024-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00025-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00026-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00027-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00028-of-00029.bin +3 -0
- checkpoint-100/pytorch_model-00029-of-00029.bin +3 -0
- checkpoint-100/pytorch_model.bin.index.json +730 -0
- checkpoint-100/special_tokens_map.json +6 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +50 -0
- checkpoint-100/training_config.yaml +136 -0
- global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- global_step100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- global_step100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- global_step100/mp_rank_00_model_states.pt +3 -0
- latest +1 -0
- logiqav2_test_mc_0shot.v1.0/test-checkpoint-100/decode_results.npy +3 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
### Framework versions
|
7 |
+
|
8 |
+
|
9 |
+
- PEFT 0.4.0
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "pretrained-models/Llama-2-70b-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"gate_proj",
|
18 |
+
"o_proj",
|
19 |
+
"q_proj",
|
20 |
+
"up_proj",
|
21 |
+
"v_proj",
|
22 |
+
"down_proj",
|
23 |
+
"k_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e2cafd0afccf0506c88474f36d878a7cb268e335e50f7a9336d4007260ec209
|
3 |
+
size 1284218069
|
checkpoint-100-adapter/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "pretrained-models/Llama-2-70b-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"gate_proj",
|
18 |
+
"o_proj",
|
19 |
+
"q_proj",
|
20 |
+
"up_proj",
|
21 |
+
"v_proj",
|
22 |
+
"down_proj",
|
23 |
+
"k_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
checkpoint-100-adapter/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d408b8994d226185c29438435e5278170f050e0a6d23ea80f77d3a5ad1592391
|
3 |
+
size 1656926781
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.5.0
|
checkpoint-100/added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<pad>": 32000,
|
4 |
+
"<s>": 1,
|
5 |
+
"<unk>": 0
|
6 |
+
}
|
checkpoint-100/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pretrained-models/Llama-2-70b-hf/",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 8192,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 28672,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 64,
|
16 |
+
"num_hidden_layers": 80,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.34.0",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
checkpoint-100/pytorch_model-00001-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20b61cc0e10a30c3e1e9a48b1b0d1bdad48b6c976ada77c37fdb19413a58944a
|
3 |
+
size 9437323399
|
checkpoint-100/pytorch_model-00002-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1461ecc80c5cce5d575cde37c8b4fe8c47c64931bff9def1128d4f71d9ef4e8b
|
3 |
+
size 9328337655
|
checkpoint-100/pytorch_model-00003-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7c19c745ee070ca5c871f3a12f39bb6cf03522697c2389b7ea910c1719c9e0e
|
3 |
+
size 9999426295
|
checkpoint-100/pytorch_model-00004-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e03629e0b86e6c4f4c2dd1ea51b15e763b794d553e9e1f0a6bed09ea4fdc337d
|
3 |
+
size 9932316819
|
checkpoint-100/pytorch_model-00005-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e137bfcc44a57893146c9534d121c57ba4128080c1d41fac8fa0146b22665925
|
3 |
+
size 9328271411
|
checkpoint-100/pytorch_model-00006-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c74be7e352e4325f316d0af85bef6e378b291b0ccef4d2c863d7c2d089d67db
|
3 |
+
size 9328337707
|
checkpoint-100/pytorch_model-00007-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:008ac3b879398af8a2732efa46e0636cc9bc9d1674d48265999134f1d35802a7
|
3 |
+
size 9328337655
|
checkpoint-100/pytorch_model-00008-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54324cdcdfff5c07eb1f296e581066514d8df4ee1426f7322324be2623dcbb26
|
3 |
+
size 9999426295
|
checkpoint-100/pytorch_model-00009-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea4a5d0e2130bf125d8c21724a640c79602def03b98be87a06fb1971338fb416
|
3 |
+
size 9932316819
|
checkpoint-100/pytorch_model-00010-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c1b4bcc3f06c8590107484a47a675fa2e5c3128e8913d3aef08b9000aae5aa7
|
3 |
+
size 9328271411
|
checkpoint-100/pytorch_model-00011-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73ddf271578b1480568e59c5254b37a59276cbd07e3aa0d42f3562ea6fa57f8a
|
3 |
+
size 9328337707
|
checkpoint-100/pytorch_model-00012-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f1b2ccf43fa257b7d006569770d53000075ce32ab6f4635c90f01720a2bcdeb
|
3 |
+
size 9328337655
|
checkpoint-100/pytorch_model-00013-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f280b2ec424cd7fbb1da236aff1f9f91f2a25ba0ee47f926e5c45146fcecae8c
|
3 |
+
size 9999426295
|
checkpoint-100/pytorch_model-00014-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc4fece06e530f61470db5ab20194e13eb8a80dbf5542f9ef9e5ab53a7eeebf8
|
3 |
+
size 9932316819
|
checkpoint-100/pytorch_model-00015-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4af4ed7a37c1d3151968eca76219c7a195e6ff2ce22178451fe9e1fb11c20d50
|
3 |
+
size 9328271411
|
checkpoint-100/pytorch_model-00016-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36868a955d42593277d9ccd54b1af77c1202c6c2047aee7f23dcaf48d2c7b76b
|
3 |
+
size 9328337707
|
checkpoint-100/pytorch_model-00017-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d23a7d171832c3db5a15d4ba303c51761036de607d8d9390680be0771db155b
|
3 |
+
size 9328337655
|
checkpoint-100/pytorch_model-00018-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230f6ebf146567d4f15a3e1aab594aafeb9ea0f7a6c1aed0bc0a533903be2ee2
|
3 |
+
size 9999426295
|
checkpoint-100/pytorch_model-00019-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee42621a77731a5870840e1b73a37e1629c29f266b4e75dc7e5c8f0798486ab9
|
3 |
+
size 9932316819
|
checkpoint-100/pytorch_model-00020-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49e4e02b566100d0319d8de8dfa93d03096925b7f3ec15473e3c7cd4b6aad979
|
3 |
+
size 9328271411
|
checkpoint-100/pytorch_model-00021-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc1f42bbc7ba5d0f5bcdf90bf208d94969bf52ff24448f79d4a6d213726feb95
|
3 |
+
size 9328337707
|
checkpoint-100/pytorch_model-00022-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:378e9336f514b7ce0350393d35d51734274a33f230902ebba58029b314af7ea3
|
3 |
+
size 9328337655
|
checkpoint-100/pytorch_model-00023-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c67efa8181e2f733cd49f656ffbfd7ce725ab7cb9782f3a3697b0c29a96e401
|
3 |
+
size 9999426295
|
checkpoint-100/pytorch_model-00024-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38bb25224f3488d419c4b61104367bb2591f28f0c6016652cf93f0a15df51b1d
|
3 |
+
size 9932316819
|
checkpoint-100/pytorch_model-00025-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b961846de1615d5ff6b1347bc3c6067879a508c1eb65f25be2319fd19fabcb06
|
3 |
+
size 9328271411
|
checkpoint-100/pytorch_model-00026-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42eb77a87f6b0bb52b3498719472a14ecd094ab35d367d502fd035118585c9e2
|
3 |
+
size 9328337707
|
checkpoint-100/pytorch_model-00027-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61dbfa62a082b27786c1c005a94115694c9efdab0cbdf41f066789276a87d4d4
|
3 |
+
size 9328337655
|
checkpoint-100/pytorch_model-00028-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c22ac59cfe6697893c1d5d08a294f13dd81540b7d3b4812c8df6fa90f64d0ba
|
3 |
+
size 9999426295
|
checkpoint-100/pytorch_model-00029-of-00029.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32bb4a562901bc7b71ce4aa74782c4270e3c62e53844ef654b78ee76c4bf83b4
|
3 |
+
size 7558305653
|
checkpoint-100/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,730 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 275906592768
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00029-of-00029.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00029.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00029.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00029.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00029.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00029.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
|
242 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
|
251 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
|
260 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
|
269 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
|
278 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
|
287 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
|
296 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
|
305 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
|
314 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
|
323 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
324 |
+
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
|
325 |
+
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
|
326 |
+
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
|
327 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
328 |
+
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
|
329 |
+
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
|
330 |
+
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
|
331 |
+
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
|
332 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
333 |
+
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
|
334 |
+
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
|
335 |
+
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
|
336 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
337 |
+
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
|
338 |
+
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
|
339 |
+
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
|
340 |
+
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
|
341 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
342 |
+
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
|
343 |
+
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
|
344 |
+
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
|
345 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
346 |
+
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
|
347 |
+
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
|
348 |
+
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
|
349 |
+
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
|
350 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
351 |
+
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
|
352 |
+
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
|
353 |
+
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
|
354 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
355 |
+
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
|
356 |
+
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
|
357 |
+
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
|
358 |
+
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
|
359 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
360 |
+
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
|
361 |
+
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
|
362 |
+
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
|
363 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
364 |
+
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
|
365 |
+
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
|
366 |
+
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
|
367 |
+
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
|
368 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
369 |
+
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
|
370 |
+
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
|
371 |
+
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
|
372 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
373 |
+
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
|
374 |
+
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
|
375 |
+
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
|
376 |
+
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
|
377 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
378 |
+
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
|
379 |
+
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
|
380 |
+
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
|
381 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
382 |
+
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
|
383 |
+
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
|
384 |
+
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
|
385 |
+
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
|
386 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
387 |
+
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
|
388 |
+
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
|
389 |
+
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
|
390 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
391 |
+
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
|
392 |
+
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
|
393 |
+
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
|
394 |
+
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
|
395 |
+
"model.layers.48.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
396 |
+
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
|
397 |
+
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
|
398 |
+
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
|
399 |
+
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
400 |
+
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
|
401 |
+
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
|
402 |
+
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
|
403 |
+
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
|
404 |
+
"model.layers.49.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
405 |
+
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
|
406 |
+
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
|
407 |
+
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
|
408 |
+
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
409 |
+
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
|
410 |
+
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
|
411 |
+
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
|
412 |
+
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
|
413 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
414 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
|
415 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
|
416 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
|
417 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
418 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
|
419 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
|
420 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
|
421 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
|
422 |
+
"model.layers.50.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
423 |
+
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
|
424 |
+
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
|
425 |
+
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
|
426 |
+
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
427 |
+
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
|
428 |
+
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
|
429 |
+
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
|
430 |
+
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
|
431 |
+
"model.layers.51.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
432 |
+
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
|
433 |
+
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
|
434 |
+
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
|
435 |
+
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
436 |
+
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
|
437 |
+
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
|
438 |
+
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
|
439 |
+
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
|
440 |
+
"model.layers.52.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
441 |
+
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
|
442 |
+
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
|
443 |
+
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
|
444 |
+
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
445 |
+
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
|
446 |
+
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
|
447 |
+
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
|
448 |
+
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
|
449 |
+
"model.layers.53.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
450 |
+
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
|
451 |
+
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
|
452 |
+
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
|
453 |
+
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
454 |
+
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
|
455 |
+
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
|
456 |
+
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
|
457 |
+
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
|
458 |
+
"model.layers.54.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
459 |
+
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
|
460 |
+
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
|
461 |
+
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
|
462 |
+
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
463 |
+
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
|
464 |
+
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
|
465 |
+
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
|
466 |
+
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
|
467 |
+
"model.layers.55.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
468 |
+
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
|
469 |
+
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
|
470 |
+
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
|
471 |
+
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
472 |
+
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
|
473 |
+
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
|
474 |
+
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
|
475 |
+
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
|
476 |
+
"model.layers.56.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
477 |
+
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
|
478 |
+
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
|
479 |
+
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
|
480 |
+
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
481 |
+
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
|
482 |
+
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
|
483 |
+
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
|
484 |
+
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
|
485 |
+
"model.layers.57.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
486 |
+
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
|
487 |
+
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
|
488 |
+
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
|
489 |
+
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
490 |
+
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
|
491 |
+
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
|
492 |
+
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
|
493 |
+
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
|
494 |
+
"model.layers.58.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
495 |
+
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
|
496 |
+
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
|
497 |
+
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
|
498 |
+
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
499 |
+
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
|
500 |
+
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
|
501 |
+
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
|
502 |
+
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
|
503 |
+
"model.layers.59.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
504 |
+
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
|
505 |
+
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
|
506 |
+
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
|
507 |
+
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
508 |
+
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
|
509 |
+
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
|
510 |
+
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
|
511 |
+
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
|
512 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
513 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
|
514 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
|
515 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
|
516 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
517 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
|
518 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
|
519 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
|
520 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
|
521 |
+
"model.layers.60.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
522 |
+
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
|
523 |
+
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
|
524 |
+
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
|
525 |
+
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
526 |
+
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
|
527 |
+
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
|
528 |
+
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
|
529 |
+
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
|
530 |
+
"model.layers.61.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
531 |
+
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
|
532 |
+
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
|
533 |
+
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
|
534 |
+
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
535 |
+
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
|
536 |
+
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
|
537 |
+
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
|
538 |
+
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
|
539 |
+
"model.layers.62.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
540 |
+
"model.layers.62.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
|
541 |
+
"model.layers.62.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
|
542 |
+
"model.layers.62.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
|
543 |
+
"model.layers.62.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
544 |
+
"model.layers.62.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
|
545 |
+
"model.layers.62.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
|
546 |
+
"model.layers.62.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
|
547 |
+
"model.layers.62.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
|
548 |
+
"model.layers.63.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
549 |
+
"model.layers.63.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
|
550 |
+
"model.layers.63.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
|
551 |
+
"model.layers.63.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
|
552 |
+
"model.layers.63.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
553 |
+
"model.layers.63.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
|
554 |
+
"model.layers.63.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
|
555 |
+
"model.layers.63.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
|
556 |
+
"model.layers.63.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
|
557 |
+
"model.layers.64.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
558 |
+
"model.layers.64.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
|
559 |
+
"model.layers.64.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
|
560 |
+
"model.layers.64.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
|
561 |
+
"model.layers.64.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
562 |
+
"model.layers.64.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
|
563 |
+
"model.layers.64.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
|
564 |
+
"model.layers.64.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
|
565 |
+
"model.layers.64.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
|
566 |
+
"model.layers.65.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
567 |
+
"model.layers.65.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
|
568 |
+
"model.layers.65.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
|
569 |
+
"model.layers.65.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
|
570 |
+
"model.layers.65.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
571 |
+
"model.layers.65.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
|
572 |
+
"model.layers.65.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
|
573 |
+
"model.layers.65.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
|
574 |
+
"model.layers.65.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
|
575 |
+
"model.layers.66.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
576 |
+
"model.layers.66.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
|
577 |
+
"model.layers.66.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
|
578 |
+
"model.layers.66.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
|
579 |
+
"model.layers.66.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
580 |
+
"model.layers.66.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
|
581 |
+
"model.layers.66.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
|
582 |
+
"model.layers.66.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
|
583 |
+
"model.layers.66.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
|
584 |
+
"model.layers.67.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
585 |
+
"model.layers.67.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
|
586 |
+
"model.layers.67.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
|
587 |
+
"model.layers.67.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
|
588 |
+
"model.layers.67.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
589 |
+
"model.layers.67.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
|
590 |
+
"model.layers.67.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
|
591 |
+
"model.layers.67.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
|
592 |
+
"model.layers.67.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
|
593 |
+
"model.layers.68.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
594 |
+
"model.layers.68.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
|
595 |
+
"model.layers.68.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
|
596 |
+
"model.layers.68.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
|
597 |
+
"model.layers.68.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
598 |
+
"model.layers.68.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
|
599 |
+
"model.layers.68.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
|
600 |
+
"model.layers.68.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
|
601 |
+
"model.layers.68.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
|
602 |
+
"model.layers.69.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
603 |
+
"model.layers.69.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
|
604 |
+
"model.layers.69.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
|
605 |
+
"model.layers.69.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
|
606 |
+
"model.layers.69.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
607 |
+
"model.layers.69.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
|
608 |
+
"model.layers.69.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
|
609 |
+
"model.layers.69.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
|
610 |
+
"model.layers.69.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
|
611 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
612 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
|
613 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
|
614 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
|
615 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
616 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
|
617 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
|
618 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
|
619 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
|
620 |
+
"model.layers.70.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
621 |
+
"model.layers.70.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
|
622 |
+
"model.layers.70.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
|
623 |
+
"model.layers.70.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
|
624 |
+
"model.layers.70.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
625 |
+
"model.layers.70.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
|
626 |
+
"model.layers.70.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
|
627 |
+
"model.layers.70.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
|
628 |
+
"model.layers.70.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
|
629 |
+
"model.layers.71.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
630 |
+
"model.layers.71.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
|
631 |
+
"model.layers.71.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
|
632 |
+
"model.layers.71.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
|
633 |
+
"model.layers.71.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
634 |
+
"model.layers.71.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
|
635 |
+
"model.layers.71.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
|
636 |
+
"model.layers.71.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
|
637 |
+
"model.layers.71.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
|
638 |
+
"model.layers.72.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
639 |
+
"model.layers.72.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
|
640 |
+
"model.layers.72.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
|
641 |
+
"model.layers.72.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
|
642 |
+
"model.layers.72.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
643 |
+
"model.layers.72.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
|
644 |
+
"model.layers.72.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
|
645 |
+
"model.layers.72.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
|
646 |
+
"model.layers.72.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
|
647 |
+
"model.layers.73.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
648 |
+
"model.layers.73.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
|
649 |
+
"model.layers.73.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
|
650 |
+
"model.layers.73.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
|
651 |
+
"model.layers.73.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
652 |
+
"model.layers.73.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
|
653 |
+
"model.layers.73.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
|
654 |
+
"model.layers.73.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
|
655 |
+
"model.layers.73.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
|
656 |
+
"model.layers.74.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
657 |
+
"model.layers.74.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
|
658 |
+
"model.layers.74.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
|
659 |
+
"model.layers.74.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
|
660 |
+
"model.layers.74.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
661 |
+
"model.layers.74.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
|
662 |
+
"model.layers.74.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
|
663 |
+
"model.layers.74.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
|
664 |
+
"model.layers.74.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
|
665 |
+
"model.layers.75.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
666 |
+
"model.layers.75.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
|
667 |
+
"model.layers.75.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
|
668 |
+
"model.layers.75.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
|
669 |
+
"model.layers.75.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
670 |
+
"model.layers.75.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
|
671 |
+
"model.layers.75.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
|
672 |
+
"model.layers.75.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
|
673 |
+
"model.layers.75.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
|
674 |
+
"model.layers.76.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
675 |
+
"model.layers.76.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
|
676 |
+
"model.layers.76.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
|
677 |
+
"model.layers.76.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
|
678 |
+
"model.layers.76.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
679 |
+
"model.layers.76.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
|
680 |
+
"model.layers.76.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
|
681 |
+
"model.layers.76.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
|
682 |
+
"model.layers.76.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
|
683 |
+
"model.layers.77.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
684 |
+
"model.layers.77.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
|
685 |
+
"model.layers.77.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
|
686 |
+
"model.layers.77.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
|
687 |
+
"model.layers.77.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
688 |
+
"model.layers.77.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
|
689 |
+
"model.layers.77.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
|
690 |
+
"model.layers.77.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
|
691 |
+
"model.layers.77.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
|
692 |
+
"model.layers.78.input_layernorm.weight": "pytorch_model-00029-of-00029.bin",
|
693 |
+
"model.layers.78.mlp.down_proj.weight": "pytorch_model-00029-of-00029.bin",
|
694 |
+
"model.layers.78.mlp.gate_proj.weight": "pytorch_model-00029-of-00029.bin",
|
695 |
+
"model.layers.78.mlp.up_proj.weight": "pytorch_model-00029-of-00029.bin",
|
696 |
+
"model.layers.78.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
|
697 |
+
"model.layers.78.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
|
698 |
+
"model.layers.78.self_attn.o_proj.weight": "pytorch_model-00029-of-00029.bin",
|
699 |
+
"model.layers.78.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
|
700 |
+
"model.layers.78.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
|
701 |
+
"model.layers.79.input_layernorm.weight": "pytorch_model-00029-of-00029.bin",
|
702 |
+
"model.layers.79.mlp.down_proj.weight": "pytorch_model-00029-of-00029.bin",
|
703 |
+
"model.layers.79.mlp.gate_proj.weight": "pytorch_model-00029-of-00029.bin",
|
704 |
+
"model.layers.79.mlp.up_proj.weight": "pytorch_model-00029-of-00029.bin",
|
705 |
+
"model.layers.79.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
|
706 |
+
"model.layers.79.self_attn.k_proj.weight": "pytorch_model-00029-of-00029.bin",
|
707 |
+
"model.layers.79.self_attn.o_proj.weight": "pytorch_model-00029-of-00029.bin",
|
708 |
+
"model.layers.79.self_attn.q_proj.weight": "pytorch_model-00029-of-00029.bin",
|
709 |
+
"model.layers.79.self_attn.v_proj.weight": "pytorch_model-00029-of-00029.bin",
|
710 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
711 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
|
712 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
|
713 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
|
714 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
715 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
|
716 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
|
717 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
|
718 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
|
719 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
720 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
|
721 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
|
722 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
|
723 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
724 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
|
725 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
|
726 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
|
727 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
|
728 |
+
"model.norm.weight": "pytorch_model-00029-of-00029.bin"
|
729 |
+
}
|
730 |
+
}
|
checkpoint-100/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<unk>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-100/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-100/tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<pad>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"additional_special_tokens": [],
|
39 |
+
"bos_token": "<s>",
|
40 |
+
"clean_up_tokenization_spaces": false,
|
41 |
+
"eos_token": "</s>",
|
42 |
+
"legacy": false,
|
43 |
+
"model_max_length": 1000000000000000019884624838656,
|
44 |
+
"pad_token": "<unk>",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"tokenizer_class": "LlamaTokenizer",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"use_default_system_prompt": true
|
50 |
+
}
|
checkpoint-100/training_config.yaml
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
train_file: wiki_erica_path/v9.1_fixed/distant_path_v9.1_fix_no_shuffle.train.0.pkl_llama_False_3_6_512_0.4_5_1.0_1.0_0.0_8_path_v9.1.2_seq2seq_bin_filter
|
2 |
+
test_file: null
|
3 |
+
model:
|
4 |
+
_target_: models.llama.LlamaForConditionalGenerationFlan.from_pretrained
|
5 |
+
use_peft: true
|
6 |
+
lora_config:
|
7 |
+
_recursive_: false
|
8 |
+
_target_: models.llama.LoraConfig
|
9 |
+
task_type: CAUSAL_LM
|
10 |
+
inference_mode: false
|
11 |
+
target_modules:
|
12 |
+
_target_: models.llama.find_all_linear_names
|
13 |
+
bits: 4
|
14 |
+
r: 64
|
15 |
+
lora_alpha: 16
|
16 |
+
lora_dropout: 0.05
|
17 |
+
gradient_checkpointing: true
|
18 |
+
torch_dtype:
|
19 |
+
_target_: general_util.training_utils.return_torch_dtype
|
20 |
+
dtype: bfloat16
|
21 |
+
quantization_config:
|
22 |
+
_target_: transformers.utils.quantization_config.BitsAndBytesConfig
|
23 |
+
load_in_4bit: true
|
24 |
+
bnb_4bit_compute_dtype:
|
25 |
+
_target_: general_util.training_utils.return_torch_dtype
|
26 |
+
dtype: bfloat16
|
27 |
+
bnb_4bit_use_double_quant: true
|
28 |
+
bnb_4bit_quant_type: nf4
|
29 |
+
device_map:
|
30 |
+
_target_: models.llama.return_single_device_map
|
31 |
+
load_in_4bit: true
|
32 |
+
low_cpu_mem_usage: true
|
33 |
+
max_memory: true
|
34 |
+
use_flash_attention_2: true
|
35 |
+
dist_load_data_barrier: false
|
36 |
+
read_tensor_train:
|
37 |
+
_target_: data.collators.wiki.WikiPathDatasetV5.init_from_bin_file
|
38 |
+
extended_vocab: null
|
39 |
+
collator:
|
40 |
+
_target_: data.collators.wiki_seq2seq_collator.WikiSeq2SeqCollatorWithCausalLMFixPaddingSide
|
41 |
+
max_seq_length: 512
|
42 |
+
tokenizer: ${model_name_or_path}
|
43 |
+
causal_lm: true
|
44 |
+
causal_lm_add_eos: false
|
45 |
+
generative_mode: true
|
46 |
+
padding_side: right
|
47 |
+
num_workers: 4
|
48 |
+
prefetch_factor: 2
|
49 |
+
do_preprocess: false
|
50 |
+
model_name_or_path: pretrained-models/Llama-2-70b-hf
|
51 |
+
pretrain: null
|
52 |
+
exp_name: llama2.70b.q_lora.merit_v91_v91.seq2seq.v5.0.6aug.filter.w4.adamw.500steps.NA100.1010
|
53 |
+
exp_notes: null
|
54 |
+
output_dir: experiments/${exp_name}
|
55 |
+
do_train: true
|
56 |
+
evaluate_during_training: false
|
57 |
+
do_eval: true
|
58 |
+
eval_sub_path: checkpoint-*
|
59 |
+
per_gpu_train_batch_size: 8
|
60 |
+
per_gpu_eval_batch_size: 16
|
61 |
+
learning_rate: 0.0002
|
62 |
+
gradient_accumulation_steps: 128
|
63 |
+
weight_decay: 0.0
|
64 |
+
adam_epsilon: 1.0e-06
|
65 |
+
adam_betas: (0.9, 0.99)
|
66 |
+
max_grad_norm: 0.3
|
67 |
+
num_train_epochs: 1
|
68 |
+
max_steps: -1
|
69 |
+
warmup_proportion: 0
|
70 |
+
warmup_steps: 50
|
71 |
+
total_dataset_len: 1808348
|
72 |
+
optimizer: null
|
73 |
+
use_nvlamb: null
|
74 |
+
bit_training: null
|
75 |
+
logging_steps: 1
|
76 |
+
save_best: false
|
77 |
+
save_steps: 100
|
78 |
+
eval_steps: -1
|
79 |
+
ddp_eval: true
|
80 |
+
no_cuda: false
|
81 |
+
seed: 42
|
82 |
+
local_rank: 0
|
83 |
+
fp16: true
|
84 |
+
fp16_opt_level: O1
|
85 |
+
fp16_bfloat16: true
|
86 |
+
prediction_cfg:
|
87 |
+
metric: acc
|
88 |
+
measure: 1
|
89 |
+
best_checkpoint: null
|
90 |
+
best_result: null
|
91 |
+
eval_forward_fn:
|
92 |
+
_target_: general_util.evaluator.DiscriminatorForwardFn
|
93 |
+
post_process: null
|
94 |
+
compile: false
|
95 |
+
fairscale_config: null
|
96 |
+
fsdp_config: null
|
97 |
+
ds_cfg:
|
98 |
+
train_micro_batch_size_per_gpu: ${per_gpu_train_batch_size}
|
99 |
+
gradient_accumulation_steps: ${gradient_accumulation_steps}
|
100 |
+
optimizer:
|
101 |
+
type: AdamW
|
102 |
+
params:
|
103 |
+
lr: ${learning_rate}
|
104 |
+
betas:
|
105 |
+
- 0.9
|
106 |
+
- 0.999
|
107 |
+
eps: ${adam_epsilon}
|
108 |
+
weight_decay: ${weight_decay}
|
109 |
+
scheduler:
|
110 |
+
type: WarmupLR
|
111 |
+
params:
|
112 |
+
warmup_max_lr: ${learning_rate}
|
113 |
+
warmup_num_steps: 50
|
114 |
+
warmup_type: linear
|
115 |
+
gradient_clipping: ${max_grad_norm}
|
116 |
+
bf16:
|
117 |
+
enabled: ${fp16}
|
118 |
+
zero_optimization:
|
119 |
+
stage: 1
|
120 |
+
contiguous_gradients: true
|
121 |
+
overlap_comm: true
|
122 |
+
reduce_scatter: true
|
123 |
+
reduce_bucket_size: 500000000.0
|
124 |
+
allgather_bucket_size: 500000000.0
|
125 |
+
steps_per_print: 1024
|
126 |
+
with_lightseq: false
|
127 |
+
summary_helper:
|
128 |
+
_target_: general_util.tensorboard_helper.WandbWriter
|
129 |
+
batch_index_or_keys: null
|
130 |
+
outputs_index_or_keys:
|
131 |
+
train/mlm_loss: mlm_loss
|
132 |
+
n_gpu: 1
|
133 |
+
device: cuda:0
|
134 |
+
train_batch_size: 8
|
135 |
+
eval_batch_size: null
|
136 |
+
world_size: 4
|
global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:870333b8d093604e80228e5b1ed955d72c0eb15c9f8de99c5dc37b55226c78af
|
3 |
+
size 2485158743
|
global_step100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0167e60ca87b267ac0669e0e4067d4ad14105356f1883249cc7ba135ee0e3e27
|
3 |
+
size 2485158871
|
global_step100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48df928c6d4dcfcc18331ca4d026be1bc2f6c3d964a23aa0649b8e6727ad30a3
|
3 |
+
size 2485158871
|
global_step100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47c53efd2234d9e5d6e3a3d7d2b8cfad2c0ad19c7808f0bed8ffbec5d0ea0371
|
3 |
+
size 2485158871
|
global_step100/mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42661318ba11b267ad6758483a7c24c5b8abbee627b3dc34d76e4f5234ef9fca
|
3 |
+
size 36934524465
|
latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step100
|
logiqav2_test_mc_0shot.v1.0/test-checkpoint-100/decode_results.npy
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c7bd830f9fc03be25a06f8e245a210d6939c516180264f8a730bdfbd9ae9584
|
3 |
+
size 12704
|