babybirdprd commited on
Commit
e9a7074
1 Parent(s): 364f9a4

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - yam-peleg/Experiment26-7B
7
+ - yam-peleg/Experiment26-7B
8
+ - yam-peleg/Experiment26-7B
9
+ - yam-peleg/Experiment26-7B
10
+ - yam-peleg/Experiment26-7B
11
+ - yam-peleg/Experiment26-7B
12
+ - yam-peleg/Experiment26-7B
13
+ - yam-peleg/Experiment26-7B
14
+ - yam-peleg/Experiment26-7B
15
+ - yam-peleg/Experiment26-7B
16
+ base_model:
17
+ - yam-peleg/Experiment26-7B
18
+ - yam-peleg/Experiment26-7B
19
+ - yam-peleg/Experiment26-7B
20
+ - yam-peleg/Experiment26-7B
21
+ - yam-peleg/Experiment26-7B
22
+ - yam-peleg/Experiment26-7B
23
+ - yam-peleg/Experiment26-7B
24
+ - yam-peleg/Experiment26-7B
25
+ - yam-peleg/Experiment26-7B
26
+ - yam-peleg/Experiment26-7B
27
+ ---
28
+
29
+ # Experiment26-7B-passthrough-10slice
30
+
31
+ Experiment26-7B-passthrough-10slice is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
32
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
33
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
34
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
35
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
36
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
37
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
38
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
39
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
40
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
41
+ * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
42
+
43
+ ## 🧩 Configuration
44
+
45
+ ```yaml
46
+ slices:
47
+ - sources:
48
+ - model: yam-peleg/Experiment26-7B
49
+ layer_range: [0, 5]
50
+ - sources:
51
+ - model: yam-peleg/Experiment26-7B
52
+ layer_range: [3, 8]
53
+ - sources:
54
+ - model: yam-peleg/Experiment26-7B
55
+ layer_range: [6, 11]
56
+ - sources:
57
+ - model: yam-peleg/Experiment26-7B
58
+ layer_range: [9, 14]
59
+ - sources:
60
+ - model: yam-peleg/Experiment26-7B
61
+ layer_range: [12, 17]
62
+ - sources:
63
+ - model: yam-peleg/Experiment26-7B
64
+ layer_range: [15, 20]
65
+ - sources:
66
+ - model: yam-peleg/Experiment26-7B
67
+ layer_range: [18, 23]
68
+ - sources:
69
+ - model: yam-peleg/Experiment26-7B
70
+ layer_range: [21, 26]
71
+ - sources:
72
+ - model: yam-peleg/Experiment26-7B
73
+ layer_range: [24, 29]
74
+ - sources:
75
+ - model: yam-peleg/Experiment26-7B
76
+ layer_range: [27, 32]
77
+ merge_method: passthrough
78
+ dtype: bfloat16
79
+ ```
80
+
81
+ ## 💻 Usage
82
+
83
+ ```python
84
+ !pip install -qU transformers accelerate
85
+
86
+ from transformers import AutoTokenizer
87
+ import transformers
88
+ import torch
89
+
90
+ model = "babybirdprd/Experiment26-7B-passthrough-10slice"
91
+ messages = [{"role": "user", "content": "What is a large language model?"}]
92
+
93
+ tokenizer = AutoTokenizer.from_pretrained(model)
94
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
95
+ pipeline = transformers.pipeline(
96
+ "text-generation",
97
+ model=model,
98
+ torch_dtype=torch.float16,
99
+ device_map="auto",
100
+ )
101
+
102
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
103
+ print(outputs[0]["generated_text"])
104
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "yam-peleg/Experiment26-7B",
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": 50,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.38.1",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: yam-peleg/Experiment26-7B
5
+ layer_range: [0, 5]
6
+ - sources:
7
+ - model: yam-peleg/Experiment26-7B
8
+ layer_range: [3, 8]
9
+ - sources:
10
+ - model: yam-peleg/Experiment26-7B
11
+ layer_range: [6, 11]
12
+ - sources:
13
+ - model: yam-peleg/Experiment26-7B
14
+ layer_range: [9, 14]
15
+ - sources:
16
+ - model: yam-peleg/Experiment26-7B
17
+ layer_range: [12, 17]
18
+ - sources:
19
+ - model: yam-peleg/Experiment26-7B
20
+ layer_range: [15, 20]
21
+ - sources:
22
+ - model: yam-peleg/Experiment26-7B
23
+ layer_range: [18, 23]
24
+ - sources:
25
+ - model: yam-peleg/Experiment26-7B
26
+ layer_range: [21, 26]
27
+ - sources:
28
+ - model: yam-peleg/Experiment26-7B
29
+ layer_range: [24, 29]
30
+ - sources:
31
+ - model: yam-peleg/Experiment26-7B
32
+ layer_range: [27, 32]
33
+ merge_method: passthrough
34
+ dtype: bfloat16
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9daf6c69976795ba3c88cd16d60a1612309712cb0c16ea31873082749b0c5a04
3
+ size 1946210752
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8037e3db34893ba589117f7bdf6861321b0c6e3175df3e92f9beee3b5134986
3
+ size 1979781424
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57fe1965fd6a68380be86b3887ad637fb3773dbf00d41f18ca42397feea5110
3
+ size 1946243944
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e45849c7028d7d0c2312852addcd0e56ac56713a9d6a327e3ad5e15a8f8a384
3
+ size 1973473600
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543121f823b2f7002a4847682bb537bd75f1743768fc8115307a914c5e66e22d
3
+ size 1946243984
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058f0a2828acb3c8509fb53375b33ce8695a8a8f01a57c448681a8642fa0eaf2
3
+ size 1895878304
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b84e9f2b48b366fb2fcdf2bb0b92f41f5d2fcd4487f57fcdeef76989dad74f
3
+ size 1946244008
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db9295ef52fcc972912ed18bab025b79612e1f2887debe1da8a3d33f9ff7eac
3
+ size 1946243992
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eec5c3b20eaf68dacbbf42f7d3b921383533fb843aed9b41714d30cd4e7be7b
3
+ size 1923182656
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1408f53a81267fd7cead17cb947705d1fd3f9766165bdd087b752a5dc040b6c9
3
+ size 1946243984
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f03c13d9cf1f95d50a052d9d6d0851355daffe2cda8febf0349edd2957b6b338
3
+ size 1979781464
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:030d24483a1518fab7ce49e599081f1974d862bba138a6baa25c61a8904ddecd
3
+ size 906020784
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.embed_tokens.weight": "model-00004-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00012.safetensors", "lm_head.weight": "model-00009-of-00012.safetensors", "model.norm.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00012.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
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.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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 32768,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }