Downloads · 30 days
260
28% of all-time downloads
numfa_-_numfalm_v2-1b-gguf
RichardErkhov/numfa_-_numfalm_v2-1b-gguf
numfa_-_numfalm_v2-1b-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
925
Public
Repo size
16.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf19.2 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 23, 2024
- Updated
- Jun 23, 2024
- SHA
- bfc67bfa
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
numfalm_v2-1b - GGUF
- Model creator: https://huggingface.co/numfa/
- Original model: https://huggingface.co/numfa/numfalm_v2-1b/
| Name | Quant method | Size |
|---|---|---|
| numfalm_v2-1b.Q2_K.gguf | Q2_K | 0.55GB |
| numfalm_v2-1b.IQ3_XS.gguf | IQ3_XS | 0.61GB |
| numfalm_v2-1b.IQ3_S.gguf | IQ3_S | 0.63GB |
| numfalm_v2-1b.Q3_K_S.gguf | Q3_K_S | 0.63GB |
| numfalm_v2-1b.IQ3_M.gguf | IQ3_M | 0.66GB |
| numfalm_v2-1b.Q3_K.gguf | Q3_K | 0.68GB |
| numfalm_v2-1b.Q3_K_M.gguf | Q3_K_M | 0.68GB |
| numfalm_v2-1b.Q3_K_L.gguf | Q3_K_L | 0.72GB |
| numfalm_v2-1b.IQ4_XS.gguf | IQ4_XS | 0.73GB |
| numfalm_v2-1b.Q4_0.gguf | Q4_0 | 0.75GB |
| numfalm_v2-1b.IQ4_NL.gguf | IQ4_NL | 0.76GB |
| numfalm_v2-1b.Q4_K_S.gguf | Q4_K_S | 0.79GB |
| numfalm_v2-1b.Q4_K.gguf | Q4_K | 0.83GB |
| numfalm_v2-1b.Q4_K_M.gguf | Q4_K_M | 0.83GB |
| numfalm_v2-1b.Q4_1.gguf | Q4_1 | 0.83GB |
| numfalm_v2-1b.Q5_0.gguf | Q5_0 | 0.9GB |
| numfalm_v2-1b.Q5_K_S.gguf | Q5_K_S | 0.91GB |
| numfalm_v2-1b.Q5_K.gguf | Q5_K | 0.95GB |
| numfalm_v2-1b.Q5_K_M.gguf | Q5_K_M | 0.95GB |
| numfalm_v2-1b.Q5_1.gguf | Q5_1 | 0.97GB |
| numfalm_v2-1b.Q6_K.gguf | Q6_K | 1.11GB |
| numfalm_v2-1b.Q8_0.gguf | Q8_0 | 1.36GB |
Original model description:
license: apache-2.0 language:
- en
- th library_name: transformers pipeline_tag: text-generation
NumFa v2 (1B)
NumFa v2 1B is a LLM pretrained that has 1B.
Base model: TinyLLama
For testing only
Model Details
Model Description
The model was trained by TPU.
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: NumFa
- Model type: text-generation
- Language(s) (NLP): English
- License: apache-2.0
Out-of-Scope Use
Math, Coding, and other language
Bias, Risks, and Limitations
The model can has a bias from dataset. Use at your own risks!
How to Get Started with the Model
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="numfa/numfa_v2-1b", 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
outputs = pipe("test is", 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"])
- Created
- Jun 23, 2024
- Updated
- Jun 23, 2024