Hugging Face's logo

Spaces:
limcheekin
/
replit-code-v1_5-3b-GGUF
Sleeping

App Files Community
replit-code-v1_5-3b-GGUF

Commit History

chore: updated models and Q8_0 to F16
a525bd4

limcheekin commited on

chore: updated model file link
86b6183

limcheekin commited on

feat: updated from F16 to Q8_0 to fix slow loading
ec314a6

limcheekin commited on

feat: updated model download url and n_ctx param
3cfa708

limcheekin commited on

feat: updated to replit-code-v1_5-3b-GGUF model
2a40a34

limcheekin commited on

feat: updated to refact-1.6B-fim-f16-GGUF model
9ff8a21

limcheekin commited on

feat: updated to agentlm-7B-GGUF model
0a542dc

limcheekin commited on

feat: updated to WizardCoder-Python-7B-V1.0-GGUF model
ed5be76

limcheekin commited on

feat: changed to dolphin-2.1-mistral-7B-GGUF model
c968716

limcheekin commited on

feat: updated for Mistral-7B-OpenOrca-GGUF model
94e3839

limcheekin commited on

feat: enabled the embeddings endpoint
6c3814d

limcheekin commited on

chore: removed OPENBLAS_NUM_THREADS as no performance improvement had been observed.
41122b6

limcheekin commited on

chore: updated OPENBLAS_NUM_THREADS to 2.
db6f5ea

limcheekin commited on

chore: added OPENBLAS_NUM_THREADS to specify the number of threads used by the OpenBLAS.
36e1e32

limcheekin commited on

feat: added notebook on how to use the api and updated index.html to include the link to the notebook
19485c0

limcheekin commited on

feat: added Mistral-7B-Instruct-v0.1-GGUF (Q4_K_M) model
8a4f00d

limcheekin commited on

updated for the CodeLlama-13B-oasst-sft-v10-GGUF (Q4_K_M) model
52a27ed

limcheekin commited on

Duplicate from limcheekin/WizardCoder-Python-13B-V1.0-GGUF
106db30

limcheekin commited on