Upload folder using huggingface_hub (#3)

- 0671e26f57cb7a1b151a02472f7385a87d02622f62ae61a4028611ff861a7114 (73c23c87722604443e2c3b9a6621c82c39d5aab3)

README.md

@@ -34,7 +34,7 @@ tags:
 
 ## Results
 
-Detailed efficiency metrics coming soon!
+![image info](./plots.png)
 
 **Frequently Asked Questions**
 - ***How does the compression work?*** The model is compressed with llm-int8.
@@ -61,7 +61,7 @@ You can run the smashed model with these steps:
    from transformers import AutoModelForCausalLM, AutoTokenizer
 
     model = AutoModelForCausalLM.from_pretrained("PrunaAI/facebook-incoder-1B-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("facebook/incoder-1B")
     
     input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/tmp6pwa02cn",
+  "_name_or_path": "/tmp/tmpxga6aiv_",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "architectures": [
@@ -22,7 +22,7 @@
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": [

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4823e9cdd67f4f021a38b6e75093f29ec67b7d3971365b45688d20afcb302c52
-size 831663481
+oid sha256:7aed32a562166691a351151420ab5803bd1fc5d75010cbd589cc1f36713701cd
+size 887798840

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsv1u9wak1",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsdlhmj_nd",
         "batch_size": 1,
         "model_name": "facebook/incoder-1B",
         "pruning_ratio": 0.0,