Haleshot commited on
Commit
e1aa198
1 Parent(s): 2104b93

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - AI-MO/NuminaMath-7B-TIR
4
+ - deepseek-ai/DeepSeek-Prover-V1.5-RL
5
+ license: apache-2.0
6
+ tags:
7
+ - moe
8
+ - frankenmoe
9
+ - merge
10
+ - mergekit
11
+ - lazymergekit
12
+ - AI-MO/NuminaMath-7B-TIR
13
+ - deepseek-ai/DeepSeek-Prover-V1.5-RL
14
+ ---
15
+
16
+ # Mathmate-7B-dare-ties
17
+
18
+ Mathmate-7B-dare-ties is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
19
+ * [AI-MO/NuminaMath-7B-TIR](https://huggingface.co/AI-MO/NuminaMath-7B-TIR)
20
+ * [deepseek-ai/DeepSeek-Prover-V1.5-RL](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1.5-RL)
21
+
22
+ ## 🧩 Configuration
23
+
24
+ ```yaml
25
+ base_model: AI-MO/NuminaMath-7B-TIR
26
+ gate_mode: hidden
27
+ dtype: bfloat16
28
+ experts:
29
+ - source_model: AI-MO/NuminaMath-7B-TIR
30
+ positive_prompts:
31
+ - "This model is good at solving math questions at high school level and generating python code for the same"
32
+ # - source_model: Qwen/Qwen2-Math-7B-Instruct
33
+ # positive_prompts:
34
+ # - "This model is really good at solving college level math to olympiad level questions"
35
+ - source_model: deepseek-ai/DeepSeek-Prover-V1.5-RL
36
+ positive_prompts:
37
+ - "This model is good at formal theorem providing math problems"
38
+ ```
39
+
40
+ ## 💻 Usage
41
+
42
+ ```python
43
+ !pip install -qU transformers bitsandbytes accelerate
44
+
45
+ from transformers import AutoTokenizer
46
+ import transformers
47
+ import torch
48
+
49
+ model = "Haleshot/Mathmate-7B-dare-ties"
50
+
51
+ tokenizer = AutoTokenizer.from_pretrained(model)
52
+ pipeline = transformers.pipeline(
53
+ "text-generation",
54
+ model=model,
55
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
56
+ )
57
+
58
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
59
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
60
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
61
+ print(outputs[0]["generated_text"])
62
+ ```
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AI-MO/NuminaMath-7B-TIR",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 100000,
9
+ "eos_token_id": 100001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "mixtral",
18
+ "num_attention_heads": 32,
19
+ "num_experts_per_tok": 2,
20
+ "num_hidden_layers": 30,
21
+ "num_key_value_heads": 32,
22
+ "num_local_experts": 2,
23
+ "output_router_logits": false,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_scaling": null,
27
+ "rope_theta": 10000.0,
28
+ "router_aux_loss_coef": 0.001,
29
+ "router_jitter_noise": 0.0,
30
+ "sliding_window": null,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.44.2",
34
+ "use_cache": true,
35
+ "vocab_size": 102400
36
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: AI-MO/NuminaMath-7B-TIR
3
+ gate_mode: hidden
4
+ dtype: bfloat16
5
+ experts:
6
+ - source_model: AI-MO/NuminaMath-7B-TIR
7
+ positive_prompts:
8
+ - "This model is good at solving math questions at high school level and generating python code for the same"
9
+ # - source_model: Qwen/Qwen2-Math-7B-Instruct
10
+ # positive_prompts:
11
+ # - "This model is really good at solving college level math to olympiad level questions"
12
+ - source_model: deepseek-ai/DeepSeek-Prover-V1.5-RL
13
+ positive_prompts:
14
+ - "This model is good at formal theorem providing math problems"
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d9d78309b7f16ce122e34bef6ab889ce15294c29533701f970e60cc3e96e03
3
+ size 9974324640
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eaeda10774d665ed6110a7a9784b2928113ae8253109b130b9d2766f698f58d
3
+ size 9982711664
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5899d00e1f849ff660277c3603c35569b3a0bd6f863df3afdf5c6252145337f7
3
+ size 1980213472
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.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.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-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-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.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-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-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.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.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"}}
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|begin▁of▁sentence|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "100000": {
7
+ "content": "<|begin▁of▁sentence|>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "100001": {
15
+ "content": "<|end▁of▁sentence|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ }
22
+ },
23
+ "bos_token": "<|begin▁of▁sentence|>",
24
+ "chat_template": "{% for message in messages %}{% if (message['role'] == 'system')%}{{ '' }}{% elif (message['role'] == 'user')%}{{ '### Problem: ' + message['content'] + '\n' }}{% elif (message['role'] == 'assistant')%}{{ '### Solution: ' + message['content'] + '\n' }}{% endif %}{% if loop.last and message['role'] == 'user' and add_generation_prompt %}{{ '### Solution: ' }}{% endif %}{% endfor %}",
25
+ "clean_up_tokenization_spaces": false,
26
+ "eos_token": "<|end▁of▁sentence|>",
27
+ "legacy": true,
28
+ "model_max_length": 4096,
29
+ "pad_token": "<|begin▁of▁sentence|>",
30
+ "sp_model_kwargs": {},
31
+ "tokenizer_class": "LlamaTokenizer",
32
+ "unk_token": null,
33
+ "use_default_system_prompt": false
34
+ }