Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1,32 @@
+{%- macro to_text(content) -%}
+{%- if content is string -%}
+{{- content -}}
+{%- elif content is iterable and content is not mapping -%}
+{%- for item in content -%}
+{%- if item is mapping and item.type == 'text' and item.text is defined -%}
+{{- item.text -}}
+{%- elif item is mapping and (item.type == 'audio' or 'audio' in item) -%}
+<|begin_of_audio|><|pad|><|end_of_audio|><|user|>
+{% elif item is string -%}
+{{- item -}}
+{%- endif -%}
+{%- endfor -%}
+{%- else -%}
+{{- content -}}
+{%- endif -%}
+{%- endmacro -%}
+{%- for m in messages -%}
+{%- if m.role == 'system' -%}
+<|system|>
+{{ to_text(m.content) | trim }}
+{%- elif m.role == 'user' -%}
+<|user|>
+{{ to_text(m.content) | trim }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{{ to_text(m.content) | trim }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+<|assistant|>
+{% endif -%}

config.json

@@ -0,0 +1,76 @@
+{
+  "architectures": [
+    "GlmAsrForConditionalGeneration"
+  ],
+  "audio_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "head_dim": 64,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "max_position_embeddings": 1500,
+    "model_type": "glmasr_encoder",
+    "num_attention_heads": 20,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 20,
+    "num_mel_bins": 128,
+    "partial_rotary_factor": 0.5,
+    "rope_parameters": {
+      "partial_rotary_factor": 0.5,
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "audio_token_id": 59260,
+  "dtype": "bfloat16",
+  "hidden_size": 2048,
+  "model_type": "glmasr",
+  "projector_hidden_act": "gelu",
+  "quantization_config": {
+    "autoround_version": "0.9.5",
+    "bits": 4,
+    "block_name_to_quantize": "audio_tower.layers,language_model.model.layers",
+    "data_type": "int",
+    "group_size": 128,
+    "iters": 0,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "sym": true
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+      59246,
+      59253,
+      59255
+    ],
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 8192,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 59264
+  },
+  "transformers_version": "5.0.0.dev0",
+  "vocab_size": 59264
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    59246,
+    59253,
+    59255
+  ],
+  "transformers_version": "5.0.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6141ae61cf6ab57dae5ca7ef36906abb91663383cd0f44494445f1958a8958
+size 1584969104

processor_config.json

@@ -0,0 +1,20 @@
+{
+  "audio_token": "<|pad|>",
+  "default_transcription_prompt": "Please transcribe this audio into text",
+  "feature_extractor": {
+    "chunk_length": 30,
+    "dither": 0.0,
+    "feature_extractor_type": "WhisperFeatureExtractor",
+    "feature_size": 128,
+    "hop_length": 160,
+    "n_fft": 400,
+    "n_samples": 480000,
+    "nb_max_frames": 3000,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "return_attention_mask": false,
+    "sampling_rate": 16000
+  },
+  "max_audio_len": 655,
+  "processor_class": "GlmAsrProcessor"
+}

quantization_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "iters": 0,
+  "autoround_version": "0.9.5",
+  "block_name_to_quantize": "audio_tower.layers,language_model.model.layers",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq"
+}

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|pad|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>"
+  ],
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 65536,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "GlmAsrProcessor",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}