Upload folder using huggingface_hub

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- mlabonne/ChimeraLlama-3-8B-v2
+- nbeerbower/llama-3-stella-8B
+- uygarkurt/llama-3-merged-linear
+base_model:
+- mlabonne/ChimeraLlama-3-8B-v2
+- nbeerbower/llama-3-stella-8B
+- uygarkurt/llama-3-merged-linear
+---
+
+# NeuralLLaMa-3-8b-DT-v0.1
+
+NeuralLLaMa-3-8b-DT-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [mlabonne/ChimeraLlama-3-8B-v2](https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v2)
+* [nbeerbower/llama-3-stella-8B](https://huggingface.co/nbeerbower/llama-3-stella-8B)
+* [uygarkurt/llama-3-merged-linear](https://huggingface.co/uygarkurt/llama-3-merged-linear)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: NousResearch/Meta-Llama-3-8B
+    # No parameters necessary for base model
+  - model: mlabonne/ChimeraLlama-3-8B-v2
+    parameters:
+      density: 0.33
+      weight: 0.2
+  - model: nbeerbower/llama-3-stella-8B
+    parameters:
+      density: 0.44
+      weight: 0.4
+  - model: uygarkurt/llama-3-merged-linear
+    parameters:
+      density: 0.55
+      weight: 0.4
+merge_method: dare_ties
+base_model: NousResearch/Meta-Llama-3-8B
+parameters:
+  int8_mask: true
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Kukedlc/NeuralLLaMa-3-8b-DT-v0.1"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+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 +1,28 @@
+{
+  "_name_or_path": "NousResearch/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

mergekit_config.yml

@@ -0,0 +1,21 @@
+
+models:
+  - model: NousResearch/Meta-Llama-3-8B
+    # No parameters necessary for base model
+  - model: mlabonne/ChimeraLlama-3-8B-v2
+    parameters:
+      density: 0.33
+      weight: 0.2
+  - model: nbeerbower/llama-3-stella-8B
+    parameters:
+      density: 0.44
+      weight: 0.4
+  - model: uygarkurt/llama-3-merged-linear
+    parameters:
+      density: 0.55
+      weight: 0.4
+merge_method: dare_ties
+base_model: NousResearch/Meta-Llama-3-8B
+parameters:
+  int8_mask: true
+dtype: float16

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb275a4858543a692f9a2b172841ad04cbb3711bfd35ebed11c43843e269311
+size 4953586328

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8fde01a96c72d9e58bdd49a5eda0b8b944226f8585e929528211b574020ff4
+size 4999819232

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0dafd3634fdb31a06249ef2962c59ce6f240d1afb482fca873f7fc568276bff
+size 4915916048

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d1605f48a1f34a071720a5d0dc47525d154a61e69b60a0d565cfa9233fed7e
+size 1191234448

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}