Upload 2 files

int4_weight_only/1-gpu/config.json

@@ -0,0 +1,48 @@
+{
+    "chatglm_version": "chatglm3",
+    "add_bias_linear": false,
+    "add_qkv_bias": true,
+    "apply_query_key_layer_scaling": false,
+    "apply_residual_connection_post_layernorm": false,
+    "rmsnorm": true,
+    "rotary_pct": 0.5,
+    "rotary_base": 500000.0,
+    "rotary_scaling": null,
+    "architecture": "ChatGLMModel",
+    "dtype": "float16",
+    "vocab_size": 65024,
+    "hidden_size": 4096,
+    "num_hidden_layers": 28,
+    "num_attention_heads": 32,
+    "hidden_act": "swiglu",
+    "logits_dtype": "float32",
+    "norm_epsilon": 1e-05,
+    "position_embedding_type": "rope_gptj",
+    "max_position_embeddings": 32768,
+    "num_key_value_heads": 2,
+    "intermediate_size": 13696,
+    "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
+    },
+    "quantization": {
+        "quant_algo": "W4A16",
+        "kv_cache_quant_algo": null,
+        "group_size": 128,
+        "smoothquant_val": 0.5,
+        "clamp_val": null,
+        "has_zero_point": false,
+        "pre_quant_scale": false,
+        "exclude_modules": null
+    },
+    "use_parallel_embedding": false,
+    "embedding_sharding_dim": 0,
+    "share_embedding_table": false,
+    "head_size": 128,
+    "qk_layernorm": false
+}

int4_weight_only/1-gpu/rank0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2824a51cc2726461ee954e0c5a271c6bff56448c073b91dd27f56d29463108ff
+size 3940415480