Commit
•
9b8d10a
1
Parent(s):
d60468f
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +8 -0
- README.md +74 -0
- all_results.json +15 -0
- checkpoint-10000/config.json +26 -0
- checkpoint-10000/generation_config.json +6 -0
- checkpoint-10000/model-00001-of-00004.safetensors +3 -0
- checkpoint-10000/model-00002-of-00004.safetensors +3 -0
- checkpoint-10000/model-00003-of-00004.safetensors +3 -0
- checkpoint-10000/model-00004-of-00004.safetensors +3 -0
- checkpoint-10000/model.safetensors.index.json +298 -0
- checkpoint-10000/optimizer.pt +3 -0
- checkpoint-10000/rng_state_0.pth +3 -0
- checkpoint-10000/rng_state_1.pth +3 -0
- checkpoint-10000/rng_state_10.pth +3 -0
- checkpoint-10000/rng_state_11.pth +3 -0
- checkpoint-10000/rng_state_12.pth +3 -0
- checkpoint-10000/rng_state_13.pth +3 -0
- checkpoint-10000/rng_state_14.pth +3 -0
- checkpoint-10000/rng_state_15.pth +3 -0
- checkpoint-10000/rng_state_16.pth +3 -0
- checkpoint-10000/rng_state_17.pth +3 -0
- checkpoint-10000/rng_state_18.pth +3 -0
- checkpoint-10000/rng_state_19.pth +3 -0
- checkpoint-10000/rng_state_2.pth +3 -0
- checkpoint-10000/rng_state_20.pth +3 -0
- checkpoint-10000/rng_state_21.pth +3 -0
- checkpoint-10000/rng_state_22.pth +3 -0
- checkpoint-10000/rng_state_23.pth +3 -0
- checkpoint-10000/rng_state_24.pth +3 -0
- checkpoint-10000/rng_state_25.pth +3 -0
- checkpoint-10000/rng_state_26.pth +3 -0
- checkpoint-10000/rng_state_27.pth +3 -0
- checkpoint-10000/rng_state_28.pth +3 -0
- checkpoint-10000/rng_state_29.pth +3 -0
- checkpoint-10000/rng_state_3.pth +3 -0
- checkpoint-10000/rng_state_30.pth +3 -0
- checkpoint-10000/rng_state_31.pth +3 -0
- checkpoint-10000/rng_state_4.pth +3 -0
- checkpoint-10000/rng_state_5.pth +3 -0
- checkpoint-10000/rng_state_6.pth +3 -0
- checkpoint-10000/rng_state_7.pth +3 -0
- checkpoint-10000/rng_state_8.pth +3 -0
- checkpoint-10000/rng_state_9.pth +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/special_tokens_map.json +23 -0
- checkpoint-10000/tokenizer.json +0 -0
- checkpoint-10000/tokenizer_config.json +42 -0
- checkpoint-10000/trainer_state.json +0 -0
- checkpoint-10000/training_args.bin +3 -0
- checkpoint-20000/config.json +26 -0
.gitattributes
CHANGED
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
llmtf_eval/daru_treewayabstractive.jsonl filter=lfs diff=lfs merge=lfs -text
|
37 |
+
llmtf_eval/daru_treewayextractive.jsonl filter=lfs diff=lfs merge=lfs -text
|
38 |
+
llmtf_eval/darumeru_MultiQ.jsonl filter=lfs diff=lfs merge=lfs -text
|
39 |
+
llmtf_eval/darumeru_USE.jsonl filter=lfs diff=lfs merge=lfs -text
|
40 |
+
llmtf_eval/darumeru_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
|
41 |
+
llmtf_eval/nlpcoreteam_enMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
|
42 |
+
llmtf_eval/nlpcoreteam_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
|
43 |
+
llmtf_eval/russiannlp_rucola_custom.jsonl filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr2e5_bs256
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr2e5_bs256
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24](https://huggingface.co/RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.2338
|
20 |
+
- Accuracy: 0.5418
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 4
|
42 |
+
- seed: 42
|
43 |
+
- distributed_type: multi-GPU
|
44 |
+
- num_devices: 32
|
45 |
+
- total_train_batch_size: 128
|
46 |
+
- total_eval_batch_size: 128
|
47 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
|
48 |
+
- lr_scheduler_type: cosine
|
49 |
+
- lr_scheduler_warmup_steps: 100
|
50 |
+
- num_epochs: 1.0
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
56 |
+
| 2.6021 | 0.09 | 2000 | 2.3285 | 0.5305 |
|
57 |
+
| 2.5355 | 0.18 | 4000 | 2.2744 | 0.5365 |
|
58 |
+
| 2.5063 | 0.27 | 6000 | 2.2538 | 0.5391 |
|
59 |
+
| 2.4939 | 0.36 | 8000 | 2.2441 | 0.5402 |
|
60 |
+
| 2.463 | 0.45 | 10000 | 2.2385 | 0.5410 |
|
61 |
+
| 2.4559 | 0.54 | 12000 | 2.2359 | 0.5414 |
|
62 |
+
| 2.5186 | 0.63 | 14000 | 2.2347 | 0.5415 |
|
63 |
+
| 2.4755 | 0.73 | 16000 | 2.2340 | 0.5416 |
|
64 |
+
| 2.4813 | 0.82 | 18000 | 2.2338 | 0.5417 |
|
65 |
+
| 2.4797 | 0.91 | 20000 | 2.2338 | 0.5418 |
|
66 |
+
| 2.4525 | 1.0 | 22000 | 2.2338 | 0.5418 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.37.2
|
72 |
+
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
|
73 |
+
- Datasets 2.18.0
|
74 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.541759001631102,
|
4 |
+
"eval_loss": 2.233785390853882,
|
5 |
+
"eval_runtime": 8.8105,
|
6 |
+
"eval_samples": 1367,
|
7 |
+
"eval_samples_per_second": 155.155,
|
8 |
+
"eval_steps_per_second": 1.249,
|
9 |
+
"perplexity": 9.335136421381748,
|
10 |
+
"train_loss": 2.52519507538886,
|
11 |
+
"train_runtime": 21683.5632,
|
12 |
+
"train_samples": 2824235,
|
13 |
+
"train_samples_per_second": 130.248,
|
14 |
+
"train_steps_per_second": 1.018
|
15 |
+
}
|
checkpoint-10000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.37.2",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 55329
|
26 |
+
}
|
checkpoint-10000/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.37.2"
|
6 |
+
}
|
checkpoint-10000/model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8890386736002ef7003c453374da92f1f091566ed4b04145e983b48b5ae40ad
|
3 |
+
size 4899392256
|
checkpoint-10000/model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:322b3610f2907b12b178a329ce2e57a6c136f5a434cbdd3b19a8e8811aefac96
|
3 |
+
size 4915916184
|
checkpoint-10000/model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd6eeda49cd19fe02f9272ba0fa246d028400625bf468bca3c3a0954184845a8
|
3 |
+
size 4597156656
|
checkpoint-10000/model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9dff056f76325d885f203a0b375d5b959ca4bc879893313af9a447a205ca869
|
3 |
+
size 453255296
|
checkpoint-10000/model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14865686528
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
297 |
+
}
|
298 |
+
}
|
checkpoint-10000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fac9b1058d5de4c38587d6c59c12a2c36bfed2ab40c33ff7e990d3614406601c
|
3 |
+
size 1813023580
|
checkpoint-10000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7d7e02ffb4d440dce7ab4ce0b5617578ec9ce3672acee7434ed6f1153f1ae0c
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5b40ca759e432b2688f021b81291d74a40f56a205e9842119f7e772275eebd3
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_10.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d77ef8825b0e27c584c2d3eaeebfd82ebe38732eae91ff9f69c9a874632730c8
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_11.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32f9f9d83cb982f1d825d89bde80de05cf37ecaa787ad08de64e0c8df94e6115
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_12.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77270e25477a4a35eaceb98ecff060e192a6357bdc322e5d19aa92ecacd4e7e3
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_13.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9eab08108477ca9ce657269520a7cfc34510e7812e8499eb4c1a918805c8fb0
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_14.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:162d71274c75bc8f1dcbf21836ecdbc2a8c2756b4971b76847083de39d3d4098
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_15.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8517010852772c3221be3f5fe18254baa1d12a58a99ef4cabc7765112ce8a7ea
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_16.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a250ed254795e4e4504b506d04db82f380f4eb2e6595f5b4db26d5287d9f19f9
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_17.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f82da447eda9d13563c872f9f02082326c2609222589e499952428deddddc0c0
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_18.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:670bb76c1a617a793d411f1fd5e637820bb73461acecb7079b46e77656742b23
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_19.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61abdae5bf60c67d4ab6dd90c24302ecc2653679c87490e05e124cef29d067c8
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdaef955ddd36d6bc1c40584113dd6205483e2aa85b02439b8b27e82e02a8359
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_20.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:208f88af7af8cd9bdf60807bf690c18250c657a04e5f149e2cc3c9d6bbde6b6a
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_21.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9c7f278df9fa37cd3734cd0a888b2abf03557f030bd4fcb8fb7f8839333ba29
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_22.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5664286b7500e3455c4e3c2484e1c9a1d4249e8dd4f5659baf6fcbd6c7e4eaca
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_23.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b5f3473cece9689d4b60980dbfadb31d214c80d2ffe2c6600d4cdba8d3f211e
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_24.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11f0c24c9ee5222490187668cc08d631e1ee07a6b63b8338900bce68f73738bc
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_25.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ab3f5c8d599ac596e106554a773afb645c00fde628d961a321177c4bdfcf3f6
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_26.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d68e0abe3b89ecf1a271ba7ae74389c841a70bd0ec78bb2e58367110f6c331ff
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_27.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac0aa38ec6826eb2657378429c2c869402118c5d7861bc4e7e6fcda83ba33424
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_28.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1887f9cde8811d5e3dd9b40238c012638cb63058f2819a957829b8396d8877bd
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_29.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55fe904e256fc348cda96846bb29f74c60d8afccc953b0178119c1e1fece2d55
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10b14ae5db356e6512538751d6b386c190754e307cc99cd652d5c6dd891e1f82
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_30.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d175386cc8bbe8aa48992fbfa5e6a66cb5c42b37a0de5f55a2f75c48f905455
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_31.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09c698121ff56cee70b59047dd5a4ca22dff6309e792bd80877a57dd2ae21c4d
|
3 |
+
size 15997
|
checkpoint-10000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f26e28be26826eeeed244b77185c67b443ac185175f8d4bf5ba94caa8b271bc5
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:847cedc1d6ca26f299a132c2ade9754887374acb9d98f26594a85d4c7742d474
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcd043d1690ae0ff6991b03322799a0b28f021427b15fd9f1e5ed8b9905d9307
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:772190f7e6667c865d25fc72da7bdd1b5d39f46fe03bb5c2d754aee1ad3c99c7
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_8.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6632cfcdbb30b4b8f6c2437ffa4a4f76a2a7c729fefd331ecb675d2f63f96bf5
|
3 |
+
size 15984
|
checkpoint-10000/rng_state_9.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e6c87b73b3f0787cc3976a6cbd289ee87123c4cb74f388630459c010fa9fbeb
|
3 |
+
size 15984
|
checkpoint-10000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04642644a95e9c41e7fa23bc5200bc679c5342228c54a3a0e0b04d598f94a7c7
|
3 |
+
size 1064
|
checkpoint-10000/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
checkpoint-10000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-10000/tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
checkpoint-10000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-10000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96b8baeb7fe2c3b0d6996a0ed15501705ce8aa377ed7c36383783f4e6a77263b
|
3 |
+
size 4856
|
checkpoint-20000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.37.2",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 55329
|
26 |
+
}
|