Upload folder using huggingface_hub (#3)

- 399873850f024afd6ac1839575b7a64b80a70154e565e471dc59f8b37bab8425 (6f9e82e83a0ecdb413232463aa81aafe3e4985d5)
- 1c9482b98633f18c141806bf3a90e418e42aa42df259c019dadbe68b8b6083fa (91b206bc2696c39c2b5ce0775849d581d90f1fe9)

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/01-ai-Yi-6B-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-6B")
     
     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/tmpwo3vg3ob",
+  "_name_or_path": "/tmp/tmp2do5pilt",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -21,7 +21,7 @@
   "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 sha256:7fe2e98346907131790a0c14f4ff12788ead71f0b48192707110d87725b9d511
-size 3905658590
+oid sha256:739af595d5cdcaaa99c269a662e929327519f8cb3edad90d6f9234308ea82684
+size 4163527680

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/models7d7zkr8g",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsyrmoplk0",
         "batch_size": 1,
         "model_name": "01-ai/Yi-6B",
         "pruning_ratio": 0.0,