Downloads · 30 days
92
7% of all-time downloads
RichardErkhov/migtissera_-_Tess-2.0-Yi-34B-200K-gguf
migtissera_-_Tess-2.0-Yi-34B-200K-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
92
7% of all-time downloads
All-time downloads
1.4K
Public
Repo size
389 GB
Likes
0
Public
Click a slice to open those files.
.gguf451 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Tess-2.0-Yi-34B-200K - GGUF
| Name | Quant method | Size |
|---|---|---|
| Tess-2.0-Yi-34B-200K.Q2_K.gguf | Q2_K | 11.94GB |
| Tess-2.0-Yi-34B-200K.IQ3_XS.gguf | IQ3_XS | 13.26GB |
| Tess-2.0-Yi-34B-200K.IQ3_S.gguf | IQ3_S | 13.99GB |
| Tess-2.0-Yi-34B-200K.Q3_K_S.gguf | Q3_K_S | 13.93GB |
| Tess-2.0-Yi-34B-200K.IQ3_M.gguf | IQ3_M | 14.5GB |
| Tess-2.0-Yi-34B-200K.Q3_K.gguf | Q3_K | 15.51GB |
| Tess-2.0-Yi-34B-200K.Q3_K_M.gguf | Q3_K_M | 15.51GB |
| Tess-2.0-Yi-34B-200K.Q3_K_L.gguf | Q3_K_L | 16.89GB |
| Tess-2.0-Yi-34B-200K.IQ4_XS.gguf | IQ4_XS | 17.36GB |
| Tess-2.0-Yi-34B-200K.Q4_0.gguf | Q4_0 | 18.13GB |
| Tess-2.0-Yi-34B-200K.IQ4_NL.gguf | IQ4_NL | 18.3GB |
| Tess-2.0-Yi-34B-200K.Q4_K_S.gguf | Q4_K_S | 18.25GB |
| Tess-2.0-Yi-34B-200K.Q4_K.gguf | Q4_K | 19.24GB |
| Tess-2.0-Yi-34B-200K.Q4_K_M.gguf | Q4_K_M | 19.24GB |
| Tess-2.0-Yi-34B-200K.Q4_1.gguf | Q4_1 | 20.1GB |
| Tess-2.0-Yi-34B-200K.Q5_0.gguf | Q5_0 | 22.08GB |
| Tess-2.0-Yi-34B-200K.Q5_K_S.gguf | Q5_K_S | 22.08GB |
| Tess-2.0-Yi-34B-200K.Q5_K.gguf | Q5_K | 22.65GB |
| Tess-2.0-Yi-34B-200K.Q5_K_M.gguf | Q5_K_M | 22.65GB |
| Tess-2.0-Yi-34B-200K.Q5_1.gguf | Q5_1 | 24.05GB |
| Tess-2.0-Yi-34B-200K.Q6_K.gguf | Q6_K | 26.28GB |
| Tess-2.0-Yi-34B-200K.Q8_0.gguf | Q8_0 | 34.03GB |
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-2.0-Yi-34B-200K was trained on the 01-ai/Yi-34B-200K base.
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
<br>

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "migtissera/Tess-2.0-Yi-34B-200K"
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")
<br>
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.
<br>