Upload folder using huggingface_hub

README.md

@@ -0,0 +1,19 @@
+
+---
+license: llama2  
+tags:  
+- code
+---
+
+This is a *int8_float16* quantized version of **WizardLM/WizardCoder-Python-7B-V1.0**, quantized using [ctranslate2](https://github.com/OpenNMT/CTranslate2) (see inference instructions there).
+
+**The license/caveats/intended usage is the same as the original model**.  
+The quality of its output may have 
+been negatively affected by the quantization process.  
+
+
+The command run to quantize the model was:
+
+ `ct2-transformers-converter --model ./models-hf/WizardLM/WizardCoder-Python-7B-V1.0 --quantization int8_float16 --output_dir ./models-ct/WizardLM/WizardCoder-Python-7B-V1.0-ct2-int8_float16`
+
+The quantization was run on a 'high-mem', CPU only (8 core, 51GB) colab instance and took approximately 10 minutes.

config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": 1e-05,
+  "unk_token": "</s>"
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b0bfbd0586dfafd5ba579e2cf386bbb419c2308f30e8ba1be8e41047d6b9fd
+size 6744414033