Infatoshi/GLM-5.3-UNCENSORED-EXL3-3.0bpw
text-generationexllamav3Verified checksumsexl3glmmoeuncensoredexllamav3safetensors
- License
- mit
- Size
- 273 GB
- Revision
- main
Mirrored from Infatoshi/GLM-5.3-UNCENSORED-EXL3-3.0bpw
All models by Infatoshi →Mirrored from Infatoshi/GLM-5.3-UNCENSORED-EXL3-3.0bpw
All models by Infatoshi →EXL3 quantization of dealignai/GLM-5.3-UNCENSORED-FP8, itself a weight-edited (no fine-tune) variant of zai-org/GLM-5.3. The edit is documented in CRACK_SURGERY.json (copied unchanged from the source repo). This repo is not affiliated with dealignai or Z.ai.
GlmMoeDsaForCausalLM, 753B total parameters, 256 routed experts (8 active) + 1 shared, MLA attention with DSA sparse indexer, 78 layers + 1 MTP layer-b 3.0 --hq; attention and shared experts at 5 bpw, dense MLPs at 4, routed experts at 3), lm_head 6 bpw, mul1 codebookdraft_mode: mtp in TabbyAPI)d3739fd, default calibration (250 rows x 2048 tokens), source read directly from the FP8 checkpointeval/model_diff.py, 20 rows x 2048 tokens of wikitext-2 test:
tau2-bench (airline, retail), Pass^1. Agent temperature 1.0, top_p 0.95; user simulator and judges GPT-4.1 at temperature 0. The reference is stock GLM-5.3 (not the uncensored edit) served at FP8 by Z.ai via OpenRouter, run through the same harness. The difference therefore mixes the dealign weight edit and this quantization.
Per trial: airline baseline 0.740 / 0.680, quant 0.600 / 0.680; retail baseline 0.465 / 0.544, quant 0.482. ± is one binomial standard error. Neither difference is statistically significant at these sample sizes; treat the airline point estimate as a possible small regression rather than a measured one.
Tested with TabbyAPI on 8x A100 40GB, layer split (gpu_split_auto), MTP drafting, 98K-token shared cache.
Tool calling caveat: GLM writes tool arguments as raw text (<arg_value>9523456873</arg_value>). TabbyAPI's glm4_5 parser (as of commit be74bf0) JSON-decodes every value without consulting the tool schema, so string parameters that look like numbers (order and product IDs, zip codes) reach your tools as integers. On tau2-bench retail this caused ~70% of tool calls to fail. Make the parser keep parameters whose schema type is string as raw text before using this model for agents. The evaluation above was run with that fix applied.
MIT, following the upstream GLM-5.3 and dealignai releases.
model: model_name: GLM-5.3-UNCENSORED-EXL3-3.0bpw backend: exllamav3 max_seq_len: 65536 cache_size: 98304 gpu_split_auto: true tool_format: glm4_7 reasoning: truedraft_model: draft_mode: mtp