powermove72 commited on
Commit
1287240
1 Parent(s): 422b15c

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - viethq188/LeoScorpius-7B-Chat-DPO
7
+ - GreenNode/GreenNode-mini-7B-multilingual-v1olet
8
+ base_model:
9
+ - viethq188/LeoScorpius-7B-Chat-DPO
10
+ - GreenNode/GreenNode-mini-7B-multilingual-v1olet
11
+ ---
12
+
13
+ # GreenScorpius2-xb
14
+
15
+ GreenScorpius2-xb is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [viethq188/LeoScorpius-7B-Chat-DPO](https://huggingface.co/viethq188/LeoScorpius-7B-Chat-DPO)
17
+ * [GreenNode/GreenNode-mini-7B-multilingual-v1olet](https://huggingface.co/GreenNode/GreenNode-mini-7B-multilingual-v1olet)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - model: viethq188/LeoScorpius-7B-Chat-DPO
25
+ layer_range: [0, 26]
26
+ - sources:
27
+ - model: GreenNode/GreenNode-mini-7B-multilingual-v1olet
28
+ layer_range: [8, 32]
29
+ merge_method: passthrough
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/GreenScorpius2-xb"
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": "GreenNode/GreenNode-mini-7B-multilingual-v1olet",
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": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: viethq188/LeoScorpius-7B-Chat-DPO
5
+ layer_range: [0, 26]
6
+ - sources:
7
+ - model: GreenNode/GreenNode-mini-7B-multilingual-v1olet
8
+ layer_range: [8, 32]
9
+ merge_method: passthrough
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:aa1d80dfe12769e65a8d30e0ddbb993813d37622178c0687ce249361aadfaab4
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:ccb890bbe30ae5bcc40737781b21829972d3f3697e6c218bd83d9d958f0323b5
3
+ size 905995856
model-00003-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0159ed8e5e6267b4b159eacbc219158d13267cb318700d4ef8b77838732828
3
+ size 989890704
model-00004-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b11ddd5d0e9c82b6fc2fd137dd9029d7397fccdf3fc0210982ca6114c8e7ed7
3
+ size 998296048
model-00005-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9474332ac39f543d2980a65457a064bb783a866426372fc2cbbd989ed3a34c7
3
+ size 981502432
model-00006-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6222bdb8012a58ea7063da4be1d1f081dbe680ee95b0eef664e9b9481d808b69
3
+ size 922798672
model-00007-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:199ae525d8b4ba329696c2b09dc13660ec63feef2392601a7be7b948d4b6b356
3
+ size 989890712
model-00008-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a89af1485a8f6e1a708f1a34e59c6f0ae10107e5198a4a2c4e2a4ee00f238b9
3
+ size 989890712
model-00009-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698bab44e081befc7998baeb8f2dbf5b4b12497c14893b95d140b24b68cde28a
3
+ size 989890712
model-00010-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c867f9cb592a87391c45d3390952e5bc70c2d0b6ef329959f6a255af32bcae7
3
+ size 989890712
model-00011-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997fa70686b6d6756e304ef44c1ab528aaf9292951c39d7043ab8905c0d00815
3
+ size 956353224
model-00012-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee5017d64db5773bb67e6f9377356ec362efe655bf94340ef811199e8b76461
3
+ size 989890712
model-00013-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d0ef5895c6e1dc48c8d8d4a62722b4af4f18d1acc7bf1b87ea62ef3355dae8
3
+ size 989890712
model-00014-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2bbc7a9875364bf5f9d2dcc2b87679cbfc2ee72333414cc12bc50b36b8814a0
3
+ size 989890712
model-00015-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590409de49f0f5bbc1287cb39b2b4d2756ecc2698e8fd596ef4b386b62065b56
3
+ size 989890704
model-00016-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4939d34af5e4e69f94e61798b335a4337bdff9863f64872fa70e844402a4070d
3
+ size 998296048
model-00017-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb780286c7f4f74156f7d95f3f0b1236f4af98d5ae4616f6878098057618dad
3
+ size 989891160
model-00018-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217b9e615c49af7db854a71c8596ed89b3a4ba80b87180a37ae3f2d78ffa1e1f
3
+ size 914401640
model-00019-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2348f48c4758f666d9a0b0b37acd1b65c5567ef64a6bc7ed92e398f1cf1c5d
3
+ size 989890704
model-00020-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa5bf466e2527f7aa7143b511238b4ab3a19e9d4e731deb1e5e40c30c0328de
3
+ size 989890688
model-00021-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b761bfa2287b081dc823391fd0bb83364ee384d629b109e18de9d6b6efe770b6
3
+ size 998287720
model-00022-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e510c1aacc5c9824dff029ee4dba791ed775e4524e4824f51e304e4418cf8a
3
+ size 947964480
model-00023-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14159ab026f8b3eacc3f36cff3002cc02849b499a29de335929a7eced74fa050
3
+ size 872441752
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.28.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.49.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00020-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-00021-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-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.26.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.27.self_attn.v_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 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_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
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": true,
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": null,
41
+ "padding_side": "left",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "split_special_tokens": false,
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }