arvindanand commited on
Commit
67a6ff4
0 Parent(s):

Duplicate from arvindanand/validate2

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - WizardLM/WizardCoder-33B-V1.1
7
+ - codefuse-ai/CodeFuse-DeepSeek-33B
8
+ - deepseek-ai/deepseek-coder-33b-instruct
9
+
10
+ base_model:
11
+ - deepseek-ai/deepseek-coder-33b-instruct
12
+
13
+ license: apache-2.0
14
+ ---
15
+
16
+ # ValidateAI-2-33B-AT
17
+
18
+ ValidateAI-2-33B-AT is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
19
+ * [deepseek-ai/deepseek-coder-33b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct)
20
+ * [WizardLM/WizardCoder-33B-V1.1](https://huggingface.co/WizardLM/WizardCoder-33B-V1.1)
21
+ * [codefuse-ai/CodeFuse-DeepSeek-33B](https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B)
22
+ *
23
+
24
+ ## 🧩 Configuration
25
+
26
+ ```yaml
27
+ models:
28
+ - model: WizardLM_WizardCoder-33B-V1.1
29
+ parameters:
30
+ density: 1
31
+ weight: .5
32
+ - model: codefuse-ai_CodeFuse-DeepSeek-33B
33
+ parameters:
34
+ density: 1
35
+ weight: .5
36
+ merge_method: ties
37
+ base_model: deepseek-ai_deepseek-coder-33b-instruct
38
+ parameters:
39
+ normalize: true
40
+ int8_mask: true
41
+ dtype: float16
42
+ ```
43
+
44
+ ## 💻 Usage
45
+
46
+ ```python
47
+ !pip install -qU transformers accelerate
48
+
49
+ from transformers import AutoTokenizer
50
+ import transformers
51
+ import torch
52
+
53
+ model = "arvindanand/ValidateAI-2"
54
+ messages = [{"role": "user", "content": "What is a large language model?"}]
55
+
56
+ tokenizer = AutoTokenizer.from_pretrained(model)
57
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
58
+ pipeline = transformers.pipeline(
59
+ "text-generation",
60
+ model=model,
61
+ torch_dtype=torch.float16,
62
+ device_map="auto",
63
+ )
64
+
65
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
66
+ print(outputs[0]["generated_text"])
67
+ ```
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "arvindanand/validate2",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "eos_token_id": 32021,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 7168,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 19200,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 56,
17
+ "num_hidden_layers": 62,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "factor": 4.0,
23
+ "type": "linear"
24
+ },
25
+ "rope_theta": 100000,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.36.2",
29
+ "use_cache": true,
30
+ "vocab_size": 32256
31
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32013,
4
+ "eos_token_id": 32021,
5
+ "transformers_version": "4.34.1"
6
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2ff7e378160a53b428c8d536158962c8fec376bbe7d64c8940c3915363d56d
3
+ size 9733135344
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47bfe0e8fb8d6468a6d18cf5ad1553abf6edae81919ba0f34ded74345d59141
3
+ size 9821259272
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c460aefc30e93a9da590b47d8c894da5cd9fe36753efb921ba876ba05d1f47f
3
+ size 9821230376
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c60c1b5b5922a64b402ed6e58fc497f89aa5d6ba2cb118fdff19fccba6c1758
3
+ size 9821230376
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c122d675bb58429ed3a2a6d27514e19089624ae3479a92421b83b2349a17ac1c
3
+ size 9938685576
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ca12847a50c003b20566d9a0f14ea3fed9f4028e9e4ef6d5d30536c4fb0a43
3
+ size 9938685568
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a53ff6b6207821146e02d968030330b22fad5f59475684e054549e1b1c62bd
3
+ size 7611821168
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors"}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|begin▁of▁sentence|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|EOT|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 16384,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<|end▁of▁sentence|>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "sp_model_kwargs": {},
32
+ "unk_token": null,
33
+ "tokenizer_class": "LlamaTokenizerFast",
34
+ "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}"
35
+ }