vanilj / calme-2.4-rys-78b

This model is a fine-tuned version of the dnhkng/RYS-XLarge, pushing the boundaries of natural language understanding and generation even further.

Tools

26 Pulls Updated 8 days ago

8 days ago

d2edcaa0b527 · 32GB

model
qwen2
·
78.0B
·
Q2_K
params
{"stop":["<|im_start|>","<|im_end|>"]}
template
{{ if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{ .System }} {{- if .Tools }} # Tools You are provided with function signatures within <tools></tools> XML tags: <tools>{{- range .Tools }} {"type": "function", "function": {{ .Function }}}{{- end }} </tools> For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags: <tool_call> {"name": <function-name>, "arguments": <args-json-object>} </tool_call> {{- end }}<|im_end|> {{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 -}} {{- if eq .Role "user" }}<|im_start|>user {{ .Content }}<|im_end|> {{ else if eq .Role "assistant" }}<|im_start|>assistant {{ if .Content }}{{ .Content }} {{- else if .ToolCalls }}<tool_call> {{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} {{ end }}</tool_call> {{- end }}{{ if not $last }}<|im_end|> {{ end }} {{- else if eq .Role "tool" }}<|im_start|>tool <tool_response> {{ .Content }} </tool_response><|im_end|> {{ end }} {{- if and (ne .Role "assistant") $last }}<|im_start|>assistant {{ end }} {{- end }} {{- else }} {{- if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user {{ .Prompt }}<|im_end|> {{ end }}<|im_start|>assistant {{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}

Readme

Model files: MaziyarPanahi/calme-2.4-rys-78b
GGUF files: mradermacher/calme-2.4-rys-78b-i1-GGUF

image.png

MaziyarPanahi/calme-2.4-rys-78b

This model is a fine-tuned version of the dnhkng/RYS-XLarge, pushing the boundaries of natural language understanding and generation even further. My goal was to create a versatile and robust model that excels across a wide range of benchmarks and real-world applications.

Use Cases

This model is suitable for a wide range of applications, including but not limited to:

  • Advanced question-answering systems
  • Intelligent chatbots and virtual assistants
  • Content generation and summarization
  • Code generation and analysis
  • Complex problem-solving and decision support

⚡ Quantized GGUF

Here are GGUF models thanks to @mradermacher:
- https://huggingface.co/mradermacher/calme-2.4-rys-78b-GGUF
- https://huggingface.co/mradermacher/calme-2.4-rys-78b-i1-GGUF

🏆 Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 50.26
IFEval (0-Shot) 80.11
BBH (3-Shot) 62.16
MATH Lvl 5 (4-Shot) 37.69
GPQA (0-shot) 20.36
MuSR (0-shot) 34.57
MMLU-PRO (5-shot) 66.69

Prompt Template

This model uses ChatML prompt template:

<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
````

# How to use


```python

# Use a pipeline as a high-level helper

from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.4-rys-78b")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.4-rys-78b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.4-rys-78b")

Ethical Considerations

As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.