12f1b24387a7880ff45968e730b754aab4a86b1dda339487b8e15c00bd3b0eb4

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "/model/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "amp": true,
+      "batch_size": 1,
+      "data_type": "int",
+      "dynamic_max_gap": -1,
+      "enable_full_range": false,
+      "enable_minmax_tuning": true,
+      "enable_quanted_input": true,
+      "gradient_accumulate_steps": 1,
+      "iters": 200,
+      "low_gpu_mem_usage": true,
+      "lr": null,
+      "lr_scheduler": null,
+      "minmax_lr": null,
+      "nblocks": 1,
+      "not_use_best_mse": false,
+      "nsamples": 512,
+      "quantizer": "gptqmodel:0.9.8-dev0",
+      "sampler": "rand",
+      "scale_dtype": "fp16",
+      "seed": 42,
+      "seqlen": 2048
+    },
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "auto_round",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa590c869b52e9788c52646c6ba632afedf92752b0897d7ef369449b662fc7f2
+size 767343824

quantize_config.json

@@ -0,0 +1,37 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "lm_head": false,
+  "damp_percent": 0.01,
+  "true_sequential": true,
+  "model_name_or_path": "",
+  "model_file_base_name": "model",
+  "quant_method": "auto_round",
+  "checkpoint_format": "gptq",
+  "meta": {
+    "quantizer": "gptqmodel:0.9.8-dev0",
+    "enable_full_range": false,
+    "batch_size": 1,
+    "amp": true,
+    "lr_scheduler": null,
+    "enable_quanted_input": true,
+    "enable_minmax_tuning": true,
+    "lr": null,
+    "minmax_lr": null,
+    "low_gpu_mem_usage": true,
+    "iters": 200,
+    "seqlen": 2048,
+    "nsamples": 512,
+    "sampler": "rand",
+    "seed": 42,
+    "nblocks": 1,
+    "gradient_accumulate_steps": 1,
+    "not_use_best_mse": false,
+    "dynamic_max_gap": -1,
+    "data_type": "int",
+    "scale_dtype": "fp16"
+  }
+}

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 +1,43 @@
+{
+  "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>",
+  "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
+}