Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + '[/INST]' }}{% elif message['role'] == 'system' %}{{ '[SYSTEM_PROMPT] ' + message['content'] + '[/SYSTEM_PROMPT]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only user, system and assistant roles are supported!') }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,76 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 12288,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 96,
+  "num_hidden_layers": 88,
+  "num_key_value_heads": 8,
+  "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": "0.14.0.1"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "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": "4.57.6"
+}

model-00001-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972393d1bd13f56c13da3b8bb3457f901c72c7ec097b01a319ff309f51f266cb
+size 4958398128

model-00002-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b979cd3f5dd580f97e11963743eaf16e2d1cc725f467820d8f3b1b264bc9832
+size 4832680488

model-00003-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ececfc09fb3d7178c20e6aa6dd4977f50e83ec0c7cbd537a5a48abe104aaaa2
+size 4857866304

model-00004-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44576ac674fba2e095fc82d830c4aef134ea3bb17a585a92733020f7a64d3986
+size 4832680552

model-00005-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5c222ab67ceb84bf8ca09699aa5fb602a4c8c5d0a2820495c8c9d78715e476
+size 4857866352

model-00006-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17484658bd05868d99d81fa21d366984029458b2b0da159429d543ba2b86367c
+size 4832680552

model-00007-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12a01f15015dbd981089347feb64dd7f8f6e20fe6ddf756c622b0a0e831cb39
+size 4857866352

model-00008-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fad71a8bbf806155aee40100e3936c48887360c443f31f326ade3b4ba55d11
+size 4832680552

model-00009-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18173cf7f80c2ba64bbc7c925ba141e11fb73d7b00bdbfb6bef1b0c43273f8f
+size 4857866352

model-00010-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4af3ab98046f3e163ee2bd25f6d993a06ad4560b85943e627a1e74c185f7da1
+size 4832680552

model-00011-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9ff8969dd14c40cf344ce86d778c8dae7069c7269bd38fafe4bc40292d014e
+size 4857866352

model-00012-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af013e9397ceebcf55a4044997c709f12128db81c498adcfb99a67807c7cf03c
+size 4832680552

model-00013-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22575391a302f906f425bf73ddef296d88e86fe868f01df9af4ad082dca9e72
+size 4857866352

model-00014-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8053e2c113ce600b97f302c1ca15ab6d21da0c8289bf2ba5fd4dcdaed758741f
+size 4832680552

model-00015-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1ed2015e925ace27a278bfbf48e4c61aa8de671910d743bd248a683b1fc1e8
+size 4857866352

model-00016-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e863c1e8ce63a224b7b0cb669628a54c27aa1684f67532a659b03341eb0f1d3
+size 4832680552

model-00017-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79993590818106fefb119184c1b14a87d20bbaf0bbdfd13dbd2be8d501d17f02
+size 4857866352

model-00018-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b437ccde918a57dad84788a1482902330d2f8e39a17869df76947072b8716e09
+size 4832680552

model-00019-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eaae28ec72772d4d0969148eabee94c4ba0ec9ea919b792c08a7593e4058951
+size 4857866352

model-00020-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d81ccfc35fa94d4b0119baca3d623dbde7c789a1cfe5139e3f7c9cd50f47632
+size 4832680552

model-00021-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b1c9d654be0fed88184096d13249aba78a9b67fdb83bc425dd088b5c371d02
+size 4857866352

model-00022-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5f2de030bf279565831dad146fa000d33b50cb3689fb04967b466cede9a82b
+size 4832680552

model-00023-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c74894fd5ce5fb0d5fec12e67d7a1c95fb83a2e5bb597799f3836ad14655f0
+size 4857866352

model-00024-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4742ceb91259570902a29b496a3da22d65220c3f0b7e6beb8190046d49f48931
+size 4832680552

model-00025-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954065752bc7e0c8d39543b20b61c8419d63df5e866ebcb3c5b7c5ff0a814365
+size 4857866352

model-00026-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dcf1aac0e1df87ae9cfff3cb3754acc8632a81b895b62638927aefd743b0686
+size 2189695048

recipe.yaml

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

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
+  }
+}