Downloads · 30 days
68
5% of all-time downloads
RichardErkhov/macadeliccc_-_gemma-orchid-7b-dpo-gguf
macadeliccc_-_gemma-orchid-7b-dpo-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
68
5% of all-time downloads
All-time downloads
1.3K
Public
Repo size
99.8 GB
Likes
0
Public
Click a slice to open those files.
.gguf116 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
gemma-orchid-7b-dpo - GGUF
| Name | Quant method | Size |
|---|---|---|
| gemma-orchid-7b-dpo.Q2_K.gguf | Q2_K | 3.24GB |
| gemma-orchid-7b-dpo.IQ3_XS.gguf | IQ3_XS | 3.54GB |
| gemma-orchid-7b-dpo.IQ3_S.gguf | IQ3_S | 3.71GB |
| gemma-orchid-7b-dpo.Q3_K_S.gguf | Q3_K_S | 3.71GB |
| gemma-orchid-7b-dpo.IQ3_M.gguf | IQ3_M | 3.82GB |
| gemma-orchid-7b-dpo.Q3_K.gguf | Q3_K | 4.07GB |
| gemma-orchid-7b-dpo.Q3_K_M.gguf | Q3_K_M | 4.07GB |
| gemma-orchid-7b-dpo.Q3_K_L.gguf | Q3_K_L | 4.39GB |
| gemma-orchid-7b-dpo.IQ4_XS.gguf | IQ4_XS | 4.48GB |
| gemma-orchid-7b-dpo.Q4_0.gguf | Q4_0 | 4.67GB |
| gemma-orchid-7b-dpo.IQ4_NL.gguf | IQ4_NL | 4.69GB |
| gemma-orchid-7b-dpo.Q4_K_S.gguf | Q4_K_S | 4.7GB |
| gemma-orchid-7b-dpo.Q4_K.gguf | Q4_K | 4.96GB |
| gemma-orchid-7b-dpo.Q4_K_M.gguf | Q4_K_M | 4.96GB |
| gemma-orchid-7b-dpo.Q4_1.gguf | Q4_1 | 5.12GB |
| gemma-orchid-7b-dpo.Q5_0.gguf | Q5_0 | 5.57GB |
| gemma-orchid-7b-dpo.Q5_K_S.gguf | Q5_K_S | 5.57GB |
| gemma-orchid-7b-dpo.Q5_K.gguf | Q5_K | 5.72GB |
| gemma-orchid-7b-dpo.Q5_K_M.gguf | Q5_K_M | 5.72GB |
| gemma-orchid-7b-dpo.Q5_1.gguf | Q5_1 | 6.02GB |
| gemma-orchid-7b-dpo.Q6_K.gguf | Q6_K | 6.53GB |
| gemma-orchid-7b-dpo.Q8_0.gguf | Q8_0 | 8.45GB |
license: other datasets:

This model is the second checkpoint of a future project. Its capable of function calling as well as having a strong base in communicational skills.
This model has been finetuned on roughly 80k samples so far.
Thermostatic/flowers is a blend of open source model generations formatted in ShareGPT. It also includes all of capybara.
This model has been exposed to a wide variety of data. macadeliccc/gemma-function-calling-7b is suitable to finetune further with the dataset of your choosing.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("macadeliccc/gemma-orchid-7b-dpo")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/gemma-orchid-7b-dpo")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("macadeliccc/gemma-orchid-7b-dpo")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/gemma-orchid-7b-dpo", device_map="auto")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
torch.float16# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("macadeliccc/gemma-orchid-7b-dpo")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/gemma-orchid-7b-dpo", device_map="auto", torch_dtype=torch.float16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
torch.bfloat16# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("macadeliccc/gemma-orchid-7b-dpo")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/gemma-orchid-7b-dpo", device_map="auto", torch_dtype=torch.bfloat16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
bitsandbytes# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("macadeliccc/gemma-orchid-7b-dpo")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/gemma-orchid-7b-dpo", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("macadeliccc/gemma-orchid-7b-dpo")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/gemma-orchid-7b-dpo", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
First make sure to install flash-attn in your environment pip install flash-attn
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
+ attn_implementation="flash_attention_2"
).to(0)
In progress
Available here
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 64.37 |
| AI2 Reasoning Challenge (25-Shot) | 62.88 |
| HellaSwag (10-Shot) | 80.95 |
| MMLU (5-Shot) | 61.41 |
| TruthfulQA (0-shot) | 53.27 |
| Winogrande (5-shot) | 77.51 |
| GSM8k (5-shot) | 50.19 |