Upload folder using huggingface_hub

config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "THUDM/glm-4v-9b",
+  "add_bias_linear": false,
+  "add_qkv_bias": true,
+  "apply_query_key_layer_scaling": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "ChatGLMModel"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "auto_map": {
+    "AutoConfig": "THUDM/glm-4v-9b--configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "THUDM/glm-4v-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "THUDM/glm-4v-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "THUDM/glm-4v-9b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "THUDM/glm-4v-9b--modeling_chatglm.ChatGLMForSequenceClassification"
+  },
+  "bias_dropout_fusion": true,
+  "boi_token_id": 151339,
+  "classifier_dropout": null,
+  "eoi_token_id": 151340,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "ffn_hidden_size": 13696,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "kv_channels": 128,
+  "layernorm_epsilon": 1.5625e-07,
+  "model_type": "chatglm",
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_layers": 40,
+  "original_rope": true,
+  "pad_token_id": 151329,
+  "padded_vocab_size": 151552,
+  "post_layer_norm": true,
+  "pre_seq_len": null,
+  "prefix_projection": false,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "group_size": 128,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rmsnorm": true,
+  "rope_ratio": 1,
+  "seq_length": 8192,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "vision_config": {
+    "dropout_prob": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1792,
+    "image_size": 1120,
+    "in_channels": 3,
+    "intermediate_size": 15360,
+    "layer_norm_eps": 1e-06,
+    "num_heads": 16,
+    "num_hidden_layers": 63,
+    "num_positions": 6401,
+    "patch_size": 14,
+    "scaling_factor": 8
+  },
+  "vocab_size": 151552
+}

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5cb1583ef07d050192d3703cc1a48e9e2bea64a9c4ede1bd61236c6a6e052e2
+size 9138334800

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq"
+}