Upload folder using huggingface_hub

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "/network/eldar/llama31_8b_evolcodealpaca/sparse_transfer/sp2of4_2ep_lr8e-5_bs64_GradClip2_warmup20ba_noKD",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "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": "mse",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "marlin-24",
+    "global_compression_ratio": 1.8917232374233346,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 0.45896846825239346,
+      "ignore": [
+        "lm_head"
+      ],
+      "registry_requires_subclass": false,
+      "sparsity_structure": "2:4",
+      "targets": [
+        "Linear"
+      ]
+    }
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edceb6450f0125e45022bc8038fb5f49e72d3c2b4aaaf4645616be9441a82b0b
+size 4828263024

recipe.yaml

@@ -0,0 +1,11 @@
+quant_stage:
+  quant_modifiers:
+    GPTQModifier:
+      sequential_update: true
+      dampening_frac: 0.01
+      ignore: [lm_head]
+      config_groups:
+        group_0:
+          weights: {num_bits: 4, type: int, symmetric: true, strategy: group, group_size: 128,
+            observer: mse}
+          targets: [Linear]