Upload folder using huggingface_hub

config.json

@@ -0,0 +1,293 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": 2.074153682854382,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 0.15754637109977196,
+      "ignore": [
+        "model.layers.0.self_attn.v_proj",
+        "model.layers.0.self_attn.o_proj",
+        "model.layers.0.mlp.gate_proj",
+        "model.layers.0.mlp.up_proj",
+        "model.layers.0.mlp.down_proj",
+        "model.layers.1.self_attn.q_proj",
+        "model.layers.1.self_attn.k_proj",
+        "model.layers.1.self_attn.v_proj",
+        "model.layers.1.self_attn.o_proj",
+        "model.layers.1.mlp.gate_proj",
+        "model.layers.1.mlp.up_proj",
+        "model.layers.1.mlp.down_proj",
+        "model.layers.2.self_attn.q_proj",
+        "model.layers.2.self_attn.k_proj",
+        "model.layers.2.self_attn.v_proj",
+        "model.layers.2.self_attn.o_proj",
+        "model.layers.2.mlp.gate_proj",
+        "model.layers.2.mlp.up_proj",
+        "model.layers.2.mlp.down_proj",
+        "model.layers.3.self_attn.q_proj",
+        "model.layers.3.self_attn.k_proj",
+        "model.layers.3.self_attn.v_proj",
+        "model.layers.3.self_attn.o_proj",
+        "model.layers.3.mlp.gate_proj",
+        "model.layers.3.mlp.up_proj",
+        "model.layers.3.mlp.down_proj",
+        "model.layers.4.self_attn.q_proj",
+        "model.layers.4.self_attn.k_proj",
+        "model.layers.4.self_attn.v_proj",
+        "model.layers.4.self_attn.o_proj",
+        "model.layers.4.mlp.gate_proj",
+        "model.layers.4.mlp.up_proj",
+        "model.layers.4.mlp.down_proj",
+        "model.layers.5.self_attn.q_proj",
+        "model.layers.5.self_attn.k_proj",
+        "model.layers.5.self_attn.v_proj",
+        "model.layers.5.self_attn.o_proj",
+        "model.layers.5.mlp.gate_proj",
+        "model.layers.5.mlp.up_proj",
+        "model.layers.5.mlp.down_proj",
+        "model.layers.6.self_attn.q_proj",
+        "model.layers.6.self_attn.k_proj",
+        "model.layers.6.self_attn.v_proj",
+        "model.layers.6.self_attn.o_proj",
+        "model.layers.6.mlp.gate_proj",
+        "model.layers.6.mlp.up_proj",
+        "model.layers.6.mlp.down_proj",
+        "model.layers.7.self_attn.q_proj",
+        "model.layers.7.self_attn.k_proj",
+        "model.layers.7.self_attn.v_proj",
+        "model.layers.7.self_attn.o_proj",
+        "model.layers.7.mlp.gate_proj",
+        "model.layers.7.mlp.up_proj",
+        "model.layers.7.mlp.down_proj",
+        "model.layers.8.self_attn.q_proj",
+        "model.layers.8.self_attn.k_proj",
+        "model.layers.8.self_attn.v_proj",
+        "model.layers.8.self_attn.o_proj",
+        "model.layers.8.mlp.gate_proj",
+        "model.layers.8.mlp.up_proj",
+        "model.layers.8.mlp.down_proj",
+        "model.layers.9.self_attn.q_proj",
+        "model.layers.9.self_attn.k_proj",
+        "model.layers.9.self_attn.v_proj",
+        "model.layers.9.self_attn.o_proj",
+        "model.layers.9.mlp.gate_proj",
+        "model.layers.9.mlp.up_proj",
+        "model.layers.9.mlp.down_proj",
+        "model.layers.10.self_attn.q_proj",
+        "model.layers.10.self_attn.k_proj",
+        "model.layers.10.self_attn.v_proj",
+        "model.layers.10.self_attn.o_proj",
+        "model.layers.10.mlp.gate_proj",
+        "model.layers.10.mlp.up_proj",
+        "model.layers.10.mlp.down_proj",
+        "model.layers.11.self_attn.q_proj",
+        "model.layers.11.self_attn.k_proj",
+        "model.layers.11.self_attn.v_proj",
+        "model.layers.11.self_attn.o_proj",
+        "model.layers.11.mlp.gate_proj",
+        "model.layers.11.mlp.up_proj",
+        "model.layers.11.mlp.down_proj",
+        "model.layers.12.self_attn.q_proj",
+        "model.layers.12.self_attn.k_proj",
+        "model.layers.12.self_attn.v_proj",
+        "model.layers.12.self_attn.o_proj",
+        "model.layers.12.mlp.gate_proj",
+        "model.layers.12.mlp.up_proj",
+        "model.layers.12.mlp.down_proj",
+        "model.layers.13.self_attn.q_proj",
+        "model.layers.13.self_attn.k_proj",
+        "model.layers.13.self_attn.v_proj",
+        "model.layers.13.self_attn.o_proj",
+        "model.layers.13.mlp.gate_proj",
+        "model.layers.13.mlp.up_proj",
+        "model.layers.13.mlp.down_proj",
+        "model.layers.14.self_attn.q_proj",
+        "model.layers.14.self_attn.k_proj",
+        "model.layers.14.self_attn.v_proj",
+        "model.layers.14.self_attn.o_proj",
+        "model.layers.14.mlp.gate_proj",
+        "model.layers.14.mlp.up_proj",
+        "model.layers.14.mlp.down_proj",
+        "model.layers.15.self_attn.q_proj",
+        "model.layers.15.self_attn.k_proj",
+        "model.layers.15.self_attn.v_proj",
+        "model.layers.15.self_attn.o_proj",
+        "model.layers.15.mlp.gate_proj",
+        "model.layers.15.mlp.up_proj",
+        "model.layers.15.mlp.down_proj",
+        "model.layers.16.self_attn.q_proj",
+        "model.layers.16.self_attn.k_proj",
+        "model.layers.16.self_attn.v_proj",
+        "model.layers.16.self_attn.o_proj",
+        "model.layers.16.mlp.gate_proj",
+        "model.layers.16.mlp.up_proj",
+        "model.layers.16.mlp.down_proj",
+        "model.layers.17.self_attn.q_proj",
+        "model.layers.17.self_attn.k_proj",
+        "model.layers.17.self_attn.v_proj",
+        "model.layers.17.self_attn.o_proj",
+        "model.layers.17.mlp.gate_proj",
+        "model.layers.17.mlp.up_proj",
+        "model.layers.17.mlp.down_proj",
+        "model.layers.18.self_attn.q_proj",
+        "model.layers.18.self_attn.k_proj",
+        "model.layers.18.self_attn.v_proj",
+        "model.layers.18.self_attn.o_proj",
+        "model.layers.18.mlp.gate_proj",
+        "model.layers.18.mlp.up_proj",
+        "model.layers.18.mlp.down_proj",
+        "model.layers.19.self_attn.q_proj",
+        "model.layers.19.self_attn.k_proj",
+        "model.layers.19.self_attn.v_proj",
+        "model.layers.19.self_attn.o_proj",
+        "model.layers.19.mlp.gate_proj",
+        "model.layers.19.mlp.up_proj",
+        "model.layers.19.mlp.down_proj",
+        "model.layers.20.self_attn.q_proj",
+        "model.layers.20.self_attn.k_proj",
+        "model.layers.20.self_attn.v_proj",
+        "model.layers.20.self_attn.o_proj",
+        "model.layers.20.mlp.gate_proj",
+        "model.layers.20.mlp.up_proj",
+        "model.layers.20.mlp.down_proj",
+        "model.layers.21.self_attn.q_proj",
+        "model.layers.21.self_attn.k_proj",
+        "model.layers.21.self_attn.v_proj",
+        "model.layers.21.self_attn.o_proj",
+        "model.layers.21.mlp.gate_proj",
+        "model.layers.21.mlp.up_proj",
+        "model.layers.21.mlp.down_proj",
+        "model.layers.22.self_attn.q_proj",
+        "model.layers.22.self_attn.k_proj",
+        "model.layers.22.self_attn.v_proj",
+        "model.layers.22.self_attn.o_proj",
+        "model.layers.22.mlp.gate_proj",
+        "model.layers.22.mlp.up_proj",
+        "model.layers.22.mlp.down_proj",
+        "model.layers.23.self_attn.q_proj",
+        "model.layers.23.self_attn.k_proj",
+        "model.layers.23.self_attn.v_proj",
+        "model.layers.23.self_attn.o_proj",
+        "model.layers.23.mlp.gate_proj",
+        "model.layers.23.mlp.up_proj",
+        "model.layers.23.mlp.down_proj",
+        "model.layers.24.self_attn.q_proj",
+        "model.layers.24.self_attn.k_proj",
+        "model.layers.24.self_attn.v_proj",
+        "model.layers.24.self_attn.o_proj",
+        "model.layers.24.mlp.gate_proj",
+        "model.layers.24.mlp.up_proj",
+        "model.layers.24.mlp.down_proj",
+        "model.layers.25.self_attn.q_proj",
+        "model.layers.25.self_attn.k_proj",
+        "model.layers.25.self_attn.v_proj",
+        "model.layers.25.self_attn.o_proj",
+        "model.layers.25.mlp.gate_proj",
+        "model.layers.25.mlp.up_proj",
+        "model.layers.25.mlp.down_proj",
+        "model.layers.26.self_attn.q_proj",
+        "model.layers.26.self_attn.k_proj",
+        "model.layers.26.self_attn.v_proj",
+        "model.layers.26.self_attn.o_proj",
+        "model.layers.26.mlp.gate_proj",
+        "model.layers.26.mlp.up_proj",
+        "model.layers.26.mlp.down_proj",
+        "model.layers.27.self_attn.q_proj",
+        "model.layers.27.self_attn.k_proj",
+        "model.layers.27.self_attn.v_proj",
+        "model.layers.27.self_attn.o_proj",
+        "model.layers.27.mlp.gate_proj",
+        "model.layers.27.mlp.up_proj",
+        "model.layers.27.mlp.down_proj",
+        "model.layers.28.self_attn.q_proj",
+        "model.layers.28.self_attn.k_proj",
+        "model.layers.28.self_attn.v_proj",
+        "model.layers.28.self_attn.o_proj",
+        "model.layers.28.mlp.gate_proj",
+        "model.layers.28.mlp.up_proj",
+        "model.layers.28.mlp.down_proj",
+        "model.layers.29.self_attn.q_proj",
+        "model.layers.29.self_attn.k_proj",
+        "model.layers.29.self_attn.v_proj",
+        "model.layers.29.self_attn.o_proj",
+        "model.layers.29.mlp.gate_proj",
+        "model.layers.29.mlp.up_proj",
+        "model.layers.29.mlp.down_proj",
+        "model.layers.30.self_attn.q_proj",
+        "model.layers.30.self_attn.k_proj",
+        "model.layers.30.self_attn.v_proj",
+        "model.layers.30.self_attn.o_proj",
+        "model.layers.30.mlp.gate_proj",
+        "model.layers.30.mlp.up_proj",
+        "model.layers.30.mlp.down_proj",
+        "model.layers.31.self_attn.q_proj",
+        "model.layers.31.self_attn.k_proj",
+        "model.layers.31.self_attn.v_proj",
+        "model.layers.31.self_attn.o_proj",
+        "model.layers.31.mlp.gate_proj",
+        "model.layers.31.mlp.up_proj",
+        "model.layers.31.mlp.down_proj",
+        "lm_head"
+      ],
+      "registry_requires_subclass": false,
+      "sparsity_structure": "unstructured",
+      "targets": [
+        "model.layers.0.self_attn.q_proj",
+        "model.layers.0.self_attn.k_proj"
+      ]
+    }
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.48.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ab1446afafdc0b7746850d54893860cac24e3915d73b837a653cba8cc614e4
+size 4136204176

recipe.yaml

@@ -0,0 +1,6 @@
+DEFAULT_stage:
+  DEFAULT_modifiers:
+    GPTQModifier:
+      scheme: W4A16
+      targets: Linear
+      ignore: [lm_head]

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404