uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Quantization made by Richard Erkhov.
|
2 |
+
|
3 |
+
[Github](https://github.com/RichardErkhov)
|
4 |
+
|
5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
6 |
+
|
7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
8 |
+
|
9 |
+
|
10 |
+
OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered - GGUF
|
11 |
+
- Model creator: https://huggingface.co/sonthenguyen/
|
12 |
+
- Original model: https://huggingface.co/sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered/
|
13 |
+
|
14 |
+
|
15 |
+
| Name | Quant method | Size |
|
16 |
+
| ---- | ---- | ---- |
|
17 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q2_K.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q2_K.gguf) | Q2_K | 2.53GB |
|
18 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
|
19 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ3_S.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ3_S.gguf) | IQ3_S | 2.96GB |
|
20 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
|
21 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ3_M.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ3_M.gguf) | IQ3_M | 3.06GB |
|
22 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q3_K.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q3_K.gguf) | Q3_K | 3.28GB |
|
23 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
|
24 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
|
25 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
|
26 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_0.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_0.gguf) | Q4_0 | 3.83GB |
|
27 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
|
28 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
|
29 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_K.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_K.gguf) | Q4_K | 4.07GB |
|
30 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
|
31 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_1.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q4_1.gguf) | Q4_1 | 4.24GB |
|
32 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_0.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_0.gguf) | Q5_0 | 4.65GB |
|
33 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
|
34 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_K.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_K.gguf) | Q5_K | 4.78GB |
|
35 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
|
36 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_1.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q5_1.gguf) | Q5_1 | 5.07GB |
|
37 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q6_K.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q6_K.gguf) | Q6_K | 5.53GB |
|
38 |
+
| [OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q8_0.gguf](https://huggingface.co/RichardErkhov/sonthenguyen_-_OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered-gguf/blob/main/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered.Q8_0.gguf) | Q8_0 | 7.17GB |
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
Original model description:
|
44 |
+
---
|
45 |
+
license: apache-2.0
|
46 |
+
---
|
47 |
+
|
48 |
+
Training hyperparameters LoRA: r=16 lora_alpha=16 lora_dropout=0.05 bias="none" task_type="CAUSAL_LM" target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
|
49 |
+
|
50 |
+
Training arguments: auto_find_batch_size=True gradient_checkpointing=True learning_rate=5e-7 lr_scheduler_type="cosine" max_steps=3922 optim="paged_adamw_32bit" warmup_steps=100
|
51 |
+
|
52 |
+
DPOTrainer: beta=0.1 max_prompt_length=1024 max_length=1536
|
53 |
+
|
54 |
+
Arxiv link: https://arxiv.org/abs/2403.02745
|
55 |
+
|