Upload folder using huggingface_hub

config.json

@@ -0,0 +1,226 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "dense",
+    "global_compression_ratio": 1.883165566487463,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "frozen",
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 0.1436103149318787,
+      "ignore": [
+        "model.layers.0.self_attn.q_proj",
+        "model.layers.0.self_attn.v_proj",
+        "model.layers.0.self_attn.o_proj",
+        "model.layers.0.mlp.gate_proj",
+        "model.layers.0.mlp.up_proj",
+        "model.layers.0.mlp.down_proj",
+        "model.layers.1.self_attn.q_proj",
+        "model.layers.1.self_attn.k_proj",
+        "model.layers.1.self_attn.v_proj",
+        "model.layers.1.self_attn.o_proj",
+        "model.layers.1.mlp.gate_proj",
+        "model.layers.1.mlp.up_proj",
+        "model.layers.1.mlp.down_proj",
+        "model.layers.2.self_attn.q_proj",
+        "model.layers.2.self_attn.k_proj",
+        "model.layers.2.self_attn.v_proj",
+        "model.layers.2.self_attn.o_proj",
+        "model.layers.2.mlp.gate_proj",
+        "model.layers.2.mlp.up_proj",
+        "model.layers.2.mlp.down_proj",
+        "model.layers.3.self_attn.q_proj",
+        "model.layers.3.self_attn.k_proj",
+        "model.layers.3.self_attn.v_proj",
+        "model.layers.3.self_attn.o_proj",
+        "model.layers.3.mlp.gate_proj",
+        "model.layers.3.mlp.up_proj",
+        "model.layers.3.mlp.down_proj",
+        "model.layers.4.self_attn.q_proj",
+        "model.layers.4.self_attn.k_proj",
+        "model.layers.4.self_attn.v_proj",
+        "model.layers.4.self_attn.o_proj",
+        "model.layers.4.mlp.gate_proj",
+        "model.layers.4.mlp.up_proj",
+        "model.layers.4.mlp.down_proj",
+        "model.layers.5.self_attn.q_proj",
+        "model.layers.5.self_attn.k_proj",
+        "model.layers.5.self_attn.v_proj",
+        "model.layers.5.self_attn.o_proj",
+        "model.layers.5.mlp.gate_proj",
+        "model.layers.5.mlp.up_proj",
+        "model.layers.5.mlp.down_proj",
+        "model.layers.6.self_attn.q_proj",
+        "model.layers.6.self_attn.k_proj",
+        "model.layers.6.self_attn.v_proj",
+        "model.layers.6.self_attn.o_proj",
+        "model.layers.6.mlp.gate_proj",
+        "model.layers.6.mlp.up_proj",
+        "model.layers.6.mlp.down_proj",
+        "model.layers.7.self_attn.q_proj",
+        "model.layers.7.self_attn.k_proj",
+        "model.layers.7.self_attn.v_proj",
+        "model.layers.7.self_attn.o_proj",
+        "model.layers.7.mlp.gate_proj",
+        "model.layers.7.mlp.up_proj",
+        "model.layers.7.mlp.down_proj",
+        "model.layers.8.self_attn.q_proj",
+        "model.layers.8.self_attn.k_proj",
+        "model.layers.8.self_attn.v_proj",
+        "model.layers.8.self_attn.o_proj",
+        "model.layers.8.mlp.gate_proj",
+        "model.layers.8.mlp.up_proj",
+        "model.layers.8.mlp.down_proj",
+        "model.layers.9.self_attn.q_proj",
+        "model.layers.9.self_attn.k_proj",
+        "model.layers.9.self_attn.v_proj",
+        "model.layers.9.self_attn.o_proj",
+        "model.layers.9.mlp.gate_proj",
+        "model.layers.9.mlp.up_proj",
+        "model.layers.9.mlp.down_proj",
+        "model.layers.10.self_attn.q_proj",
+        "model.layers.10.self_attn.k_proj",
+        "model.layers.10.self_attn.v_proj",
+        "model.layers.10.self_attn.o_proj",
+        "model.layers.10.mlp.gate_proj",
+        "model.layers.10.mlp.up_proj",
+        "model.layers.10.mlp.down_proj",
+        "model.layers.11.self_attn.q_proj",
+        "model.layers.11.self_attn.k_proj",
+        "model.layers.11.self_attn.v_proj",
+        "model.layers.11.self_attn.o_proj",
+        "model.layers.11.mlp.gate_proj",
+        "model.layers.11.mlp.up_proj",
+        "model.layers.11.mlp.down_proj",
+        "model.layers.12.self_attn.q_proj",
+        "model.layers.12.self_attn.k_proj",
+        "model.layers.12.self_attn.v_proj",
+        "model.layers.12.self_attn.o_proj",
+        "model.layers.12.mlp.gate_proj",
+        "model.layers.12.mlp.up_proj",
+        "model.layers.12.mlp.down_proj",
+        "model.layers.13.self_attn.q_proj",
+        "model.layers.13.self_attn.k_proj",
+        "model.layers.13.self_attn.v_proj",
+        "model.layers.13.self_attn.o_proj",
+        "model.layers.13.mlp.gate_proj",
+        "model.layers.13.mlp.up_proj",
+        "model.layers.13.mlp.down_proj",
+        "model.layers.14.self_attn.q_proj",
+        "model.layers.14.self_attn.k_proj",
+        "model.layers.14.self_attn.v_proj",
+        "model.layers.14.self_attn.o_proj",
+        "model.layers.14.mlp.gate_proj",
+        "model.layers.14.mlp.up_proj",
+        "model.layers.14.mlp.down_proj",
+        "model.layers.15.self_attn.q_proj",
+        "model.layers.15.self_attn.k_proj",
+        "model.layers.15.self_attn.v_proj",
+        "model.layers.15.self_attn.o_proj",
+        "model.layers.15.mlp.gate_proj",
+        "model.layers.15.mlp.up_proj",
+        "model.layers.15.mlp.down_proj",
+        "model.layers.16.self_attn.q_proj",
+        "model.layers.16.self_attn.k_proj",
+        "model.layers.16.self_attn.v_proj",
+        "model.layers.16.self_attn.o_proj",
+        "model.layers.16.mlp.gate_proj",
+        "model.layers.16.mlp.up_proj",
+        "model.layers.16.mlp.down_proj",
+        "model.layers.17.self_attn.q_proj",
+        "model.layers.17.self_attn.k_proj",
+        "model.layers.17.self_attn.v_proj",
+        "model.layers.17.self_attn.o_proj",
+        "model.layers.17.mlp.gate_proj",
+        "model.layers.17.mlp.up_proj",
+        "model.layers.17.mlp.down_proj",
+        "model.layers.18.self_attn.q_proj",
+        "model.layers.18.self_attn.k_proj",
+        "model.layers.18.self_attn.v_proj",
+        "model.layers.18.self_attn.o_proj",
+        "model.layers.18.mlp.gate_proj",
+        "model.layers.18.mlp.up_proj",
+        "model.layers.18.mlp.down_proj",
+        "model.layers.19.self_attn.q_proj",
+        "model.layers.19.self_attn.k_proj",
+        "model.layers.19.self_attn.v_proj",
+        "model.layers.19.self_attn.o_proj",
+        "model.layers.19.mlp.gate_proj",
+        "model.layers.19.mlp.up_proj",
+        "model.layers.19.mlp.down_proj",
+        "model.layers.20.self_attn.q_proj",
+        "model.layers.20.self_attn.k_proj",
+        "model.layers.20.self_attn.v_proj",
+        "model.layers.20.self_attn.o_proj",
+        "model.layers.20.mlp.gate_proj",
+        "model.layers.20.mlp.up_proj",
+        "model.layers.20.mlp.down_proj",
+        "model.layers.21.self_attn.q_proj",
+        "model.layers.21.self_attn.k_proj",
+        "model.layers.21.self_attn.v_proj",
+        "model.layers.21.self_attn.o_proj",
+        "model.layers.21.mlp.gate_proj",
+        "model.layers.21.mlp.up_proj",
+        "model.layers.21.mlp.down_proj",
+        "lm_head"
+      ],
+      "registry_requires_subclass": false,
+      "sparsity_structure": "unstructured",
+      "targets": [
+        "model.layers.0.self_attn.k_proj"
+      ]
+    }
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec20b089f9ed2fc6a1ccd697b76e18a6bf425254a4a589c447c851f1350084b
+size 2222865296

recipe.yaml

@@ -0,0 +1,6 @@
+DEFAULT_stage:
+  DEFAULT_modifiers:
+    GPTQModifier:
+      targets: Linear
+      ignore: [lm_head]
+      scheme: W4A16

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}