Downloads · 30 days
93
2% of all-time downloads
CortexLM_-_btlm-7b-base-v0.2-gguf
RichardErkhov/CortexLM_-_btlm-7b-base-v0.2-gguf
CortexLM_-_btlm-7b-base-v0.2-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.
All-time downloads
4.1K
Public
Repo size
82.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.4 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 20, 2024
- Updated
- Sep 20, 2024
- SHA
- 82862416
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
btlm-7b-base-v0.2 - GGUF
- Model creator: https://huggingface.co/CortexLM/
- Original model: https://huggingface.co/CortexLM/btlm-7b-base-v0.2/
| Name | Quant method | Size |
|---|---|---|
| btlm-7b-base-v0.2.Q2_K.gguf | Q2_K | 2.72GB |
| btlm-7b-base-v0.2.IQ3_XS.gguf | IQ3_XS | 2.99GB |
| btlm-7b-base-v0.2.IQ3_S.gguf | IQ3_S | 3.12GB |
| btlm-7b-base-v0.2.Q3_K_S.gguf | Q3_K_S | 3.11GB |
| btlm-7b-base-v0.2.IQ3_M.gguf | IQ3_M | 3.2GB |
| btlm-7b-base-v0.2.Q3_K.gguf | Q3_K | 3.38GB |
| btlm-7b-base-v0.2.Q3_K_M.gguf | Q3_K_M | 3.38GB |
| btlm-7b-base-v0.2.Q3_K_L.gguf | Q3_K_L | 3.54GB |
| btlm-7b-base-v0.2.IQ4_XS.gguf | IQ4_XS | 3.62GB |
| btlm-7b-base-v0.2.Q4_0.gguf | Q4_0 | 3.71GB |
| btlm-7b-base-v0.2.IQ4_NL.gguf | IQ4_NL | 3.75GB |
| btlm-7b-base-v0.2.Q4_K_S.gguf | Q4_K_S | 3.91GB |
| btlm-7b-base-v0.2.Q4_K.gguf | Q4_K | 4.2GB |
| btlm-7b-base-v0.2.Q4_K_M.gguf | Q4_K_M | 4.2GB |
| btlm-7b-base-v0.2.Q4_1.gguf | Q4_1 | 4.09GB |
| btlm-7b-base-v0.2.Q5_0.gguf | Q5_0 | 4.46GB |
| btlm-7b-base-v0.2.Q5_K_S.gguf | Q5_K_S | 4.56GB |
| btlm-7b-base-v0.2.Q5_K.gguf | Q5_K | 4.8GB |
| btlm-7b-base-v0.2.Q5_K_M.gguf | Q5_K_M | 4.8GB |
| btlm-7b-base-v0.2.Q5_1.gguf | Q5_1 | 4.84GB |
| btlm-7b-base-v0.2.Q6_K.gguf | Q6_K | 5.63GB |
| btlm-7b-base-v0.2.Q8_0.gguf | Q8_0 | 6.82GB |
Original model description:
license: mit library_name: transformers tags:
- bittensor
- decentralization
- subnet 9 datasets:
- tiiuae/falcon-refinedweb
<img src="https://cdn-uploads.huggingface.co/production/uploads/655a0bdf3ff5ba1b1b1c01b7/y1dKBZh8UhII6wtbs5boj.png" alt="drawing" width="512"/>
🚀 BTLM-7B v0.2
BTLM (Bittensor Language Model) is a collection of pretrained generative text models. This is the repository for the 7B pretrained model, optimized for dialogue use cases and converted for the Hugging Face Transformers format.
Model Details
Bittensor's decentralized subnet 9 facilitated the development and release of the first version of the BTLM-7B model. This initial release comprises a sophisticated large language model designed for a variety of applications.In creating this model, significant effort was made to ensure its effectiveness and safety, setting a new standard in the decentralized open-source AI community.
⛔ This is a pretrained model, which should be further finetuned for most usecases.
Training subnetwork : 9
Checkpoint : 06-06-2024
Top Bittensor Model Checkpoint
Inference
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model = "CortexLM/btlm-7b-base-v0.2"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
)
sequences = pipeline(
"Tell me about decentralization.",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
Benchmark
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---|
LM Evaluation Harness Repository
License
BTLM-7B is licensed under the MIT License, a permissive license that allows for reuse with virtually no restrictions.
- Created
- Sep 20, 2024
- Updated
- Sep 20, 2024