1d6ee5839cd29b66481f3a49c92e5fd9cad77de5c649f2d51506f3d16a99fe72

README.md

@@ -14,8 +14,8 @@ tags:
 <!-- header start -->
 <!-- 200823 -->
 <div style="width: auto; margin-left: auto; margin-right: auto">
-    <a href="https://docs.pruna.ai/en/latest/setup/pip.html" target="_blank" rel="noopener noreferrer">
-        <img src="https://imgur.com/rVAgqMY.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+    <a href="https://www.pruna.ai/" target="_blank" rel="noopener noreferrer">
+        <img src="https://i.imgur.com/eDAlcgk.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
     </a>
 </div>
 <!-- header end -->
@@ -82,4 +82,4 @@ The license of the smashed model follows the license of the original model. Plea
 ## Want to compress other models?
 
 - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
-- Do it by yourself [here](https://docs.pruna.ai/en/latest/setup/pip.html).
+- Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).

config.json

@@ -1,57 +1,56 @@
 {
-    "_name_or_path": "/covalent/.cache/models/tmprz_p8abo1bk3610p",
-    "architectures": [
-        "LlamaForCausalLM"
+  "_name_or_path": "/home/ubuntu/.cache/pruna/tmp6r_sc64vvr7zr28q",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head"
     ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "head_dim": 64,
-    "hidden_act": "silu",
-    "hidden_size": 576,
-    "initializer_range": 0.041666666666666664,
-    "intermediate_size": 1536,
-    "is_llama_config": true,
-    "max_position_embeddings": 8192,
-    "mlp_bias": false,
-    "model_type": "llama",
-    "num_attention_heads": 9,
-    "num_hidden_layers": 30,
-    "num_key_value_heads": 3,
-    "pad_token_id": 2,
-    "pretraining_tp": 1,
-    "quantization_config": {
-        "_load_in_4bit": false,
-        "_load_in_8bit": true,
-        "bnb_4bit_compute_dtype": "bfloat16",
-        "bnb_4bit_quant_storage": "uint8",
-        "bnb_4bit_quant_type": "fp4",
-        "bnb_4bit_use_double_quant": false,
-        "llm_int8_enable_fp32_cpu_offload": false,
-        "llm_int8_has_fp16_weight": false,
-        "llm_int8_skip_modules": [
-            "lm_head"
-        ],
-        "llm_int8_threshold": 6.0,
-        "load_in_4bit": false,
-        "load_in_8bit": true,
-        "quant_method": "bitsandbytes"
-    },
-    "rms_norm_eps": 1e-05,
-    "rope_interleaved": false,
-    "rope_scaling": null,
-    "rope_theta": 100000,
-    "tie_word_embeddings": true,
-    "torch_dtype": "float16",
-    "transformers.js_config": {
-        "kv_cache_dtype": {
-            "fp16": "float16",
-            "q4f16": "float16"
-        }
-    },
-    "transformers_version": "4.46.2",
-    "use_cache": true,
-    "vocab_size": 49152,
-    "api_key": null
-}
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.46.3"
 }

smash_config.json

@@ -3,13 +3,16 @@
     "comp_ctranslate_active": false,
     "comp_cwhisper_active": false,
     "comp_diffusers2_active": false,
+    "comp_flux_caching_active": false,
     "comp_ifw_active": false,
+    "comp_ipex_llm_active": false,
     "comp_onediff_active": false,
     "comp_step_caching_active": false,
     "comp_torch_compile_active": false,
     "comp_ws2t_active": false,
     "comp_x-fast_active": false,
     "prune_torch-structured_active": false,
+    "prune_torch-unstructured_active": false,
     "quant_aqlm_active": false,
     "quant_awq_active": false,
     "quant_gptq_active": false,
@@ -28,8 +31,8 @@
     "quant_llm-int8_weight_bits": 8,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/covalent/.cache/models/tmprz_p8abo",
+    "cache_dir": "/home/ubuntu/.cache/pruna/tmp6r_sc64v",
     "task": "",
-    "save_load_fn": "bitsandbytes",
+    "save_load_fn": "llm-int8",
     "save_load_fn_args": {}
 }

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}