vgel commited on
Commit
b3edaf4
1 Parent(s): 83667de

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - mistralai/Mistral-7B-v0.1
7
+ - mistralai/Mistral-7B-v0.1
8
+ - mistralai/Mistral-7B-v0.1
9
+ base_model:
10
+ - mistralai/Mistral-7B-v0.1
11
+ - mistralai/Mistral-7B-v0.1
12
+ - mistralai/Mistral-7B-v0.1
13
+ ---
14
+
15
+ # mistral-7b-selfmerge-0-32-8-24-8-32
16
+
17
+ mistral-7b-selfmerge-0-32-8-24-8-32 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
18
+ * [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
19
+ * [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
20
+ * [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
21
+
22
+ ## 🧩 Configuration
23
+
24
+ ```yaml
25
+ slices:
26
+ - sources:
27
+ - model: mistralai/Mistral-7B-v0.1
28
+ layer_range: [0, 32]
29
+ - sources:
30
+ - model: mistralai/Mistral-7B-v0.1
31
+ layer_range: [8, 24]
32
+ - sources:
33
+ - model: mistralai/Mistral-7B-v0.1
34
+ layer_range: [8, 32]
35
+ merge_method: passthrough
36
+ dtype: bfloat16
37
+ ```
38
+
39
+ ## 💻 Usage
40
+
41
+ ```python
42
+ !pip install -qU transformers accelerate
43
+
44
+ from transformers import AutoTokenizer
45
+ import transformers
46
+ import torch
47
+
48
+ model = "vgel/mistral-7b-selfmerge-0-32-8-24-8-32"
49
+ messages = [{"role": "user", "content": "What is a large language model?"}]
50
+
51
+ tokenizer = AutoTokenizer.from_pretrained(model)
52
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
53
+ pipeline = transformers.pipeline(
54
+ "text-generation",
55
+ model=model,
56
+ torch_dtype=torch.float16,
57
+ device_map="auto",
58
+ )
59
+
60
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
61
+ print(outputs[0]["generated_text"])
62
+ ```
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 72,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.35.2",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: mistralai/Mistral-7B-v0.1
5
+ layer_range: [0, 32]
6
+ - sources:
7
+ - model: mistralai/Mistral-7B-v0.1
8
+ layer_range: [8, 24]
9
+ - sources:
10
+ - model: mistralai/Mistral-7B-v0.1
11
+ layer_range: [8, 32]
12
+ merge_method: passthrough
13
+ dtype: bfloat16
model-00001-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e417b3aaebf613df431e77ede6f6cccf4af5c46ba696171080a41ac108671ed
3
+ size 1912656688
model-00002-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a4ee7a37109cec2fd09981033d875cd9e54dba29f468b8ccf6f99ba3434a261
3
+ size 1895878296
model-00003-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7d691932bbedddca25ad6f5b876becf654acce6fb1fff2dadc34d0f8e75962c
3
+ size 1912706528
model-00004-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a28ff6953a8339dacfd052f7431ce37d7f65b20957bcf8ed97f6f7e6e4100ea
3
+ size 1895878296
model-00005-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abfd7b080aee3f9962dd36e23df0dc0f357f441ca02176d60f1c3c8a2c28c9e8
3
+ size 1912706520
model-00006-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05b467e19fce7a90eb423ab32e4c94a880ac9603fe6e155af61b8921267f534
3
+ size 1895878296
model-00007-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb43d16bfcf0c45be6395a60e0524d94a5cf8ba99d816370f7e67004e51777ae
3
+ size 1912706520
model-00008-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca056f14e506d6ea4da3df497f38627f7269869c17523ababbb2d46420d6011c
3
+ size 1895878296
model-00009-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1fe19f58c44adfdbf23aa7704f1b6bec3c6444f871d8f6c8acc7006afa95f7d
3
+ size 1996567672
model-00010-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a61d1715cecbb4b6a2843861b9ea7113f7675e3517a4250d6127313e05509228
3
+ size 1895920256
model-00011-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b084ebf5c59d2df14d18e0f83219028a335d382331c0c3ade6e4b9ba64f8b5
3
+ size 1979789736
model-00012-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c2322163e66406cc4f444fa4cb1ba1b5ffd5ee59b0ecf90bec6d2b9dd5f0d49
3
+ size 1950403936
model-00013-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380000ee5ac9348925cdbf8dfed2b06c1f3ad3d2367286339341c7d64e3793c6
3
+ size 1979798080
model-00014-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b028e9369a01ab712b53c5c5fa9565f80d4ffbee61146d2a22a2bc9476b1e8
3
+ size 1912689896
model-00015-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe8687a0357d019903a074907479ec10800128305ee04887a38d8b440f7c6dc
3
+ size 1979781456
model-00016-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:851bf63c1e063f417e42843e248987626b987105972fca7b59d9cec41d934589
3
+ size 1946243984
model-00017-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc77630376f8f437c7970f64a94bbd9c68db923af1dedc668c0eeb15500f97b1
3
+ size 1057015496
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.62.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00001-of-00017.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00001-of-00017.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00017.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00017.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00017.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00017.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00017.safetensors", "model.layers.61.input_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00017.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00017.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00002-of-00017.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00017.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00017.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00002-of-00017.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00017.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00017.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00002-of-00017.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00017.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00017.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00002-of-00017.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00017.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00017.safetensors", "model.layers.60.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00017.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00017.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00017.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00017.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.43.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00017.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00017.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00017.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00017.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00017.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00017.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.42.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00017.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00003-of-00017.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00004-of-00017.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00017.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00017.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00004-of-00017.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00017.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00017.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00004-of-00017.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00017.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00017.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00004-of-00017.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00017.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00017.safetensors", "model.layers.57.input_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.41.input_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00017.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00017.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00017.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00004-of-00017.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.56.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00017.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00017.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00017.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00017.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00017.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00017.safetensors", "model.layers.55.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00017.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00005-of-00017.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00017.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00017.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00017.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00017.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00017.safetensors", "model.layers.54.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00017.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00017.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00017.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.53.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00017.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00017.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00017.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00008-of-00017.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00017.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00008-of-00017.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00017.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00017.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00017.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00017.safetensors", "model.layers.51.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00017.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00008-of-00017.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00017.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.10.input_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00009-of-00017.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00009-of-00017.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00017.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00017.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.49.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.48.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00017.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00017.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00017.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00017.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00017.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00017.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00017.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00017.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00017.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00011-of-00017.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00017.safetensors", "model.layers.6.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00017.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00017.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00017.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00011-of-00017.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00011-of-00017.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00017.safetensors", "model.layers.4.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00017.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00017.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00011-of-00017.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00017.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00017.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00017.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00017.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.2.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00012-of-00017.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.1.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00012-of-00017.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00012-of-00017.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00012-of-00017.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00012-of-00017.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00012-of-00017.safetensors", "model.layers.0.input_layernorm.weight": "model-00012-of-00017.safetensors", "model.embed_tokens.weight": "model-00012-of-00017.safetensors", "lm_head.weight": "model-00012-of-00017.safetensors", "model.norm.weight": "model-00012-of-00017.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00017.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00017.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00013-of-00017.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.71.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00013-of-00017.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00017.safetensors", "model.layers.70.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00017.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00017.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00017.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.69.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.29.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00014-of-00017.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00014-of-00017.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.68.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.28.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00014-of-00017.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00014-of-00017.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00017.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00014-of-00017.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00017.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00017.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00017.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00017.safetensors", "model.layers.67.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00017.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.66.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.26.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00017.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00015-of-00017.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00017.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00017.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00017.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00017.safetensors", "model.layers.65.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.25.input_layernorm.weight": "model-00015-of-00017.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00017.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.64.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00016-of-00017.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00017.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00016-of-00017.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00016-of-00017.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00016-of-00017.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00017.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00017.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00017.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00017.safetensors", "model.layers.63.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.23.input_layernorm.weight": "model-00016-of-00017.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00017-of-00017.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00017-of-00017.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00017.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00017-of-00017.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00017-of-00017.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00017.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00017-of-00017.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.62.input_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.46.input_layernorm.weight": "model-00017-of-00017.safetensors", "model.layers.22.input_layernorm.weight": "model-00017-of-00017.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": true,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": null,
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }