EricSpencer00/chattla-20b at main

86.4 GB

1 contributor

History: 12 commits

EricSpencer00's picture

v11: add Q8_0 GGUF (21 GB, harmony TEMPLATE fix)

d06da4d verified about 13 hours ago

eval
Add v10 benchmark results (single-shot, 20 problems) about 15 hours ago
gguf
v11: add Q8_0 GGUF (21 GB, harmony template fix) about 13 hours ago
.gitattributes

1.7 kB

v11: add Q8_0 GGUF (21 GB, harmony template fix) about 13 hours ago
README.md

7.04 kB

v11: updated README with working harmony Modelfile template about 13 hours ago
chat_template.jinja

16.7 kB

ChatTLA v10 — fine-tuned gpt-oss-20b for TLA+ spec generation about 21 hours ago
config.json

1.64 kB

ChatTLA v10 — fine-tuned gpt-oss-20b for TLA+ spec generation about 21 hours ago
generation_config.json

171 Bytes

ChatTLA v10 — fine-tuned gpt-oss-20b for TLA+ spec generation about 21 hours ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.BFloat16Storage"
What is a pickle import?
41.8 GB
xet

ChatTLA v10 — fine-tuned gpt-oss-20b for TLA+ spec generation about 21 hours ago
tokenizer.json

27.9 MB
xet

ChatTLA v10 — fine-tuned gpt-oss-20b for TLA+ spec generation about 21 hours ago
tokenizer_config.json

351 Bytes

ChatTLA v10 — fine-tuned gpt-oss-20b for TLA+ spec generation about 21 hours ago