We lifted 17 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| lianjiatech/belle | canonical | 7 of 17 |
| Function | Status | Where it lives |
|---|---|---|
| find_layers | Ran | lianjiatech/belle/models/gptq/modelutils.py code served (permissive licence) · get_code("a9e7f2cdf016b88b") |
| get_bloom | Ran | lianjiatech/belle/models/gptq/bloom.py code served (permissive licence) · get_code("cd666c16d4aaa66d") |
| get_llama | Ran | lianjiatech/belle/models/gptq/llama.py code served (permissive licence) · get_code("88d590323ed219c8") |
| quantize | Ran | lianjiatech/belle/models/gptq/quant.py code served (permissive licence) · get_code("50ceff9d34d96d60") |
| read_data | Ran | lianjiatech/belle/eval/generation_html.py code served (permissive licence) · get_code("d273809d732ec42f") |
| write_result_chunk | Ran | lianjiatech/belle/models/decrypt.py code served (permissive licence) · get_code("abee36b2437e1ffd") |
| xor_bytes | Ran | lianjiatech/belle/models/decrypt.py code served (permissive licence) · get_code("9638c3be1c6b03d1") |
| bloom_pack | Not yet run | lianjiatech/belle/models/gptq/bloom.py code served (permissive licence) · get_code("3861600d453a9d43") |
| bloom_sequential | Not yet run | lianjiatech/belle/models/gptq/bloom.py code served (permissive licence) · get_code("f1450934dfa7e840") |
| get_c4 | Not yet run | lianjiatech/belle/models/gptq/datautils.py code served (permissive licence) · get_code("91dba77fa391e15e") |
| get_ptb | Not yet run | lianjiatech/belle/models/gptq/datautils.py code served (permissive licence) · get_code("c1c9acf2a2b2ad95") |
| get_wikitext2 | Not yet run | lianjiatech/belle/models/gptq/datautils.py code served (permissive licence) · get_code("58476252d7ce923b") |
| llama_pack | Not yet run | lianjiatech/belle/models/gptq/llama.py code served (permissive licence) · get_code("7f1c42c308933cd9") |
| llama_sequential | Not yet run | lianjiatech/belle/models/gptq/llama.py code served (permissive licence) · get_code("5f5434220ca9b107") |
| load_quant | Not yet run | lianjiatech/belle/models/gptq/bloom_inference.py code served (permissive licence) · get_code("4b1d6ad992ab7654") |
| load_quant | Not yet run | lianjiatech/belle/models/gptq/llama_inference.py code served (permissive licence) · get_code("aa8b0294a8126264") |
| load_quant | Not yet run | lianjiatech/belle/models/gptq/llama_inference_offload.py code served (permissive licence) · get_code("6cf8c1ef38ec0eb8") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper presents the development and evaluation of ChatHome, a domain-specific language model (DSLM) designed for the intricate field of home renovation. Considering the proven competencies of large language models (LLMs) like GPT-4 and the escalating fascination with home renovation, this study endeavors to reconcile these aspects by generating a dedicated model that can yield high-fidelity, precise outputs relevant to the home renovation arena. ChatHome's novelty rests on its methodology, fusing domain-adaptive pretraining and instruction-tuning over an extensive dataset. This dataset includes professional articles, standard documents, and web content pertinent to home renovation. This dual-pronged strategy is designed to ensure that our model can assimilate comprehensive domain knowledge and effectively address user inquiries. Via thorough experimentation on diverse datasets, both universal and domain-specific, including the freshly introduced "EvalHome" domain dataset, we substantiate that ChatHome not only amplifies domain-specific functionalities but also preserves its versatility.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2307.15290")
get_code_for_paper("2307.15290")
have("2307.15290")
Connect an agent — have() is free.