Update README.md

README.md

@@ -1,41 +1,93 @@
 ---
 base_model:
+- mistralai/Mixtral-8x22B-Instruct-v0.1
+- mistralai/Mixtral-8x7B-Instruct-v0.1
 - cognitivecomputations/dolphin-2.7-mixtral-8x7b
 - alpindale/WizardLM-2-8x22B
+datasets:
+- ehartford/dolphin
+- jondurbin/airoboros-2.2.1
+- ehartford/dolphin-coder
+- migtissera/Synthia-v1.3
+- teknium/openhermes
+- ise-uiuc/Magicoder-OSS-Instruct-75K
+- ise-uiuc/Magicoder-Evol-Instruct-110K
+- LDJnr/Pure-Dove
 library_name: transformers
 tags:
-- mergekit
+- mixtral
+- mixtral-8x22b
+- mixtral-8x7b
+- instruct
 - merge
-
+pipeline_tag: text-generation
+license: apache-2.0
+language:
+- en
+- fr
+- de
+- es
+- it
 ---
-# merge
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+# Gixtral (Mixtral from 8x22B & 8x7B to 100B)
+
+![logo](assets/logo.png)
+
+We created a model from other cool models to combine everything into one cool model.
+
+
+## Model Details
+
+### Model Description
+
+- **Developed by:** [@ehristoforu](https://huggingface.co/ehristoforu)
+- **Model type:** Text Generation (conversational)
+- **Language(s) (NLP):** English, French, German, Spanish, Italian
+- **Finetuned from model:** [mistralai/Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1) & [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
+
 
-## Merge Details
-### Merge Method
+## How to Get Started with the Model
 
-This model was merged using the passthrough merge method.
+Use the code below to get started with the model.
 
-### Models Merged
+```py
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-The following models were included in the merge:
-* [cognitivecomputations/dolphin-2.7-mixtral-8x7b](https://huggingface.co/cognitivecomputations/dolphin-2.7-mixtral-8x7b)
-* [alpindale/WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B)
+model_id = "ehristoforu/Gixtral-100B"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-### Configuration
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
 
-The following YAML configuration was used to produce this model:
+messages = [
+    {"role": "user", "content": "What is your favourite condiment?"},
+    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
+    {"role": "user", "content": "Do you have mayonnaise recipes?"}
+]
 
-```yaml
-slices:
-  - sources:
-    - model: alpindale/WizardLM-2-8x22B
-      layer_range: [0, 32]
-  - sources:
-    - model: cognitivecomputations/dolphin-2.7-mixtral-8x7b
-      layer_range: [20, 32]
-merge_method: passthrough
-dtype: bfloat16
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
 
+outputs = model.generate(inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
+
+
+## About merge
+
+Base model: mistralai/Mixtral-8x22B-Instruct-v0.1 & mistralai/Mixtral-8x7B-Instruct-v0.1
+
+Merge models:
+- mistralai/Mixtral-8x22B-Instruct-v0.1
+- mistralai/Mixtral-8x7B-Instruct-v0.1
+- cognitivecomputations/dolphin-2.7-mixtral-8x7b
+- alpindale/WizardLM-2-8x22B
+
+Merge datasets:
+- ehartford/dolphin
+- jondurbin/airoboros-2.2.1
+- ehartford/dolphin-coder
+- migtissera/Synthia-v1.3
+- teknium/openhermes
+- ise-uiuc/Magicoder-OSS-Instruct-75K
+- ise-uiuc/Magicoder-Evol-Instruct-110K
+- LDJnr/Pure-Dove