powermove72 commited on
Commit
23e70d0
1 Parent(s): c00499d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - powermove72/Elysium-Omni-Itt-11b
7
+ - powermove72/SoMix2-xb
8
+ base_model:
9
+ - powermove72/Elysium-Omni-Itt-11b
10
+ - powermove72/SoMix2-xb
11
+ ---
12
+
13
+ # Elysium-Omni-11b
14
+
15
+ Elysium-Omni-11b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [powermove72/Elysium-Omni-Itt-11b](https://huggingface.co/powermove72/Elysium-Omni-Itt-11b)
17
+ * [powermove72/SoMix2-xb](https://huggingface.co/powermove72/SoMix2-xb)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ models:
23
+ - model: powermove72/Elysium-Omni-Itt-11b
24
+ parameters:
25
+ weight: 0.8
26
+ - model: powermove72/SoMix2-xb
27
+ parameters:
28
+ weight: 0.2
29
+ merge_method: linear
30
+ tokenizer_source: union
31
+ dtype: float16
32
+ ```
33
+
34
+ ## 💻 Usage
35
+
36
+ ```python
37
+ !pip install -qU transformers accelerate
38
+
39
+ from transformers import AutoTokenizer
40
+ import transformers
41
+ import torch
42
+
43
+ model = "powermove72/Elysium-Omni-11b"
44
+ messages = [{"role": "user", "content": "What is a large language model?"}]
45
+
46
+ tokenizer = AutoTokenizer.from_pretrained(model)
47
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
48
+ pipeline = transformers.pipeline(
49
+ "text-generation",
50
+ model=model,
51
+ torch_dtype=torch.float16,
52
+ device_map="auto",
53
+ )
54
+
55
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
56
+ print(outputs[0]["generated_text"])
57
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "powermove72/SoMix2-xb",
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": "float16",
23
+ "transformers_version": "4.41.2",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: powermove72/Elysium-Omni-Itt-11b
4
+ parameters:
5
+ weight: 0.8
6
+ - model: powermove72/SoMix2-xb
7
+ parameters:
8
+ weight: 0.2
9
+ merge_method: linear
10
+ tokenizer_source: union
11
+ dtype: float16
12
+
model-00001-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8706437f9667d62980382b77fefe43b361541c2dcbc6574fd439516fbd452434
3
+ size 960521544
model-00002-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2672c29f3e91a04794bfb19e64d205802d4609f88e3b8630ac8bbe42df118454
3
+ size 989890704
model-00003-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f3373c08cfdf3d01de9186b915a7650026ec991d6eeb7af73724d2716996f09
3
+ size 989890712
model-00004-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1786cec5da07ae114a8540e0d8fc7c6c21284e2576a11cc804c1b00b4bac19d3
3
+ size 998287736
model-00005-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03e7509c73ddb6b0b4ea307b89c48e393d148a9f219897a8faa04169caaffbe
3
+ size 947956192
model-00006-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5618ce05c9ae806931280b77d06badd5908b608d9c796f63b9f61a6e9bbc00d0
3
+ size 989890704
model-00007-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8bb1add534dd1ac2593ec85951970a3fa12addf876d07106028f26c39a82cb5
3
+ size 989890704
model-00008-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:affed12fbb4649b32c01c007612e70f5d4623dbd8a3f1095d271d51cbbf3f5bc
3
+ size 998287736
model-00009-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b98f662a5903dac1d4022b3c9594f60bb0b81c32a644b8df02cd191b8eb611f
3
+ size 947956192
model-00010-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:812e84aca0fe21bdef118330e9c8dc3d78f87efd6d67d17597c22db524a87f49
3
+ size 989890712
model-00011-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fdf8478c68d408ca3a64aeb7af5227eb9c91a6e4a64ad3d0c1433bf66e0708d
3
+ size 989890704
model-00012-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4252bbd032a70c2b4584a04ee0a6c0f7ef92247f16c5a44bfa362965fc960504
3
+ size 998287736
model-00013-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4104fbeff19fb660c5098c8379d6b163a558567c3459338556bb3a7d1d2ea8fb
3
+ size 947956192
model-00014-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71e75d13681a4696cd49a6bc6b1f6762cfab19e4b7e95b58261ab54eeb9555b
3
+ size 989890712
model-00015-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772a348b61ca5ef15039a8c7fb40dee817cd5b6186e93beb591e26a29a22ad42
3
+ size 989890712
model-00016-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccb50d7c276eb59183d129f5e3bc7772433c6a29e96b65e5b1dec74a8d714fb
3
+ size 998287736
model-00017-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec11b3eee4a1a1c91885fd4e13cc3dc26bd18cd36b791916326e29f393327b5
3
+ size 947956192
model-00018-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfabbba31712ca87c64d58d922298e262fa9f2cec5f2bc707bd707170ce1757
3
+ size 989890712
model-00019-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f705e6d389777457e4e8337cb22fabe5d8f0d38f6c3b49d1e49905a3dd8a958b
3
+ size 989890712
model-00020-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50aa664456b4810d8042fe30aee88386baea228251f59416e66b367bb219448
3
+ size 998287736
model-00021-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd98d0f76a08e5bfa8a39602835100fc76b395f9e6499543d4bff907a3d6136
3
+ size 947956184
model-00022-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1091a629142577afe42ec13664a43dfbbdd885bfbacdb1795af79e03cec2782f
3
+ size 989890688
model-00023-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f90fe8e4f596fafb948a6f3eb9a1be91c5a4a7efc2150b03e0b6774251b1853
3
+ size 755009424
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 22335496192}, "weight_map": {"lm_head.weight": "model-00001-of-00023.safetensors", "model.embed_tokens.weight": "model-00001-of-00023.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00023.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.42.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.44.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.norm.weight": "model-00023-of-00023.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "truncation_side": "left",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }