aipib commited on
Commit
f52714d
1 Parent(s): a5a5cd1

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - aipib/Tinyllama-moe3
7
+ - aipib/karasu-moe
8
+ base_model:
9
+ - aipib/Tinyllama-moe3
10
+ - aipib/karasu-moe
11
+ ---
12
+
13
+ # karasu-moexdareties
14
+
15
+ karasu-moexdareties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [aipib/Tinyllama-moe3](https://huggingface.co/aipib/Tinyllama-moe3)
17
+ * [aipib/karasu-moe](https://huggingface.co/aipib/karasu-moe)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - layer_range: [0, 22]
25
+ model: aipib/Tinyllama-moe3
26
+ parameters:
27
+ density: [1, 0.7, 0.1]
28
+ weight: 1.0
29
+ - layer_range: [0, 22]
30
+ model: aipib/karasu-moe
31
+ parameters:
32
+ density: 0.33
33
+ weight:
34
+ - filter: mlp
35
+ value: 0.5
36
+ - value: 0
37
+ merge_method: dare_ties
38
+ base_model: aipib/Tinyllama-moe3
39
+ parameters:
40
+ normalize: true
41
+ int8_mask: true
42
+ dtype: bfloat16
43
+ ```
44
+
45
+ ## 💻 Usage
46
+
47
+ ```python
48
+ !pip install -qU transformers accelerate
49
+
50
+ from transformers import AutoTokenizer
51
+ import transformers
52
+ import torch
53
+
54
+ model = "aipib/karasu-moexdareties"
55
+ messages = [{"role": "user", "content": "What is a large language model?"}]
56
+
57
+ tokenizer = AutoTokenizer.from_pretrained(model)
58
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
59
+ pipeline = transformers.pipeline(
60
+ "text-generation",
61
+ model=model,
62
+ torch_dtype=torch.float16,
63
+ device_map="auto",
64
+ )
65
+
66
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
67
+ print(outputs[0]["generated_text"])
68
+ ```
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aipib/Tinyllama-moe3",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "router_aux_loss_coef": 0.001,
27
+ "router_jitter_noise": 0.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.40.1",
32
+ "use_cache": true,
33
+ "vocab_size": 32000
34
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - layer_range: [0, 22]
5
+ model: aipib/Tinyllama-moe3
6
+ parameters:
7
+ density: [1, 0.7, 0.1]
8
+ weight: 1.0
9
+ - layer_range: [0, 22]
10
+ model: aipib/karasu-moe
11
+ parameters:
12
+ density: 0.33
13
+ weight:
14
+ - filter: mlp
15
+ value: 0.5
16
+ - value: 0
17
+ merge_method: dare_ties
18
+ base_model: aipib/Tinyllama-moe3
19
+ parameters:
20
+ normalize: true
21
+ int8_mask: true
22
+ dtype: bfloat16
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b768cb57c7af9d3d52a90d13521a771b4c45ae4687e439f10473c8b481adcb0d
3
+ size 1992492416
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7e0bc85e3e2e8af942cc43d07fd64e4716bd1070bc0d62c2f693124ed36773
3
+ size 1730352272
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 3722809344}, "weight_map": {"lm_head.weight": "model-00001-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "max_length": null,
36
+ "model_max_length": 2048,
37
+ "pad_to_multiple_of": null,
38
+ "pad_token": "<s>",
39
+ "pad_token_type_id": 0,
40
+ "padding_side": "left",
41
+ "sp_model_kwargs": {},
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false
45
+ }