Commit
•
d107b22
1
Parent(s):
c2fb566
Upload folder using huggingface_hub
Browse files- README.md +23 -0
- adapter_config.json +1 -0
- adapter_model.safetensors +3 -0
- config.json +26 -0
- generation_config.json +6 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +298 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: True
|
10 |
+
- _load_in_4bit: False
|
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: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
- load_in_4bit: False
|
19 |
+
- load_in_8bit: True
|
20 |
+
### Framework versions
|
21 |
+
|
22 |
+
|
23 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"auto_mapping": null, "base_model_name_or_path": "atsuki-yamaguchi/Mistral-7B-v0.1-heuristics-untied-ar", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layers_pattern": null, "layers_to_transform": null, "lora_alpha": 32, "lora_dropout": 0.05, "modules_to_save": ["lm_head", "embed_tokens"], "peft_type": "LORA", "r": 8, "revision": null, "target_modules": ["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "task_type": "CAUSAL_LM"}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c040196ad86da9b99ae3d4d5b59ca00569b475d5e7c3b8dc0dabcb0124f12b2
|
3 |
+
size 2181099424
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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": "float64",
|
23 |
+
"transformers_version": "4.39.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 64000
|
26 |
+
}
|
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": "4.39.0.dev0"
|
6 |
+
}
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55280b8df4355a0e9154629e9af76e26985e90327e1945167d487df94035136c
|
3 |
+
size 4882271864
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f0bac6759c14ee4d41847d0bae723b5a6a49581431401e0e1bde7e727c0d1aa
|
3 |
+
size 4832007448
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26363511ef9b74574e4b1d0240bd8cfdd94e4f7b0c89ef4ff70da486d804051d
|
3 |
+
size 4999813112
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e9ffd6a5d87b5ef96d752d8d1558aa36ac3fc5d05e9c4f6162061cec092b116
|
3 |
+
size 4999813128
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76a7302529c832d7cfc43e98e64ccf942c9ddd3e574f283ae2e596df8f9ae364
|
3 |
+
size 4832007496
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40c1a941d32a3c23f0a37ecfa4b38ea8eb7913a5373bb9244277309935e84d69
|
3 |
+
size 4999813120
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40fa394b29ae7236e446100ca1300e7960e64c167908ba41758675b7d86f51b7
|
3 |
+
size 2566963880
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 32112656384
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00007-of-00007.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
296 |
+
"model.norm.weight": "model-00007-of-00007.safetensors"
|
297 |
+
}
|
298 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e25a8b2148411814dfd5a4a2eabf593d63882c5c91727c4ee59b69dcda8df354
|
3 |
+
size 1093167324
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:596f5d844ee0ec5cd0d4a254ac22c2f983915248c5e9e9216fba1aa228fd9265
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c502c4839bd0e8f15b5c7edfd874c07c774ff47fb7f76292ac238af80666792
|
3 |
+
size 1064
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:057ff43f57834f5736203d9127ba9a20c6f6b25fb549f8582117aee433f8eda2
|
3 |
+
size 5048
|