Upload folder using huggingface_hub

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- openaccess-ai-collective/tiny-mistral
+base_model:
+- openaccess-ai-collective/tiny-mistral
+- openaccess-ai-collective/tiny-mistral
+- openaccess-ai-collective/tiny-mistral
+- openaccess-ai-collective/tiny-mistral
+---
+
+# test_tiny_mixtral_only_router
+
+test_tiny_mixtral_only_router is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral)
+* [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral)
+* [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral)
+* [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral)
+
+## 🧩 Configuration
+
+```yaml
+base_model: openaccess-ai-collective/tiny-mistral
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: openaccess-ai-collective/tiny-mistral
+    positive_prompts:
+      - "math"
+    # You can add negative_prompts if needed
+  - source_model: openaccess-ai-collective/tiny-mistral
+
+    positive_prompts:
+      - "science"
+  - source_model: openaccess-ai-collective/tiny-mistral
+    positive_prompts:
+      - "writing"
+    # You can add negative_prompts if needed
+  - source_model: openaccess-ai-collective/tiny-mistral
+    positive_prompts:
+      - "general"
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "JSpergel/test_tiny_mixtral_only_router"
+
+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": "openaccess-ai-collective/tiny-mistral",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dropout_p": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 4,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,20 @@
+
+base_model: openaccess-ai-collective/tiny-mistral
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: openaccess-ai-collective/tiny-mistral
+    positive_prompts:
+      - "math"
+    # You can add negative_prompts if needed
+  - source_model: openaccess-ai-collective/tiny-mistral
+
+    positive_prompts:
+      - "science"
+  - source_model: openaccess-ai-collective/tiny-mistral
+    positive_prompts:
+      - "writing"
+    # You can add negative_prompts if needed
+  - source_model: openaccess-ai-collective/tiny-mistral
+    positive_prompts:
+      - "general"

moe_router_weights.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f030f672fe5e9dbf86bccef6eee1b7b67e506055dff820c323fbe21db254f461
+size 36228

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "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": true
+}