Downloads · 30 days
36
1% of all-time downloads
johnsnowlabs_-_PhigRange-DPO-gguf
RichardErkhov/johnsnowlabs_-_PhigRange-DPO-gguf
johnsnowlabs_-_PhigRange-DPO-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.
All-time downloads
2.7K
Public
Repo size
32.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf37.4 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 12, 2024
- Updated
- Oct 12, 2024
- SHA
- 5c97e174
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
PhigRange-DPO - GGUF
- Model creator: https://huggingface.co/johnsnowlabs/
- Original model: https://huggingface.co/johnsnowlabs/PhigRange-DPO/
| Name | Quant method | Size |
|---|---|---|
| PhigRange-DPO.Q2_K.gguf | Q2_K | 1.03GB |
| PhigRange-DPO.IQ3_XS.gguf | IQ3_XS | 1.12GB |
| PhigRange-DPO.IQ3_S.gguf | IQ3_S | 1.16GB |
| PhigRange-DPO.Q3_K_S.gguf | Q3_K_S | 1.16GB |
| PhigRange-DPO.IQ3_M.gguf | IQ3_M | 1.23GB |
| PhigRange-DPO.Q3_K.gguf | Q3_K | 1.33GB |
| PhigRange-DPO.Q3_K_M.gguf | Q3_K_M | 1.33GB |
| PhigRange-DPO.Q3_K_L.gguf | Q3_K_L | 1.47GB |
| PhigRange-DPO.IQ4_XS.gguf | IQ4_XS | 1.43GB |
| PhigRange-DPO.Q4_0.gguf | Q4_0 | 1.49GB |
| PhigRange-DPO.IQ4_NL.gguf | IQ4_NL | 1.5GB |
| PhigRange-DPO.Q4_K_S.gguf | Q4_K_S | 1.51GB |
| PhigRange-DPO.Q4_K.gguf | Q4_K | 1.62GB |
| PhigRange-DPO.Q4_K_M.gguf | Q4_K_M | 1.62GB |
| PhigRange-DPO.Q4_1.gguf | Q4_1 | 1.65GB |
| PhigRange-DPO.Q5_0.gguf | Q5_0 | 1.8GB |
| PhigRange-DPO.Q5_K_S.gguf | Q5_K_S | 1.8GB |
| PhigRange-DPO.Q5_K.gguf | Q5_K | 1.87GB |
| PhigRange-DPO.Q5_K_M.gguf | Q5_K_M | 1.87GB |
| PhigRange-DPO.Q5_1.gguf | Q5_1 | 1.95GB |
| PhigRange-DPO.Q6_K.gguf | Q6_K | 2.13GB |
| PhigRange-DPO.Q8_0.gguf | Q8_0 | 2.75GB |
Original model description:
license: cc-by-nc-4.0 base_model: PhigRange-2.7B-slerp tags:
- generated_from_trainer
- DPO
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation model-index:
- name: PhigRange-DPO results: [] datasets:
- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha language:
- en library_name: transformers pipeline_tag: text-generation
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
PhigRange-DPO
PhigRange-DPO is a DPO fine-tuned of johnsnowlabs/PhigRange-2.7B-Slerp using the mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha preference dataset. The model has been trained for for 1080 steps.
🏆 Evaluation results
Coming Soon
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "johnsnowlabs/PhigRange-DPO"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-04
- train_batch_size: 1
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: AdamOptimizer32bit
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1080
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.17.0
- Tokenizers 0.15.0
- Created
- Oct 12, 2024
- Updated
- Oct 12, 2024