Upload folder using huggingface_hub

README.md

@@ -1,3 +1,66 @@
 ---
 license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- h4rz3rk4s3/TinyNewsLlama-1.1B
+- h4rz3rk4s3/TinyParlaMintLlama-1.1B
+- Tensoic/TinyLlama-1.1B-3T-openhermes
+base_model:
+- TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- h4rz3rk4s3/TinyNewsLlama-1.1B
+- h4rz3rk4s3/TinyParlaMintLlama-1.1B
+- Tensoic/TinyLlama-1.1B-3T-openhermes
 ---
+
+# TinyPoliticaLlama-4x1.1B-nf4
+
+TinyPoliticaLlama-4x1.1B-nf4 is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
+* [h4rz3rk4s3/TinyNewsLlama-1.1B](https://huggingface.co/h4rz3rk4s3/TinyNewsLlama-1.1B)
+* [h4rz3rk4s3/TinyParlaMintLlama-1.1B](https://huggingface.co/h4rz3rk4s3/TinyParlaMintLlama-1.1B)
+* [Tensoic/TinyLlama-1.1B-3T-openhermes](https://huggingface.co/Tensoic/TinyLlama-1.1B-3T-openhermes)
+
+## 🧩 Configuration
+
+```yaml
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+dtype: bfloat16
+gate_mode: hidden
+experts:
+  - source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    positive_prompts: ["chat", "assistant", "tell me", "explain"]
+  - source_model: h4rz3rk4s3/TinyNewsLlama-1.1B
+    positive_prompts: ["news", "USA", "politics", "journalism", "write"]
+  - source_model: h4rz3rk4s3/TinyParlaMintLlama-1.1B
+    positive_prompts: ["speech", "politics", "EU", "europe", "write"]
+  - source_model: Tensoic/TinyLlama-1.1B-3T-openhermes
+    positive_prompts: ["reason", "provide", "instruct", "summarize", "count"]```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "h4rz3rk4s3/TinyPoliticaLlama-4x1.1B-nf4"
+
+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": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "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": true,
+  "vocab_size": 32000
+}