Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+language:
+- hu
+license: apache-2.0
+library_name: mlx
+base_model: utter-project/EuroLLM-22B
+pipeline_tag: text-generation
+tags:
+- hungarian
+- emese
+- eurollm
+- instruct
+- chatml
+- mlx
+- apple-silicon
+- quantized
+---
+
+# Emese-Folyó (22B) — MLX q8
+
+**MLX q8** — the **native training/serving precision** for Folyó (CPT, SFT, and DPO were all trained on
+top of a q8-quantized base). See the `folyo/` repo's README for full architecture, CPT/SFT/DPO training
+details, and benchmarks — this file covers only the q8-specific notes.
+
+| | |
+|---|---|
+| **Quantization** | q8, group size 64 |
+| **Size on disk** | ~22 GB (vs. ~42 GB bf16) |
+| **Quality** | This *is* the model's native precision — the `folyo/` bf16 repo is dequantized *from* this, not the other way around. |
+| **Max context length** | 32,768 tokens (EuroLLM-22B's native context) |
+
+## Usage
+
+```python
+from mlx_lm import load, generate
+from mlx_lm.sample_utils import make_sampler
+model, tok = load("emese-tech/folyo-mlx")
+p = tok.apply_chat_template([{"role": "user", "content": "Mi Magyarország fővárosa?"}],
+                            tokenize=False, add_generation_prompt=True)
+print(generate(model, tok, prompt=p, max_tokens=256, sampler=make_sampler(temp=0.2)))
+```
+
+**Decode:** temperature `0.2`, no repetition penalty, eos `{2, 4}`, ChatML template.
+
+⚠️ **This repo is `mlx_lm`-only** — MLX's q8 quantization packs weights into `uint32` + per-group
+`scales`/`biases` tensors with a `quantization` block in `config.json` that plain `transformers` does not
+understand. Use the `folyo/` (bf16) repo for `transformers`/vLLM/TGI.
+
+## Training
+
+This is the primary artifact of the CPT+SFT+DPO training chain — see `folyo/README.md` for the full
+q8-native CPT (~6M tokens/6,000 iters, rank64), SFT (`instruct_v18b`, 1 epoch, rank16/scale16/lr5e-6,
+iteration 3,600 selected), and DPO (36 alfa pairs, 120 iters, rank16/scale16/lr2e-6) recipe, plus the
+211/250 Ultimate · 310/376 BlindSpot benchmark results.
+
+## Benchmarks
+
+**This exact q8 artifact scored 410/500 (82%) on emese-bench v1** (200 questions + 10 chat sessions,
+consolidated Ultimate+BlindSpot) — a close second to Patak (413/500) and far ahead of Csermely
+(211/500). Strongest on safety, reading, translation, and code; weakest on multi-step math and logic
+puzzles. Notably the best of the three models on in-context memory recall and roleplay (both 10/10),
+but it failed to stay in English during the English-chat session, answering in Hungarian throughout.
+See `emese-bench/results/folyo-mlx.md` for the full transcript and category breakdown.

chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}<|im_start|>{{ message['role'] }}
+{{ message['content'] }}<|im_end|>
+{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,42 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        2,
+        4
+    ],
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 32768,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 48,
+    "num_hidden_layers": 54,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.56.1",
+    "use_cache": true,
+    "vocab_size": 128000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    4
+  ],
+  "transformers_version": "4.56.1"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd9f29745e73f232a7c194999c472056021a86377cc644a54e3fd6b01efa279e
+size 5287849928

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fd4f7a582bfa06174c3861c38950e53658e84e24f052a2b1ca7064a627bf6a
+size 5281244401

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffa24a6113e1178b34a86791052b972f0449bb6c429fe2a257816c48a373e2d
+size 5281244390

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1811d96bbd40cd7d099c167405784a982936103e38a388361ff9f224c7d34284
+size 5348091098

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887f3260a5a3cd146108d665ce6f874bf6251fd7c5feab7ca1aaf5751a28c9bf
+size 2854502703

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f236d4eaa17b1b3f4f2aff62301eaa163a4176a74509874bd5514e8fb93ff32a
+size 15783361

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}