Quantization made by Richard Erkhov.

Tess-10.7B-v2.0 - GGUF

Model creator: https://huggingface.co/Joseph717171/
Original model: https://huggingface.co/Joseph717171/Tess-10.7B-v2.0/

Name	Quant method	Size
Tess-10.7B-v2.0.Q2_K.gguf	Q2_K	3.73GB
Tess-10.7B-v2.0.IQ3_XS.gguf	IQ3_XS	4.14GB
Tess-10.7B-v2.0.IQ3_S.gguf	IQ3_S	4.37GB
Tess-10.7B-v2.0.Q3_K_S.gguf	Q3_K_S	4.34GB
Tess-10.7B-v2.0.IQ3_M.gguf	IQ3_M	4.51GB
Tess-10.7B-v2.0.Q3_K.gguf	Q3_K	4.84GB
Tess-10.7B-v2.0.Q3_K_M.gguf	Q3_K_M	4.84GB
Tess-10.7B-v2.0.Q3_K_L.gguf	Q3_K_L	5.26GB
Tess-10.7B-v2.0.IQ4_XS.gguf	IQ4_XS	5.43GB
Tess-10.7B-v2.0.Q4_0.gguf	Q4_0	5.66GB
Tess-10.7B-v2.0.IQ4_NL.gguf	IQ4_NL	5.72GB
Tess-10.7B-v2.0.Q4_K_S.gguf	Q4_K_S	5.7GB
Tess-10.7B-v2.0.Q4_K.gguf	Q4_K	6.02GB
Tess-10.7B-v2.0.Q4_K_M.gguf	Q4_K_M	6.02GB
Tess-10.7B-v2.0.Q4_1.gguf	Q4_1	6.27GB
Tess-10.7B-v2.0.Q5_0.gguf	Q5_0	6.89GB
Tess-10.7B-v2.0.Q5_K_S.gguf	Q5_K_S	6.89GB
Tess-10.7B-v2.0.Q5_K.gguf	Q5_K	7.08GB
Tess-10.7B-v2.0.Q5_K_M.gguf	Q5_K_M	7.08GB
Tess-10.7B-v2.0.Q5_1.gguf	Q5_1	7.51GB
Tess-10.7B-v2.0.Q6_K.gguf	Q6_K	8.2GB
Tess-10.7B-v2.0.Q8_0.gguf	Q8_0	10.62GB

Original model description:

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.