Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+tags:
+- mixture of experts
+- moe
+- merge
+- mergekit
+- mistralai/Mistral-7B-Instruct-v0.2
+- nvidia/OpenMath-Mistral-7B-v0.1-hf
+base_model:
+- mistralai/Mistral-7B-Instruct-v0.2
+- nvidia/OpenMath-Mistral-7B-v0.1-hf
+---
+
+# mistral_2x7b_v0.1
+
+mistral_2x7b_v0.1 is a Mixure of Experts (MoE) made with the following models using [mergekit-moe](https://github.com/arcee-ai/mergekit/blob/main/docs/moe.md):
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
+* [nvidia/OpenMath-Mistral-7B-v0.1-hf](https://huggingface.co/nvidia/OpenMath-Mistral-7B-v0.1-hf)
+
+## 🧩 Configuration
+
+```yamlbase_model: mistralai/Mistral-7B-v0.1
+gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+experts:
+  - source_model: mistralai/Mistral-7B-Instruct-v0.2
+    positive_prompts:
+      - "What are some fun activities to do in Seattle?"
+      - "What are the potential long-term economic impacts of raising the minimum wage?"
+  - source_model: nvidia/OpenMath-Mistral-7B-v0.1-hf
+    positive_prompts:
+     - "What is 27 * 49? Show your step-by-step work."
+     - "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?"
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "HachiML/mistral_2x7b_v0.1"
+
+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 +1,31 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "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": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,12 @@
+base_model: mistralai/Mistral-7B-v0.1
+gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+experts:
+  - source_model: mistralai/Mistral-7B-Instruct-v0.2
+    positive_prompts:
+      - "What are some fun activities to do in Seattle?"
+      - "What are the potential long-term economic impacts of raising the minimum wage?"
+  - source_model: nvidia/OpenMath-Mistral-7B-v0.1-hf
+    positive_prompts:
+     - "What is 27 * 49? Show your step-by-step work."
+     - "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?"

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f25aa44a949070225a76d4e5d9fff2be9674446d0224d8cd024e3e251be4b8
+size 9986869088

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba98e15b7d653467317df67b40d6fc094fc817214875c970883d465873b1319b
+size 9898781200

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e881867e1fe7aead5c8b620ebf86ab16869d1a89d09c3ecb6c0e4dd3bb682b97
+size 5872679152

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 25758277632}, "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.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_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.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.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.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.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.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.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.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.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.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.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.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.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.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.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.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.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.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.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.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.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.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.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.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.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.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.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.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.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.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.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.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.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.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.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.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.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.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.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.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.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.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.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.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.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.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.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.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.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.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.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.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.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.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.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.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.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.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.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-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}