Downloads · 30 days
107
2% of all-time downloads
RichardErkhov/yam-peleg_-_Hebrew-Gemma-11B-V2-gguf
yam-peleg_-_Hebrew-Gemma-11B-V2-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
107
2% of all-time downloads
All-time downloads
4.3K
Public
Repo size
122 GB
Likes
0
Public
Click a slice to open those files.
.gguf141 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Hebrew-Gemma-11B-V2 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Hebrew-Gemma-11B-V2.Q2_K.gguf | Q2_K | 3.9GB |
| Hebrew-Gemma-11B-V2.IQ3_XS.gguf | IQ3_XS | 4.27GB |
| Hebrew-Gemma-11B-V2.IQ3_S.gguf | IQ3_S | 4.48GB |
| Hebrew-Gemma-11B-V2.Q3_K_S.gguf | Q3_K_S | 4.48GB |
| Hebrew-Gemma-11B-V2.IQ3_M.gguf | IQ3_M | 4.63GB |
| Hebrew-Gemma-11B-V2.Q3_K.gguf | Q3_K | 4.94GB |
| Hebrew-Gemma-11B-V2.Q3_K_M.gguf | Q3_K_M | 4.94GB |
| Hebrew-Gemma-11B-V2.Q3_K_L.gguf | Q3_K_L | 5.33GB |
| Hebrew-Gemma-11B-V2.IQ4_XS.gguf | IQ4_XS | 5.44GB |
| Hebrew-Gemma-11B-V2.Q4_0.gguf | Q4_0 | 5.68GB |
| Hebrew-Gemma-11B-V2.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| Hebrew-Gemma-11B-V2.Q4_K_S.gguf | Q4_K_S | 5.72GB |
| Hebrew-Gemma-11B-V2.Q4_K.gguf | Q4_K | 6.04GB |
| Hebrew-Gemma-11B-V2.Q4_K_M.gguf | Q4_K_M | 6.04GB |
| Hebrew-Gemma-11B-V2.Q4_1.gguf | Q4_1 | 6.25GB |
| Hebrew-Gemma-11B-V2.Q5_0.gguf | Q5_0 | 6.81GB |
| Hebrew-Gemma-11B-V2.Q5_K_S.gguf | Q5_K_S | 6.81GB |
| Hebrew-Gemma-11B-V2.Q5_K.gguf | Q5_K | 7.0GB |
| Hebrew-Gemma-11B-V2.Q5_K_M.gguf | Q5_K_M | 7.0GB |
| Hebrew-Gemma-11B-V2.Q5_1.gguf | Q5_1 | 7.37GB |
| Hebrew-Gemma-11B-V2.Q6_K.gguf | Q6_K | 8.01GB |
| Hebrew-Gemma-11B-V2.Q8_0.gguf | Q8_0 | 10.37GB |
license: other license_name: gemma-terms-of-use license_link: https://ai.google.dev/gemma/terms language:
An updated version of Hebrew-Gemma-11B that was trained longer and had some bugs fixes.
Hebrew-Gemma-11B is an open-source Large Language Model (LLM) is a hebrew/english pretrained generative text model with 11 billion parameters, based on the Gemma-7B architecture from Google.
It is continued pretrain of gemma-7b, extended to a larger scale and trained on 3B additional tokens of both English and Hebrew text data.
The resulting model Gemma-11B is a powerful general-purpose language model suitable for a wide range of natural language processing tasks, with a focus on Hebrew language understanding and generation.
As an extention of Gemma-7B, this model is subject to the original license and terms of use by Google.
Gemma-7B original Terms of Use: Terms
Below are some code snippets on how to get quickly started with running the model.
First make sure to pip install -U transformers, then copy the snippet from the section that is relevant for your usecase.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2", device_map="auto")
input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2", quantization_config = BitsAndBytesConfig(load_in_4bit=True))
input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0])
Hebrew-Gemma-11B-V2 is a pretrained base model and therefore does not have any moderation mechanisms.