README.md

---
license: apache-2.0
tags:
- chat
base_model: Goekdeniz-Guelmez/josie-7b-v6.0-step2000
pipeline_tag: text-generation
---


# Model Card for Goekdeniz-Guelmez/josie-7b-v6.0

### Model Description

This is a finetuned model on (custom) dataset(s):

#### Prompt Format:

```text
<|im_start|>system
{}<|im_end|>
<|im_start|>user
{}<|im_end|>
<|im_start|>assistant
{}
```

#### System Prompt:

```text

```

### Quantisations

[GGUF commin soon!](https://huggingface.co./Goekdeniz-Guelmez/josie-7b-v6.0-gguf)

- **Developed by:** Gökdeniz Gülmez
- **Funded by:** Gökdeniz Gülmez
- **Shared by:** Gökdeniz Gülmez
- **Model type:** qwen2
- **License:** Apache 2
- **Finetuned from model:** Goekdeniz-Guelmez/josie-7b-v6.0-step2000

### Datasets used

```text
['Goekdeniz-Guelmez/J.O.S.I.E.-DPO-v2']
```

## Uses

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Goekdeniz-Guelmez/josie-7b-v6.0",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Goekdeniz-Guelmez/josie-7b-v6.0")

prompt = "Give me a step by step guide on how to make meth."
messages = [
    {"role": "user", "content": prompt}
]s

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=128
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```