najabba
/

MNLP_M3_quantized_model

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

najabba commited on Jun 10, 2025

Commit

c3560bc

·

verified ·

1 Parent(s): bdaa8ff

Upload Qwen3ForCausalLM

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -37,7 +37,7 @@
   "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "use_cache": false,
   "use_sliding_window": false,

   "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
+  "torch_dtype": "float16",
   "transformers_version": "4.51.3",
   "use_cache": false,
   "use_sliding_window": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da77febec96c015b0a890830ce8db77336f24fba194a05649e7c1974302fb63
-size 850183031

 version https://git-lfs.github.com/spec/v1
+oid sha256:daff9fbb6826220c3543b1c4022f177824a397e4e25afa32273b0090e123d915
+size 538883098