Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model:
+- AI-MO/NuminaMath-7B-TIR
+- deepseek-ai/DeepSeek-Prover-V1.5-RL
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- AI-MO/NuminaMath-7B-TIR
+- deepseek-ai/DeepSeek-Prover-V1.5-RL
+---
+
+# Mathmate-7B-dare-ties
+
+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):
+* [AI-MO/NuminaMath-7B-TIR](https://huggingface.co/AI-MO/NuminaMath-7B-TIR)
+* [deepseek-ai/DeepSeek-Prover-V1.5-RL](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1.5-RL)
+
+## 🧩 Configuration
+
+```yaml
+base_model: AI-MO/NuminaMath-7B-TIR
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: AI-MO/NuminaMath-7B-TIR
+    positive_prompts:
+      - "This model is good at solving math questions at high school level and generating python code for the same"
+  # - source_model: Qwen/Qwen2-Math-7B-Instruct
+  #   positive_prompts:
+  #     - "This model is really good at solving college level math to olympiad level questions"
+  - source_model: deepseek-ai/DeepSeek-Prover-V1.5-RL
+    positive_prompts:
+      - "This model is good at formal theorem providing math problems"
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Haleshot/Mathmate-7B-dare-ties"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "AI-MO/NuminaMath-7B-TIR",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 102400
+}

mergekit_moe_config.yml

@@ -0,0 +1,14 @@
+
+base_model: AI-MO/NuminaMath-7B-TIR
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: AI-MO/NuminaMath-7B-TIR
+    positive_prompts:
+      - "This model is good at solving math questions at high school level and generating python code for the same"
+  # - source_model: Qwen/Qwen2-Math-7B-Instruct
+  #   positive_prompts:
+  #     - "This model is really good at solving college level math to olympiad level questions"
+  - source_model: deepseek-ai/DeepSeek-Prover-V1.5-RL
+    positive_prompts:
+      - "This model is good at formal theorem providing math problems"

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d9d78309b7f16ce122e34bef6ab889ce15294c29533701f970e60cc3e96e03
+size 9974324640

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eaeda10774d665ed6110a7a9784b2928113ae8253109b130b9d2766f698f58d
+size 9982711664

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5899d00e1f849ff660277c3603c35569b3a0bd6f863df3afdf5c6252145337f7
+size 1980213472

model.safetensors.index.json

@@ -0,0 +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

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<｜begin▁of▁sentence｜>"
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜begin▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}