LunaticPython161 commited on
Commit
bfd3224
1 Parent(s): b8387f7

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - frankenmoe
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
10
+ - LunaticPython161/CyberWitch-7B
11
+ base_model:
12
+ - cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
13
+ - LunaticPython161/CyberWitch-7B
14
+ ---
15
+
16
+ # Lily-MoE-2x7b
17
+
18
+ Lily-MoE-2x7b is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
19
+ * [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)
20
+ * [LunaticPython161/CyberWitch-7B](https://huggingface.co/LunaticPython161/CyberWitch-7B)
21
+
22
+ ## 🧩 Configuration
23
+
24
+ ```yaml
25
+ base_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
26
+ gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
27
+ dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
28
+ experts:
29
+ - source_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
30
+ positive_prompts:
31
+ - "chat"
32
+ - "assistant"
33
+ - "tell me"
34
+ - "explain"
35
+ - "code"
36
+ - "programming"
37
+ - source_model: LunaticPython161/CyberWitch-7B
38
+ positive_prompts:
39
+ - "solve"
40
+ - "count"
41
+ - "math"
42
+ - "mathematics"
43
+ - "algorithm"
44
+ - "cypher"
45
+ - "cybersecurity"
46
+ - "penetration testing"
47
+ - "red team"
48
+ - "blue team"
49
+ - "hacking"
50
+ ```
51
+
52
+ ## 💻 Usage
53
+
54
+ ```python
55
+ !pip install -qU transformers bitsandbytes accelerate
56
+
57
+ from transformers import AutoTokenizer
58
+ import transformers
59
+ import torch
60
+
61
+ model = "LunaticPython161/Lily-MoE-2x7b"
62
+
63
+ tokenizer = AutoTokenizer.from_pretrained(model)
64
+ pipeline = transformers.pipeline(
65
+ "text-generation",
66
+ model=model,
67
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
68
+ )
69
+
70
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
71
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
72
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
73
+ print(outputs[0]["generated_text"])
74
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|im_start|>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
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": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 2,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.37.2",
28
+ "use_cache": false,
29
+ "vocab_size": 32001
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
3
+ gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
4
+ dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
5
+ experts:
6
+ - source_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
7
+ positive_prompts:
8
+ - "chat"
9
+ - "assistant"
10
+ - "tell me"
11
+ - "explain"
12
+ - "code"
13
+ - "programming"
14
+ - source_model: LunaticPython161/CyberWitch-7B
15
+ positive_prompts:
16
+ - "solve"
17
+ - "count"
18
+ - "math"
19
+ - "mathematics"
20
+ - "algorithm"
21
+ - "cypher"
22
+ - "cybersecurity"
23
+ - "penetration testing"
24
+ - "red team"
25
+ - "blue team"
26
+ - "hacking"
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867d597c922d9f9e6dbc2cde609d0d1a247dc6ce4bb043fadc7535d6d9120e5d
3
+ size 9919830088
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91536055330c40c8489ff72f1f11065cdaf5d697c8882a900ece554ba6e17341
3
+ size 9982454736
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf04ef9463e480c2e157c86c3ccbb2141363384a735f12d55d6398aef198871
3
+ size 5856061008
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.norm.weight": "model-00001-of-00003.safetensors", "lm_head.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff