gmonsoon commited on
Commit
66fc012
1 Parent(s): ac4fb46

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - abacaj/phi-2-super
7
+ - abacaj/phi-2-super
8
+ - abacaj/phi-2-super
9
+ - abacaj/phi-2-super
10
+ - abacaj/phi-2-super
11
+ - abacaj/phi-2-super
12
+ - abacaj/phi-2-super
13
+ base_model:
14
+ - abacaj/phi-2-super
15
+ - abacaj/phi-2-super
16
+ - abacaj/phi-2-super
17
+ - abacaj/phi-2-super
18
+ - abacaj/phi-2-super
19
+ - abacaj/phi-2-super
20
+ - abacaj/phi-2-super
21
+ ---
22
+
23
+ # phi-2-medium
24
+
25
+ phi-2-medium is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
26
+ * [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
27
+ * [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
28
+ * [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
29
+ * [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
30
+ * [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
31
+ * [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
32
+ * [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
33
+
34
+ ## 🧩 Configuration
35
+
36
+ ```yaml
37
+ dtype: bfloat16
38
+ merge_method: passthrough
39
+ slices:
40
+ - sources:
41
+ - layer_range: [0, 8]
42
+ model: abacaj/phi-2-super
43
+ - sources:
44
+ - layer_range: [4, 12]
45
+ model: abacaj/phi-2-super
46
+ - sources:
47
+ - layer_range: [8, 16]
48
+ model: abacaj/phi-2-super
49
+ - sources:
50
+ - layer_range: [12, 20]
51
+ model: abacaj/phi-2-super
52
+ - sources:
53
+ - layer_range: [16, 24]
54
+ model: abacaj/phi-2-super
55
+ - sources:
56
+ - layer_range: [20, 28]
57
+ model: abacaj/phi-2-super
58
+ - sources:
59
+ - layer_range: [24, 32]
60
+ model: abacaj/phi-2-super
61
+ ```
62
+
63
+ ## 💻 Usage
64
+
65
+ ```python
66
+ !pip install -qU transformers accelerate
67
+
68
+ from transformers import AutoTokenizer
69
+ import transformers
70
+ import torch
71
+
72
+ model = "gmonsoon/phi-2-medium"
73
+ messages = [{"role": "user", "content": "What is a large language model?"}]
74
+
75
+ tokenizer = AutoTokenizer.from_pretrained(model)
76
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
77
+ pipeline = transformers.pipeline(
78
+ "text-generation",
79
+ model=model,
80
+ torch_dtype=torch.float16,
81
+ device_map="auto",
82
+ )
83
+
84
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
85
+ print(outputs[0]["generated_text"])
86
+ ```
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "abacaj/phi-2-super",
3
+ "architectures": [
4
+ "PhiForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": 50256,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 50256,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_size": 2560,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 10240,
18
+ "layer_norm_eps": 1e-05,
19
+ "max_position_embeddings": 2048,
20
+ "model_type": "phi",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 56,
23
+ "num_key_value_heads": 32,
24
+ "partial_rotary_factor": 0.4,
25
+ "qk_layernorm": false,
26
+ "resid_pdrop": 0.1,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.38.2",
32
+ "use_cache": true,
33
+ "vocab_size": 51200
34
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ dtype: bfloat16
3
+ merge_method: passthrough
4
+ slices:
5
+ - sources:
6
+ - layer_range: [0, 8]
7
+ model: abacaj/phi-2-super
8
+ - sources:
9
+ - layer_range: [4, 12]
10
+ model: abacaj/phi-2-super
11
+ - sources:
12
+ - layer_range: [8, 16]
13
+ model: abacaj/phi-2-super
14
+ - sources:
15
+ - layer_range: [12, 20]
16
+ model: abacaj/phi-2-super
17
+ - sources:
18
+ - layer_range: [16, 24]
19
+ model: abacaj/phi-2-super
20
+ - sources:
21
+ - layer_range: [20, 28]
22
+ model: abacaj/phi-2-super
23
+ - sources:
24
+ - layer_range: [24, 32]
25
+ model: abacaj/phi-2-super
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5daadcde037d6cd340782121efea8ed9f5bb0f74aefb47432bfa8af77a9a3641
3
+ size 1953672656
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daade7b6cb463bbc6d5a232233b2f4f232796419dbd41c986f5db3796b1f2498
3
+ size 1992999496
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042bfeba5f9e2a8080c943b1655da1605cf312574bda2c938ddee1c0b50de9e9
3
+ size 1993051512
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec4cca31e2b92a92eb8d4c29580e975a1efb1562ad7b45effd547dc90b29f2c
3
+ size 1993036344
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d530807fc5f6be3242ad4d902a54134177f0f39ae3982c85a2084643d69306
3
+ size 1402920008
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.54.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.53.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.53.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.53.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.53.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.53.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.53.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.53.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.52.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.52.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.52.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.52.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.52.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.52.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.52.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.51.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.47.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.51.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.47.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.51.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.47.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.51.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.47.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.51.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.47.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.51.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.47.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.51.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.47.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.50.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.46.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.50.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.46.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.50.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.46.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.50.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.46.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.50.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.46.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.50.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.46.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.50.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.46.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.49.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.45.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.49.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.45.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.49.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.45.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.49.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.45.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.49.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.45.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.49.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.45.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.49.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.45.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.48.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.44.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.48.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.44.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.48.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.44.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.48.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.44.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.48.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.44.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.48.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.44.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.48.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.44.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.43.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.39.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.43.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.39.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.layers.43.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.39.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.layers.43.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.39.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", "model.layers.43.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.39.self_attn.dense.weight": "model-00001-of-00005.safetensors", "model.layers.43.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.39.self_attn.dense.bias": "model-00001-of-00005.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.43.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.39.input_layernorm.bias": "model-00001-of-00005.safetensors", "model.layers.42.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.layers.38.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.42.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.38.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.42.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.38.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.42.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.38.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.42.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.38.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.42.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.38.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.42.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.38.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.41.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.37.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.41.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.37.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.41.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.37.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.41.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.37.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.41.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.37.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.41.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.37.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.41.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.37.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.40.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.36.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.40.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.36.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.40.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.36.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.40.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.36.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.40.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.36.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.40.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.36.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.40.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.36.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.35.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.31.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.35.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.31.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.35.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.31.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.35.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.31.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.35.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.35.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.31.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.35.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.31.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.34.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.30.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.34.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.30.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.34.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.30.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.34.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.30.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.34.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.34.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.30.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.33.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.29.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.33.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.29.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.33.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.29.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.33.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.29.mlp.fc1.bias": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.dense.weight": "model-00002-of-00005.safetensors", "model.layers.33.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.dense.bias": "model-00002-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.33.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.29.input_layernorm.bias": "model-00002-of-00005.safetensors", "model.layers.32.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.28.mlp.fc2.weight": "model-00002-of-00005.safetensors", "model.layers.32.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.28.mlp.fc2.bias": "model-00002-of-00005.safetensors", "model.layers.32.mlp.fc1.weight": "model-00002-of-00005.safetensors", "model.layers.28.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.32.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.28.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.32.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.28.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.27.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.23.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.27.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.23.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.23.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.26.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.22.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.26.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.22.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.22.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.25.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.21.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.25.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.21.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.21.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.24.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.20.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.24.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.20.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.20.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.19.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.15.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.19.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.15.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.19.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.15.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.19.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.15.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.dense.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.dense.bias": "model-00003-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.15.input_layernorm.bias": "model-00003-of-00005.safetensors", "model.layers.18.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.14.mlp.fc2.weight": "model-00003-of-00005.safetensors", "model.layers.18.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.14.mlp.fc2.bias": "model-00003-of-00005.safetensors", "model.layers.18.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.14.mlp.fc1.weight": "model-00003-of-00005.safetensors", "model.layers.18.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.14.mlp.fc1.bias": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.18.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.14.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.17.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.13.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.17.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.13.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.17.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.13.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.17.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.13.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.17.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.17.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.13.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.16.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.12.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.16.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.12.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.16.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.12.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.16.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.12.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.16.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.16.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.12.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.11.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.11.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.7.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.11.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.11.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.7.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.11.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.7.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.10.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.10.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.6.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.10.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.10.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.6.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.10.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.6.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.9.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.5.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.9.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.5.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.9.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.5.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.9.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.5.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.9.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.5.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.8.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.4.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.8.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.4.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.8.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.4.mlp.fc1.weight": "model-00004-of-00005.safetensors", "model.layers.8.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.4.mlp.fc1.bias": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.dense.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.4.self_attn.dense.bias": "model-00004-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.8.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.4.input_layernorm.bias": "model-00004-of-00005.safetensors", "model.layers.3.mlp.fc2.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.fc2.bias": "model-00004-of-00005.safetensors", "model.layers.3.mlp.fc1.weight": "model-00005-of-00005.safetensors", "model.layers.3.mlp.fc1.bias": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.dense.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.dense.bias": "model-00005-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.3.input_layernorm.bias": "model-00005-of-00005.safetensors", "model.layers.2.mlp.fc2.weight": "model-00005-of-00005.safetensors", "model.layers.2.mlp.fc2.bias": "model-00005-of-00005.safetensors", "model.layers.2.mlp.fc1.weight": "model-00005-of-00005.safetensors", "model.layers.2.mlp.fc1.bias": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.dense.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.dense.bias": "model-00005-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.2.input_layernorm.bias": "model-00005-of-00005.safetensors", "model.layers.1.mlp.fc2.weight": "model-00005-of-00005.safetensors", "model.layers.1.mlp.fc2.bias": "model-00005-of-00005.safetensors", "model.layers.1.mlp.fc1.weight": "model-00005-of-00005.safetensors", "model.layers.1.mlp.fc1.bias": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.dense.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.dense.bias": "model-00005-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.1.input_layernorm.bias": "model-00005-of-00005.safetensors", "model.layers.0.mlp.fc2.weight": "model-00005-of-00005.safetensors", "model.layers.0.mlp.fc2.bias": "model-00005-of-00005.safetensors", "model.layers.0.mlp.fc1.weight": "model-00005-of-00005.safetensors", "model.layers.0.mlp.fc1.bias": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.dense.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.dense.bias": "model-00005-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.0.input_layernorm.bias": "model-00005-of-00005.safetensors", "model.embed_tokens.weight": "model-00005-of-00005.safetensors", "model.final_layernorm.weight": "model-00005-of-00005.safetensors", "model.final_layernorm.bias": "model-00005-of-00005.safetensors", "lm_head.weight": "model-00005-of-00005.safetensors", "lm_head.bias": "model-00005-of-00005.safetensors", "model.layers.55.mlp.fc2.weight": "model-00005-of-00005.safetensors", "model.layers.55.mlp.fc2.bias": "model-00005-of-00005.safetensors", "model.layers.55.mlp.fc1.weight": "model-00005-of-00005.safetensors", "model.layers.55.mlp.fc1.bias": "model-00005-of-00005.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.55.self_attn.dense.weight": "model-00005-of-00005.safetensors", "model.layers.55.self_attn.dense.bias": "model-00005-of-00005.safetensors", "model.layers.55.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.55.input_layernorm.bias": "model-00005-of-00005.safetensors", "model.layers.54.mlp.fc2.weight": "model-00005-of-00005.safetensors", "model.layers.54.mlp.fc2.bias": "model-00005-of-00005.safetensors", "model.layers.54.mlp.fc1.weight": "model-00005-of-00005.safetensors", "model.layers.54.mlp.fc1.bias": "model-00005-of-00005.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.54.self_attn.dense.weight": "model-00005-of-00005.safetensors", "model.layers.54.self_attn.dense.bias": "model-00005-of-00005.safetensors", "model.layers.54.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.54.input_layernorm.bias": "model-00005-of-00005.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
319
+ "clean_up_tokenization_spaces": true,
320
+ "eos_token": "<|endoftext|>",
321
+ "model_max_length": 2048,
322
+ "pad_token": "<|endoftext|>",
323
+ "tokenizer_class": "CodeGenTokenizer",
324
+ "unk_token": "<|endoftext|>"
325
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff