Downloads · 30 days
37
2% of all-time downloads
RichardErkhov/wannaphong_-_han-llm-7b-v3-gguf
wannaphong_-_han-llm-7b-v3-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
37
2% of all-time downloads
All-time downloads
1.7K
Public
Repo size
82.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf95.6 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
han-llm-7b-v3 - GGUF
| Name | Quant method | Size |
|---|---|---|
| han-llm-7b-v3.Q2_K.gguf | Q2_K | 2.55GB |
| han-llm-7b-v3.IQ3_XS.gguf | IQ3_XS | 2.83GB |
| han-llm-7b-v3.IQ3_S.gguf | IQ3_S | 2.98GB |
| han-llm-7b-v3.Q3_K_S.gguf | Q3_K_S | 2.96GB |
| han-llm-7b-v3.IQ3_M.gguf | IQ3_M | 3.07GB |
| han-llm-7b-v3.Q3_K.gguf | Q3_K | 3.29GB |
| han-llm-7b-v3.Q3_K_M.gguf | Q3_K_M | 3.29GB |
| han-llm-7b-v3.Q3_K_L.gguf | Q3_K_L | 3.57GB |
| han-llm-7b-v3.IQ4_XS.gguf | IQ4_XS | 3.69GB |
| han-llm-7b-v3.Q4_0.gguf | Q4_0 | 3.84GB |
| han-llm-7b-v3.IQ4_NL.gguf | IQ4_NL | 3.89GB |
| han-llm-7b-v3.Q4_K_S.gguf | Q4_K_S | 3.87GB |
| han-llm-7b-v3.Q4_K.gguf | Q4_K | 4.09GB |
| han-llm-7b-v3.Q4_K_M.gguf | Q4_K_M | 4.09GB |
| han-llm-7b-v3.Q4_1.gguf | Q4_1 | 4.26GB |
| han-llm-7b-v3.Q5_0.gguf | Q5_0 | 4.67GB |
| han-llm-7b-v3.Q5_K_S.gguf | Q5_K_S | 4.67GB |
| han-llm-7b-v3.Q5_K.gguf | Q5_K | 4.8GB |
| han-llm-7b-v3.Q5_K_M.gguf | Q5_K_M | 4.8GB |
| han-llm-7b-v3.Q5_1.gguf | Q5_1 | 5.09GB |
| han-llm-7b-v3.Q6_K.gguf | Q6_K | 5.55GB |
| han-llm-7b-v3.Q8_0.gguf | Q8_0 | 7.19GB |
library_name: transformers license: apache-2.0 datasets:
Han LLM 7B v3 is a model that trained by han-instruct-dataset v2.0 and more. The model are working with Thai.
Base model: scb10x/typhoon-7b
Google colab: Demo Han LLM 7B v3
Thank you kaggle for free gpu!
The model was trained by LoRA.
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Thai users
Math, Coding, and other language
The model can has a bias from dataset. Use at your own risks!
Use the code below to get started with the model.
Example
# !pip install accelerate sentencepiece transformers bitsandbytes
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="wannaphong/han-llm-7b-v3", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{"role": "user", "content": "แมวคืออะไร"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=300, do_sample=True, temperature=0.9, top_k=50, top_p=0.95, no_repeat_ngram_size=2,typical_p=1.)
print(outputs[0]["generated_text"])