Upload folder using huggingface_hub (#2)

- ca58aaf60f62ed98d37613145c46495dadb4ba22ab0492a31c859e11044e4184 (f091c34f21ad5285e8ac52ba2db2e40f8934b383)
- 96b274f300f033cb922057c0c7a759a4506ae28816248bf080c8b3315693636d (63399cf655b8363529af2a5b91f28dd4da947fec)

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/migtissera-Tess-XS-v1-3-yarn-128K-bnb-4bit-smashed",
-                                                 trust_remote_code=True)
+                                                 trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("migtissera/Tess-XS-v1-3-yarn-128K")
     
     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/tmpl6mfsy9f",
+  "_name_or_path": "/tmp/tmprli0219s",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -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 sha256:45d86d28c8f481ff635a82f5b3054e7d70fc8b031ba8aafd762b86c5a4e257d8
-size 4125687633
+oid sha256:b6c0d1c5c506bfc586096add48fa5f69a77d9a3fd244ecb8dd1adc662cb81f89
+size 4450837496

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsm3iv7rcd",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsc_4h8yxk",
         "batch_size": 1,
         "model_name": "migtissera/Tess-XS-v1-3-yarn-128K",
         "pruning_ratio": 0.0,