Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1,2 @@
+.history*
+.info

config.json

@@ -0,0 +1,88 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 48,
+  "dtype": "bfloat16",
+  "eos_token_id": 48,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.005,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 65536,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 48,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "float-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.17.1"
+  },
+  "rms_norm_eps": 3e-06,
+  "rope_parameters": {
+    "attention_factor": 1.0,
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 10.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 200000,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.1",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 48,
+  "eos_token_id": 48,
+  "transformers_version": "5.10.1"
+}

model.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1255dbcb60721f8a1de89ab5e16e7d8702b8751ded3783c01108074f0a7d71
+size 2316877

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0487fe6dcbe5761aa5633196553b91f3332f9ced69fade0d2efd9c7dc58737
+size 16246858184

recipe.yaml

@@ -0,0 +1,7 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: [lm_head]
+      scheme: FP8_DYNAMIC
+      bypass_divisibility_checks: false

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "tokenizer_class": "LlamaTokenizer",
+  "vocab_file":      "model.model",
+  "model_max_length": 65536,
+  "add_prefix_space": false,
+  "legacy":           true,
+  "use_chat_template": true,
+
+  "additional_special_tokens": ["<|system|>", "<|user|>", "<|assistant|>"],
+  "eos_token":                 "<|endoftext|>",
+  "add_generation_prompt": true,
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "chat_template": "{% for m in messages %}{% if m.role == 'system' %}<|system|>{{ m.content | trim }}<|system|>{% elif m.role == 'user' %}<|user|>{{ m.content | trim }}<|user|>{% elif m.role == 'assistant' %}<|assistant|>{{ m.content | trim }}<|assistant|>{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1].role != 'assistant' %}<|assistant|>{% endif %}"
+}