Upload folder using huggingface_hub

config.json

@@ -1,231 +1,26 @@
 {
-    "version": "0.17.0.post1",
-    "pretrained_config": {
-        "mlp_bias": false,
-        "attn_bias": false,
-        "rotary_base": 10000.0,
-        "rotary_scaling": null,
-        "residual_mlp": false,
-        "disable_weight_only_quant_plugin": false,
-        "moe": {
-            "num_experts": 0,
-            "shared_expert_intermediate_size": 0,
-            "top_k": 0,
-            "normalization_mode": null,
-            "sparse_mixer_epsilon": 0.01,
-            "tp_mode": 0,
-            "device_limited_n_group": 0,
-            "device_limited_topk_group": 0,
-            "device_limited_routed_scaling_factor": 1.0
-        },
-        "remove_duplicated_kv_heads": false,
-        "fc_after_embed": false,
-        "use_input_layernorm_in_first_layer": true,
-        "use_last_layernorm": true,
-        "layer_idx_offset": 0,
-        "embedding_multiplier": 1.0,
-        "attention_multiplier": 1.0,
-        "residual_multiplier": 1.0,
-        "output_multiplier_scale": 1.0,
-        "architecture": "LlamaForCausalLM",
-        "dtype": "bfloat16",
-        "vocab_size": 32000,
-        "hidden_size": 2048,
-        "num_hidden_layers": 22,
-        "num_attention_heads": 32,
-        "hidden_act": "silu",
-        "logits_dtype": "float16",
-        "norm_epsilon": 1e-05,
-        "runtime_defaults": null,
-        "position_embedding_type": "rope_gpt_neox",
-        "num_key_value_heads": 4,
-        "intermediate_size": 5632,
-        "max_position_embeddings": 2048,
-        "mapping": {
-            "world_size": 1,
-            "gpus_per_node": 8,
-            "cp_size": 1,
-            "tp_size": 1,
-            "pp_size": 1,
-            "moe_tp_size": 1,
-            "moe_ep_size": 1,
-            "auto_parallel": false
-        },
-        "quantization": {
-            "quant_algo": "FP8",
-            "kv_cache_quant_algo": "FP8",
-            "group_size": 128,
-            "smoothquant_val": 0.5,
-            "clamp_val": null,
-            "use_meta_recipe": false,
-            "has_zero_point": false,
-            "pre_quant_scale": false,
-            "exclude_modules": [
-                "transformer.layers.14.post_layernorm",
-                "transformer.layers.4.post_layernorm",
-                "transformer.layers.2.input_layernorm",
-                "transformer.vocab_embedding",
-                "transformer.layers.7.input_layernorm",
-                "transformer.layers.18.input_layernorm",
-                "lm_head",
-                "transformer.layers.20.input_layernorm",
-                "transformer.layers.10.post_layernorm",
-                "transformer.layers.16.input_layernorm",
-                "transformer.layers.8.input_layernorm",
-                "transformer.layers.1.input_layernorm",
-                "transformer.layers.20.post_layernorm",
-                "transformer.layers.14.input_layernorm",
-                "transformer.layers.3.post_layernorm",
-                "transformer.layers.17.input_layernorm",
-                "transformer.layers.17.post_layernorm",
-                "transformer.layers.13.input_layernorm",
-                "transformer.layers.21.input_layernorm",
-                "transformer.layers.5.input_layernorm",
-                "transformer.layers.6.post_layernorm",
-                "transformer.layers.19.input_layernorm",
-                "transformer.layers.12.post_layernorm",
-                "transformer.layers.21.post_layernorm",
-                "transformer.layers.11.input_layernorm",
-                "transformer.layers.0.post_layernorm",
-                "transformer.layers.16.post_layernorm",
-                "transformer.layers.4.input_layernorm",
-                "transformer.layers.11.post_layernorm",
-                "transformer.layers.8.post_layernorm",
-                "transformer.layers.6.input_layernorm",
-                "transformer.layers.3.input_layernorm",
-                "transformer.layers.10.input_layernorm",
-                "transformer.layers.1.post_layernorm",
-                "transformer.layers.15.input_layernorm",
-                "transformer.layers.0.input_layernorm",
-                "transformer.layers.9.input_layernorm",
-                "transformer.layers.15.post_layernorm",
-                "transformer.layers.18.post_layernorm",
-                "transformer.layers.2.post_layernorm",
-                "transformer.layers.13.post_layernorm",
-                "transformer.layers.7.post_layernorm",
-                "transformer.layers.12.input_layernorm",
-                "transformer.ln_f",
-                "transformer.layers.9.post_layernorm",
-                "transformer.layers.5.post_layernorm",
-                "transformer.layers.19.post_layernorm"
-            ]
-        },
-        "use_parallel_embedding": true,
-        "embedding_sharding_dim": 0,
-        "head_size": 64,
-        "qk_layernorm": false,
-        "rotary_embedding_dim": 64,
-        "producer": {
-            "name": "modelopt",
-            "version": "0.23.2"
-        },
-        "share_embedding_table": false,
-        "bias": false,
-        "rotary_pct": 1.0,
-        "rank": 0,
-        "decoder": "llama",
-        "rmsnorm": true,
-        "lm_head_bias": false,
-        "tie_word_embeddings": false,
-        "model_type": "llama"
-    },
-    "build_config": {
-        "max_input_len": 4096,
-        "max_seq_len": 4096,
-        "opt_batch_size": 8,
-        "max_batch_size": 1,
-        "max_beam_width": 1,
-        "max_num_tokens": 4096,
-        "opt_num_tokens": null,
-        "max_prompt_embedding_table_size": 0,
-        "kv_cache_type": "PAGED",
-        "gather_context_logits": false,
-        "gather_generation_logits": false,
-        "strongly_typed": true,
-        "force_num_profiles": null,
-        "profiling_verbosity": "layer_names_only",
-        "enable_debug_output": false,
-        "max_draft_len": 0,
-        "speculative_decoding_mode": 1,
-        "use_refit": false,
-        "input_timing_cache": null,
-        "output_timing_cache": "model.cache",
-        "lora_config": {
-            "lora_dir": [],
-            "lora_ckpt_source": "hf",
-            "max_lora_rank": 64,
-            "lora_target_modules": [],
-            "trtllm_modules_to_hf_modules": {}
-        },
-        "auto_parallel_config": {
-            "world_size": 1,
-            "gpus_per_node": 8,
-            "cluster_key": null,
-            "cluster_info": null,
-            "sharding_cost_model": "alpha_beta",
-            "comm_cost_model": "alpha_beta",
-            "enable_pipeline_parallelism": false,
-            "enable_shard_unbalanced_shape": false,
-            "enable_shard_dynamic_shape": false,
-            "enable_reduce_scatter": true,
-            "builder_flags": null,
-            "debug_mode": false,
-            "infer_shape": true,
-            "validation_mode": false,
-            "same_buffer_io": {},
-            "same_spec_io": {},
-            "sharded_io_allowlist": [],
-            "fill_weights": false,
-            "parallel_config_cache": null,
-            "profile_cache": null,
-            "dump_path": null,
-            "debug_outputs": []
-        },
-        "weight_sparsity": false,
-        "weight_streaming": false,
-        "plugin_config": {
-            "dtype": "bfloat16",
-            "bert_attention_plugin": "auto",
-            "gpt_attention_plugin": "auto",
-            "gemm_plugin": null,
-            "explicitly_disable_gemm_plugin": false,
-            "gemm_swiglu_plugin": null,
-            "fp8_rowwise_gemm_plugin": null,
-            "qserve_gemm_plugin": null,
-            "identity_plugin": null,
-            "nccl_plugin": null,
-            "lora_plugin": null,
-            "weight_only_groupwise_quant_matmul_plugin": null,
-            "weight_only_quant_matmul_plugin": null,
-            "smooth_quant_plugins": true,
-            "smooth_quant_gemm_plugin": null,
-            "layernorm_quantization_plugin": null,
-            "rmsnorm_quantization_plugin": null,
-            "quantize_per_token_plugin": false,
-            "quantize_tensor_plugin": false,
-            "moe_plugin": "auto",
-            "mamba_conv1d_plugin": "auto",
-            "low_latency_gemm_plugin": null,
-            "low_latency_gemm_swiglu_plugin": null,
-            "context_fmha": true,
-            "bert_context_fmha_fp32_acc": false,
-            "paged_kv_cache": true,
-            "remove_input_padding": true,
-            "reduce_fusion": false,
-            "user_buffer": false,
-            "tokens_per_block": 64,
-            "use_paged_context_fmha": true,
-            "use_fp8_context_fmha": true,
-            "multiple_profiles": true,
-            "paged_state": false,
-            "streamingllm": false,
-            "manage_weights": false,
-            "use_fused_mlp": true,
-            "pp_reduce_scatter": false
-        },
-        "use_strip_plan": false,
-        "max_encoder_input_len": 1024,
-        "monitor_memory": false,
-        "use_mrope": false
-    }
-}
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.707406759262085,
+    "eval_logits/rejected": -2.656524419784546,
+    "eval_logps/chosen": -370.1297607421875,
+    "eval_logps/rejected": -296.0738525390625,
+    "eval_loss": 0.513750433921814,
+    "eval_rewards/accuracies": 0.738095223903656,
+    "eval_rewards/chosen": -0.02744222804903984,
+    "eval_rewards/margins": 1.0087225437164307,
+    "eval_rewards/rejected": -1.03616464138031,
+    "eval_runtime": 93.5908,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 21.37,
+    "eval_steps_per_second": 0.673
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.0"
+}

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 +1,40 @@
+{
+  "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
+}