Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./test_llama1.1b_W4A16_channel_compressed",
+  "_name_or_path": "/network/sadkins/llama1.1b_W4A16_channel_compressed",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -38,7 +38,7 @@
     },
     "sparsity_config": {
       "format": "dense",
-      "global_sparsity": 19.26420974588696,
+      "global_sparsity": 19.09593405666055,
       "registry_requires_subclass": false,
       "sparsity_structure": "unstructured"
     }
@@ -59,7 +59,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.39.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.39.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c34de4541f8c5b1f8c28db806396483cd474c4f3521b6985d42dd8c0486cb2
+oid sha256:e0e68908a6e7a66b8402436e489d5f439163752faa77f5ed61fd095728ef0ce4
 size 1011146888

recipe.yaml

@@ -0,0 +1,9 @@
+test_stage:
+  quant_modifiers:
+    vLLMQuantizationModifier:
+      ignore: [lm_head]
+      config_groups:
+        group_0:
+          weights: {num_bits: 4, type: int, symmetric: true, strategy: channel}
+          targets: [Linear]
+    SparseGPTModifier: {sparsity: 0.0, quantize: true, sequential_update: false}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}