mvpmaster commited on
Commit
119afd4
1 Parent(s): 9ae5ef5

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
7
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
8
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
9
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
10
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
11
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
12
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
13
+ base_model:
14
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
15
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
16
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
17
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
18
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
19
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
20
+ - argilla/distilabeled-Marcoro14-7B-slerp-full
21
+ ---
22
+
23
+ # distilabeled-Marcoro14-12B-32k-slerp-full
24
+
25
+ distilabeled-Marcoro14-12B-32k-slerp-full is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
26
+ * [argilla/distilabeled-Marcoro14-7B-slerp-full](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp-full)
27
+ * [argilla/distilabeled-Marcoro14-7B-slerp-full](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp-full)
28
+ * [argilla/distilabeled-Marcoro14-7B-slerp-full](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp-full)
29
+ * [argilla/distilabeled-Marcoro14-7B-slerp-full](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp-full)
30
+ * [argilla/distilabeled-Marcoro14-7B-slerp-full](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp-full)
31
+ * [argilla/distilabeled-Marcoro14-7B-slerp-full](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp-full)
32
+ * [argilla/distilabeled-Marcoro14-7B-slerp-full](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp-full)
33
+
34
+ ## 🧩 Configuration
35
+
36
+ ```yaml
37
+ dtype: float16
38
+ merge_method: passthrough
39
+ slices:
40
+ - sources:
41
+ - layer_range: [0, 8]
42
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
43
+ - sources:
44
+ - layer_range: [4, 12]
45
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
46
+ - sources:
47
+ - layer_range: [8, 16]
48
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
49
+ - sources:
50
+ - layer_range: [12, 20]
51
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
52
+ - sources:
53
+ - layer_range: [16, 24]
54
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
55
+ - sources:
56
+ - layer_range: [20, 28]
57
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
58
+ - sources:
59
+ - layer_range: [24, 32]
60
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
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 = "mvpmaster/distilabeled-Marcoro14-12B-32k-slerp-full"
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
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "argilla/distilabeled-Marcoro14-7B-slerp-full",
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": 56,
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": "float16",
23
+ "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ dtype: float16
3
+ merge_method: passthrough
4
+ slices:
5
+ - sources:
6
+ - layer_range: [0, 8]
7
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
8
+ - sources:
9
+ - layer_range: [4, 12]
10
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
11
+ - sources:
12
+ - layer_range: [8, 16]
13
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
14
+ - sources:
15
+ - layer_range: [12, 20]
16
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
17
+ - sources:
18
+ - layer_range: [16, 24]
19
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
20
+ - sources:
21
+ - layer_range: [20, 28]
22
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
23
+ - sources:
24
+ - layer_range: [24, 32]
25
+ model: argilla/distilabeled-Marcoro14-7B-slerp-full
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4115324ba1aa539567be1403ab8db59fb97df4a3010364f648df346adf882c1
3
+ size 1979748192
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d822a4308169085100a725d33ff358fb4086a2f2473f4d8240908fe894ba6f0e
3
+ size 1979798024
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0add22cdd54c0f46c269acb368d533ae35889ad0963bf5143a777b4d00a9452a
3
+ size 1912689792
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d02ea7cea655eaa4a9644773f6ae88fe0f96de6433077637dc24f04d646c5b
3
+ size 1744900120
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa76df43a64bb3e2f81182843f6a905335d39bd461bb6c501be5d09b2211926
3
+ size 1889570424
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69aba1555afda159e46577ae813bf3f0c83efaaef1365cb2337e13816d438851
3
+ size 1996575968
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef32faa77f1b9ac261fe82a73c705344da7dc56134500a4e7ca0e948bb9bc695
3
+ size 1895911944
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c766afd9980a3873d54457ba1c59cfd0422e8eb0ec4f2625e7d49dea4a7c3b0d
3
+ size 1979781416
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a61a0de65c9bad82d8cd8a8ebbe4db7a1091cee3a173622d2d07d081f7d1c1
3
+ size 1979781432
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bfda82aca3ce12b3d0de41c3cb8b67402a145d907a9196beab984114059c19
3
+ size 1889645144
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500963cbf77593ec12d4329bc6e0487c562086fe09addd422029b9009c65f3e9
3
+ size 1979781432
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb49fbff5b3fc50a923237b1a0d6a76583dabd5d485b763a9c3ca1a757684bc
3
+ size 1979798040
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890eea9c2df1e60ef96d3c576f307b7106a448281a41edd5ccfeba08d1c5ca17
3
+ size 1744916768
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.embed_tokens.weight": "model-00005-of-00013.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00010-of-00013.safetensors", "lm_head.weight": "model-00010-of-00013.safetensors", "model.norm.weight": "model-00010-of-00013.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.55.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.46.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.45.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.48.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.44.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.42.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00013.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": true,
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": null,
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }