license: apache-2.0
base_model: []
library_name: transformers
tags:
- mergekit
- merge
pipeline_tag: text-generation
Credit for the model card's description goes to ddh0, mergekit, and, migtissera
Inspired by ddh0/Starling-LM-10.7B-beta and ddh0/Mistral-10.7B-Instruct-v0.2
Tess-10.7B-v0.2
Deprecated
"This model is deprecated due to the use of wrong sliding window parameter while training. Will update with the new model link in a couple of days." - migtissera
This is Tess-10.7B-v0.2, a depth-upscaled version of migtissera/Tess-7B-v2.0.
This model is intended to be used as a basis for further fine-tuning, or as a drop-in upgrade from the original 7 billion parameter model.
Paper detailing how Depth-Up Scaling works: SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
This is a merge of pre-trained language models created using mergekit.
Prompt format same as migtissera/Tess-7B-v2.0
Prompt Format:
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
- /Users/jsarnecki/opt/migtissera/Tess-7B-v2.0
Configuration
The following YAML configuration was used to produce this model:
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 24]
model: /Users/jsarnecki/opt/migtissera/Tess-7B-v2.0
- sources:
- layer_range: [8, 32]
model: /Users/jsarnecki/opt/migtissera/Tess-7B-v2.0
GGUFs (Thanks to bartowski)
https://huggingface.co/bartowski/Tess-10.7B-v2.0-GGUF
exl2s (Thanks to bartowski)
https://huggingface.co/bartowski/Tess-10.7B-v2.0-exl2
license: apache-2.0
Tess-7B-v2.0
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-7B-v2.0 was trained on the Mistral-7B-v0.2 base.
Prompt Format:
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
Below shows a code example on how to use this model:
import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "migtissera/Tess-7B-v2.0"
output_file_path = "./conversations.jsonl"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
def generate_text(instruction):
tokens = tokenizer.encode(instruction)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to("cuda")
instance = {
"input_ids": tokens,
"top_p": 1.0,
"temperature": 0.5,
"generate_len": 1024,
"top_k": 50,
}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length + instance["generate_len"],
use_cache=True,
do_sample=True,
top_p=instance["top_p"],
temperature=instance["temperature"],
top_k=instance["top_k"],
num_return_sequences=1,
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
answer = string.split("USER:")[0].strip()
return f"{answer}"
conversation = f"SYSTEM: Answer the question thoughtfully and intelligently. Always answer without hesitation."
while True:
user_input = input("You: ")
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
answer = generate_text(llm_prompt)
print(answer)
conversation = f"{llm_prompt}{answer}"
json_data = {"prompt": user_input, "answer": answer}
## Save your conversation
with open(output_file_path, "a") as output_file:
output_file.write(json.dumps(json_data) + "\n")
Limitations & Biases:
While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
Exercise caution and cross-check information when necessary. This is an uncensored model.