Upload folder using huggingface_hub

README.md

@@ -0,0 +1,108 @@
+---
+license: apache-2.0
+tags:
+- moe
+- merge
+- mergekit
+- lazymergekit
+- BEE-spoke-data/smol_llama-220M-openhermes
+- BEE-spoke-data/beecoder-220M-python
+- BEE-spoke-data/zephyr-220m-sft-full
+- BEE-spoke-data/zephyr-220m-dpo-full
+---
+
+# smol_llama-4x220M-MoE
+
+smol_llama-4x220M-MoE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [BEE-spoke-data/smol_llama-220M-openhermes](https://huggingface.co/BEE-spoke-data/smol_llama-220M-openhermes)
+* [BEE-spoke-data/beecoder-220M-python](https://huggingface.co/BEE-spoke-data/beecoder-220M-python)
+* [BEE-spoke-data/zephyr-220m-sft-full](https://huggingface.co/BEE-spoke-data/zephyr-220m-sft-full)
+* [BEE-spoke-data/zephyr-220m-dpo-full](https://huggingface.co/BEE-spoke-data/zephyr-220m-dpo-full)
+
+## 🧩 Configuration
+
+```yamlbase_model: BEE-spoke-data/smol_llama-220M-openhermes
+experts:
+  - source_model: BEE-spoke-data/smol_llama-220M-openhermes
+    positive_prompts:
+    - "reasoning"
+    - "logic"
+    - "problem-solving"
+    - "critical thinking"
+    - "analysis"
+    - "synthesis"
+    - "evaluation"
+    - "decision-making"
+    - "judgment"
+    - "insight"
+
+  - source_model: BEE-spoke-data/beecoder-220M-python
+    positive_prompts:
+    - "program"
+    - "software"
+    - "develop"
+    - "build"
+    - "create"
+    - "design"
+    - "implement"
+    - "debug"
+    - "test"
+    - "code"
+    - "python"
+    - "programming"
+    - "algorithm"
+    - "function"
+
+  - source_model: BEE-spoke-data/zephyr-220m-sft-full
+    positive_prompts:
+    - "storytelling"
+    - "narrative"
+    - "fiction"
+    - "creative writing"
+    - "plot"
+    - "characters"
+    - "dialogue"
+    - "setting"
+    - "emotion"
+    - "imagination"
+    - "scene"
+    - "story"
+    - "character"
+    
+  - source_model: BEE-spoke-data/zephyr-220m-dpo-full
+    positive_prompts:
+    - "chat"
+    - "conversation"
+    - "dialogue"
+    - "discuss"
+    - "ask questions"
+    - "share thoughts"
+    - "explore ideas"
+    - "learn new things"
+    - "personal assistant"
+    - "friendly helper"
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Isotonic/smol_llama-4x220M-MoE"
+
+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 +1,33 @@
+{
+  "_name_or_path": "BEE-spoke-data/smol_llama-220M-openhermes",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 10,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "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,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": false,
+  "vocab_size": 32128
+}

mergekit_moe_config.yml

@@ -0,0 +1,60 @@
+base_model: BEE-spoke-data/smol_llama-220M-openhermes
+experts:
+  - source_model: BEE-spoke-data/smol_llama-220M-openhermes
+    positive_prompts:
+    - "reasoning"
+    - "logic"
+    - "problem-solving"
+    - "critical thinking"
+    - "analysis"
+    - "synthesis"
+    - "evaluation"
+    - "decision-making"
+    - "judgment"
+    - "insight"
+
+  - source_model: BEE-spoke-data/beecoder-220M-python
+    positive_prompts:
+    - "program"
+    - "software"
+    - "develop"
+    - "build"
+    - "create"
+    - "design"
+    - "implement"
+    - "debug"
+    - "test"
+    - "code"
+    - "python"
+    - "programming"
+    - "algorithm"
+    - "function"
+
+  - source_model: BEE-spoke-data/zephyr-220m-sft-full
+    positive_prompts:
+    - "storytelling"
+    - "narrative"
+    - "fiction"
+    - "creative writing"
+    - "plot"
+    - "characters"
+    - "dialogue"
+    - "setting"
+    - "emotion"
+    - "imagination"
+    - "scene"
+    - "story"
+    - "character"
+    
+  - source_model: BEE-spoke-data/zephyr-220m-dpo-full
+    positive_prompts:
+    - "chat"
+    - "conversation"
+    - "dialogue"
+    - "discuss"
+    - "ask questions"
+    - "share thoughts"
+    - "explore ideas"
+    - "learn new things"
+    - "personal assistant"
+    - "friendly helper"

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106cbbfaaf9a53e2d822b32bb2c9530c12677eda9eca9400c82397b0c984904f
+size 1190806744

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "lm_head.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00001.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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}