初始化项目,由ModelHub XC社区提供模型

Model: meshllm/olmo-7b-instruct-hf-parity-bf16-mlx
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 07:13:38 +08:00
commit 9eea25a2b4
12 changed files with 251143 additions and 0 deletions

27
README.md Normal file
View File

@@ -0,0 +1,27 @@
---
language: en
pipeline_tag: text-generation
tags:
- mlx
- meshllm
- parity
- same-origin
- olmo
library_name: mlx
license: apache-2.0
---
# OLMo-7B-Instruct-hf Parity BF16 MLX
Same-origin parity artifact derived from `allenai/OLMo-7B-Instruct-hf`.
This repo contains the high-fidelity `bf16` MLX artifact used for mesh-llm backend parity validation against the corresponding GGUF artifact.
Accepted local validation status:
- Exact prompts: MLX now tracks GGUF on the semantic probe set after prompt-render parity fixes, with shared family-level drift on strict one-word canaries
- Behavior smoke: 0 flagged prompts out of 80 on the MT-Bench-derived harness
Paired GGUF repo:
- `meshllm/olmo-7b-instruct-hf-parity-f16-gguf`