---
language:
- en
- fr
- ru
- de
- ja
- ko
- zh
- it
- uk
- multilingual
- code
library_name: transformers
tags:
- mistral
- gistral
- gistral-16b
- multilingual
- code
- 128k
- metamath
- grok-1
- anthropic
- openhermes
- instruct
- merge
- llama-cpp
- gguf-my-repo
base_model:
- Gaivoronsky/Mistral-7B-Saiga
- snorkelai/Snorkel-Mistral-PairRM-DPO
- OpenBuddy/openbuddy-mistral2-7b-v20.3-32k
- meta-math/MetaMath-Mistral-7B
- HuggingFaceH4/mistral-7b-grok
- HuggingFaceH4/mistral-7b-anthropic
- NousResearch/Yarn-Mistral-7b-128k
- ajibawa-2023/Code-Mistral-7B
- SherlockAssistant/Mistral-7B-Instruct-Ukrainian
datasets:
- HuggingFaceH4/grok-conversation-harmless
- HuggingFaceH4/ultrachat_200k
- HuggingFaceH4/ultrafeedback_binarized_fixed
- HuggingFaceH4/cai-conversation-harmless
- meta-math/MetaMathQA
- emozilla/yarn-train-tokenized-16k-mistral
- snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
- microsoft/orca-math-word-problems-200k
- m-a-p/Code-Feedback
- teknium/openhermes
- lksy/ru_instruct_gpt4
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/ru_sharegpt_cleaned
- IlyaGusev/oasst1_ru_main_branch
pipeline_tag: text-generation
inference: false
---

# Gistral-16B-Q4_K_M-GGUF
This model was converted to GGUF format from [`ehristoforu/Gistral-16B`](https://huggingface.co/ehristoforu/Gistral-16B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/ehristoforu/Gistral-16B) for more details on the model.
## Use with llama.cpp

Install llama.cpp through brew.

```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.

CLI:

```bash
llama-cli --hf-repo ehristoforu/Gistral-16B-Q4_K_M-GGUF --model gistral-16b.Q4_K_M.gguf -p "The meaning to life and the universe is"
```

Server:

```bash
llama-server --hf-repo ehristoforu/Gistral-16B-Q4_K_M-GGUF --model gistral-16b.Q4_K_M.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

```
git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m gistral-16b.Q4_K_M.gguf -n 128
```

# Gistral 16B (Mistral from 7B to 16B)

![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, Russian, German, Japanese, Chinese, Korean, Italian, Ukrainian, Code
- **Finetuned from model:** [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)


## How to Get Started with the Model

Use the code below to get started with the model.

```py
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "ehristoforu/Gistral-16B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
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?"}
]
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/Mistral-7B-Instruct-v0.2

Merge models:
- Gaivoronsky/Mistral-7B-Saiga
- snorkelai/Snorkel-Mistral-PairRM-DPO
- OpenBuddy/openbuddy-mistral2-7b-v20.3-32k
- meta-math/MetaMath-Mistral-7B
- HuggingFaceH4/mistral-7b-grok
- HuggingFaceH4/mistral-7b-anthropic
- NousResearch/Yarn-Mistral-7b-128k
- ajibawa-2023/Code-Mistral-7B
- SherlockAssistant/Mistral-7B-Instruct-Ukrainian

Merge datasets:
- HuggingFaceH4/grok-conversation-harmless
- HuggingFaceH4/ultrachat_200k
- HuggingFaceH4/ultrafeedback_binarized_fixed
- HuggingFaceH4/cai-conversation-harmless
- meta-math/MetaMathQA
- emozilla/yarn-train-tokenized-16k-mistral
- snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
- microsoft/orca-math-word-problems-200k
- m-a-p/Code-Feedback
- teknium/openhermes
- lksy/ru_instruct_gpt4
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/ru_sharegpt_cleaned
- IlyaGusev/oasst1_ru_main_branch