初始化项目，由ModelHub XC社区提供模型
Model: RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf Source: Original Platform
This commit is contained in:
ModelHub XC
86
README.md
Normal file
86
README.md
Normal file
@@ -0,0 +1,86 @@
|
||||
Quantization made by Richard Erkhov.
|
||||
|
||||
[Github](https://github.com/RichardErkhov)
|
||||
|
||||
[Discord](https://discord.gg/pvy7H8DZMG)
|
||||
|
||||
[Request more models](https://github.com/RichardErkhov/quant_request)
|
||||
|
||||
|
||||
gemma-2b-ForexAI - GGUF
|
||||
- Model creator: https://huggingface.co/mjmanashti/
|
||||
- Original model: https://huggingface.co/mjmanashti/gemma-2b-ForexAI/
|
||||
|
||||
|
||||
| Name | Quant method | Size |
|
||||
| ---- | ---- | ---- |
|
||||
| [gemma-2b-ForexAI.Q2_K.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q2_K.gguf) | Q2_K | 1.08GB |
|
||||
| [gemma-2b-ForexAI.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.IQ3_XS.gguf) | IQ3_XS | 1.16GB |
|
||||
| [gemma-2b-ForexAI.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.IQ3_S.gguf) | IQ3_S | 1.2GB |
|
||||
| [gemma-2b-ForexAI.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q3_K_S.gguf) | Q3_K_S | 1.2GB |
|
||||
| [gemma-2b-ForexAI.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.IQ3_M.gguf) | IQ3_M | 1.22GB |
|
||||
| [gemma-2b-ForexAI.Q3_K.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q3_K.gguf) | Q3_K | 1.29GB |
|
||||
| [gemma-2b-ForexAI.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q3_K_M.gguf) | Q3_K_M | 1.29GB |
|
||||
| [gemma-2b-ForexAI.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q3_K_L.gguf) | Q3_K_L | 1.36GB |
|
||||
| [gemma-2b-ForexAI.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.IQ4_XS.gguf) | IQ4_XS | 1.4GB |
|
||||
| [gemma-2b-ForexAI.Q4_0.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q4_0.gguf) | Q4_0 | 1.44GB |
|
||||
| [gemma-2b-ForexAI.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.IQ4_NL.gguf) | IQ4_NL | 1.45GB |
|
||||
| [gemma-2b-ForexAI.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q4_K_S.gguf) | Q4_K_S | 1.45GB |
|
||||
| [gemma-2b-ForexAI.Q4_K.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q4_K.gguf) | Q4_K | 1.52GB |
|
||||
| [gemma-2b-ForexAI.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q4_K_M.gguf) | Q4_K_M | 1.52GB |
|
||||
| [gemma-2b-ForexAI.Q4_1.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q4_1.gguf) | Q4_1 | 1.56GB |
|
||||
| [gemma-2b-ForexAI.Q5_0.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q5_0.gguf) | Q5_0 | 1.68GB |
|
||||
| [gemma-2b-ForexAI.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q5_K_S.gguf) | Q5_K_S | 1.68GB |
|
||||
| [gemma-2b-ForexAI.Q5_K.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q5_K.gguf) | Q5_K | 1.71GB |
|
||||
| [gemma-2b-ForexAI.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q5_K_M.gguf) | Q5_K_M | 1.71GB |
|
||||
| [gemma-2b-ForexAI.Q5_1.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q5_1.gguf) | Q5_1 | 1.79GB |
|
||||
| [gemma-2b-ForexAI.Q6_K.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q6_K.gguf) | Q6_K | 1.92GB |
|
||||
| [gemma-2b-ForexAI.Q8_0.gguf](https://huggingface.co/RichardErkhov/mjmanashti_-_gemma-2b-ForexAI-gguf/blob/main/gemma-2b-ForexAI.Q8_0.gguf) | Q8_0 | 2.49GB |
|
||||
|
||||
|
||||
|
||||
|
||||
Original model description:
|
||||
---
|
||||
license: other
|
||||
tags:
|
||||
- autotrain
|
||||
- text-generation
|
||||
widget:
|
||||
- text: 'I love AutoTrain because '
|
||||
---
|
||||
|
||||
# Model Trained Using AutoTrain
|
||||
|
||||
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
||||
|
||||
# Usage
|
||||
|
||||
```python
|
||||
!pip install transformers
|
||||
|
||||
!pip install accelerate
|
||||
|
||||
|
||||
from huggingface_hub import notebook_login
|
||||
notebook_login()
|
||||
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("mjmanashti/gemma-2b-ForexAI")
|
||||
torch.set_default_dtype(torch.float16)
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("mjmanashti/gemma-2b-ForexAI", device_map="auto")
|
||||
|
||||
chat = [
|
||||
{ "role": "user", "content": "Based on the following input data: [Time: 2024-01-29 23:00:00, Open: 1.0834, High: 1.0837, Low: 1.08334, Close: 1.08338, Volume: 722] what trading signal (BUY, SELL, or HOLD) should be executed to maximize profit? If the signal is BUY, what would be the entry price and If the signal is SELL, what would be the exit price for profit maximization? " },
|
||||
]
|
||||
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
|
||||
inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
|
||||
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user