Update README.md

README.md

@@ -1,12 +1,99 @@
+Hugging Face's logo
+Hugging Face
+Search models, datasets, users...
+Models
+Datasets
+Spaces
+Posts
+Docs
+Solutions
+Pricing
+
+
+
+
+DarqueDante
+/
+LLama-3-Mega-Dolphin-2.9.1-120b 
+
+like
+0
+Text Generation
+Transformers
+Safetensors
+
+cognitivecomputations/Dolphin-2.9
+
+teknium/OpenHermes-2.5
+
+m-a-p/CodeFeedback-Filtered-Instruction
+
+cognitivecomputations/dolphin-coder
+
+cognitivecomputations/samantha-data
+
+HuggingFaceH4/ultrachat_200k
+
+microsoft/orca-math-word-problems-200k
+
+abacusai/SystemChat-1.1
+
+Locutusque/function-calling-chatml
+
+internlm/Agent-FLAN
+English
+llama
+mergekit
+Merge
+conversational
+Inference Endpoints
+text-generation-inference
+Model card
+Files and versions
+Community
+Settings
+LLama-3-Mega-Dolphin-2.9.1-120b
+/
+README.md
+
+DarqueDante's picture
+DarqueDante
+Update README.md
+9f0a74b
+VERIFIED
+3 minutes ago
+Preview
+Code
+|
+raw
+history
+blame
+edit
+delete
+2.68 kB
 ---
 base_model:
-- DarqueDante/LLama-3-Dolphin-2.9.1-120b
+- cognitivecomputations/dolphin-2.9.1-llama-3-70b
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+language:
+- en
+datasets:
+- cognitivecomputations/Dolphin-2.9
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- HuggingFaceH4/ultrachat_200k
+- microsoft/orca-math-word-problems-200k
+- abacusai/SystemChat-1.1
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
 ---
+![image/jpeg](https://huggingface.co/DarqueDante/LLama-3-Dolphin-2.9.1-120b/blob/main/mega_dolphin.png)
+
 # merge
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
@@ -20,7 +107,6 @@ This model was merged using the passthrough merge method.
 
 The following models were included in the merge:
 * [cognitivecomputations/dolphin-2.9.1-llama-3-70b](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-70b)
-* [cognitivecomputations/dolphin-2.9.1-llama-3-70b](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-70b)
 
 ### Configuration
 
@@ -52,3 +138,38 @@ slices:
 merge_method: passthrough
 dtype: float16
 ```
+
+This model uses ChatML prompt template format.
+
+example:
+
+```
+<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+
+## 💻 Usage
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "DarqueDante/LLama-3-Dolphin-2.9.1-120b"
+messages = [{"role": "user", "content": "Who is Andrej Karpathy?"}]
+
+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"])
+```