Downloads · 30 days
61
6% of all-time downloads
RichardErkhov/MaziyarPanahi_-_calme-2.2-qwen2-72b-gguf
MaziyarPanahi_-_calme-2.2-qwen2-72b-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
61
6% of all-time downloads
All-time downloads
963
Public
Repo size
785 GB
Likes
0
Public
Click a slice to open those files.
.gguf877 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
calme-2.2-qwen2-72b - GGUF
| Name | Quant method | Size |
|---|---|---|
| calme-2.2-qwen2-72b.Q2_K.gguf | Q2_K | 27.76GB |
| calme-2.2-qwen2-72b.Q3_K_S.gguf | Q3_K_S | 32.12GB |
| calme-2.2-qwen2-72b.Q3_K.gguf | Q3_K | 35.11GB |
| calme-2.2-qwen2-72b.Q3_K_M.gguf | Q3_K_M | 35.11GB |
| calme-2.2-qwen2-72b.Q3_K_L.gguf | Q3_K_L | 36.79GB |
| calme-2.2-qwen2-72b.IQ4_XS.gguf | IQ4_XS | 37.4GB |
| calme-2.2-qwen2-72b.Q4_0.gguf | Q4_0 | 38.4GB |
| calme-2.2-qwen2-72b.IQ4_NL.gguf | IQ4_NL | 38.9GB |
| calme-2.2-qwen2-72b.Q4_K_S.gguf | Q4_K_S | 40.88GB |
| calme-2.2-qwen2-72b.Q4_K.gguf | Q4_K | 44.16GB |
| calme-2.2-qwen2-72b.Q4_K_M.gguf | Q4_K_M | 44.16GB |
| calme-2.2-qwen2-72b.Q4_1.gguf | Q4_1 | 42.56GB |
| calme-2.2-qwen2-72b.Q5_0.gguf | Q5_0 | 46.72GB |
| calme-2.2-qwen2-72b.Q5_K_S.gguf | Q5_K_S | 47.85GB |
| calme-2.2-qwen2-72b.Q5_K.gguf | Q5_K | 50.71GB |
| calme-2.2-qwen2-72b.Q5_K_M.gguf | Q5_K_M | 50.71GB |
| calme-2.2-qwen2-72b.Q5_1.gguf | Q5_1 | 50.88GB |
| calme-2.2-qwen2-72b.Q6_K.gguf | Q6_K | 59.93GB |
| calme-2.2-qwen2-72b.Q8_0.gguf | Q8_0 | 71.96GB |
language:
This model is a fine-tuned version of the powerful Qwen/Qwen2-72B-Instruct, 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.
The post-training process is identical to the calme-2.1-qwen2-72b model; however, some parameters are different, and it was trained for a longer period.
This model is suitable for a wide range of applications, including but not limited to:
All GGUF models are available here: MaziyarPanahi/calme-2.2-qwen2-72b-GGUF
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 43.40 |
| IFEval (0-Shot) | 80.08 |
| BBH (3-Shot) | 56.80 |
| MATH Lvl 5 (4-Shot) | 41.16 |
| GPQA (0-shot) | 16.55 |
| MuSR (0-shot) | 16.52 |
| MMLU-PRO (5-shot) | 49.27 |
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|--------------|------:|------|-----:|------|-----:|---|-----:|
|truthfulqa_mc2| 2|none | 0|acc |0.6856|± |0.0148|
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|----------|------:|------|-----:|------|-----:|---|-----:|
|winogrande| 1|none | 5|acc |0.8343|± |0.0105|
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|-------------|------:|------|-----:|--------|-----:|---|-----:|
|arc_challenge| 1|none | 25|acc |0.6928|± |0.0135|
| | |none | 25|acc_norm|0.7227|± |0.0131|
|Tasks|Version| Filter |n-shot| Metric |Value | |Stderr|
|-----|------:|----------------|-----:|-----------|-----:|---|-----:|
|gsm8k| 3|strict-match | 5|exact_match|0.8582|± |0.0096|
| | |flexible-extract| 5|exact_match|0.8878|± |0.0087|
This model uses ChatML prompt template:
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
# 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-2.2-qwen2-72b")
pipe(messages)
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.2-qwen2-72b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.2-qwen2-72b")
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.