初始化项目，由ModelHub XC社区提供模型

Model: mesolitica/mallam-1.1b-20k-instructions Source: Original Platform
2026-06-07 19:06:12 +08:00
commit 4f052a47f2
9 changed files with 280 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,50 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,97 @@
+---
+language:
+- ms
+---
+
+# Full Parameter Finetuning MaLLaM 🌙 1.1B 20480 context length on Malaysian instructions dataset
+
+README at https://github.com/mesolitica/malaya/tree/5.1/session/mistral#mallam-1.1b
+
+We use exact Mistral Instruct chat template.
+
+WandB, https://wandb.ai/mesolitica/fpf-mallam-1.1b-instructions-16k?workspace=user-husein-mesolitica
+
+WandB report, https://wandb.ai/mesolitica/fpf-mallam-5b-instructions-16k/reports/Instruction-finetuning--Vmlldzo2MjE5Njg2
+
+## Dataset
+
+Dataset gathered at https://huggingface.co/collections/mesolitica/malaysian-synthetic-dataset-656c2673fe7fe0b1e9e25fe2
+
+Notebook to prepare dataset at https://github.com/mesolitica/malaysian-dataset/blob/master/llm-instruction/combine-malay-no-alignment-multitasks-partial-ultrachat-v2.ipynb
+
+## Limitations
+
+This model is a quick demonstration that the base model can be easily fine-tuned to achieve some performance. 
+It does have minimal moderation mechanisms.
+
+## how-to
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+import torch
+import json
+
+def parse_mistral_chat(messages, function_call = None):
+
+    user_query = messages[-1]['content']
+
+    users, assistants = [], []
+    for q in messages[:-1]:
+        if q['role'] == 'user':
+            users.append(q['content'])
+        elif q['role'] == 'assistant':
+            assistants.append(q['content'])
+
+    texts = ['<s>']
+    
+    if function_call:
+        fs = []
+        for f in function_call:
+            f = json.dumps(f, indent=4)
+            fs.append(f)
+        fs = '\n\n'.join(fs)
+        texts.append(f'\n[FUNCTIONCALL]\n{fs}\n')
+        
+    for u, a in zip(users, assistants):
+        texts.append(f'[INST] {u.strip()} [/INST] {a.strip()}</s>')
+
+    texts.append(f'[INST] {user_query.strip()} [/INST]')
+    prompt = ''.join(texts).strip()
+    return prompt
+
+TORCH_DTYPE = 'bfloat16'
+nf4_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type='nf4',
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_compute_dtype=getattr(torch, TORCH_DTYPE)
+)
+
+tokenizer = AutoTokenizer.from_pretrained('mesolitica/mallam-1.1b-20k-instructions')
+model = AutoModelForCausalLM.from_pretrained(
+    'mesolitica/mallam-1.1b-20k-instructions',
+    use_flash_attention_2 = True,
+    quantization_config = nf4_config
+)
+
+messages = [
+    {'role': 'user', 'content': 'kwsp tu apa'}
+]
+prompt = parse_mistral_chat(messages)
+inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to('cuda')
+generate_kwargs = dict(
+    inputs,
+    max_new_tokens=1024,
+    top_p=0.95,
+    top_k=50,
+    temperature=0.9,
+    do_sample=True,
+    num_beams=1,
+)
+r = model.generate(**generate_kwargs)
+tokenizer.decode(r[0])
+```
+
+```text
+<s> [INST] kwsp tu apa [/INST]KWSP bermaksud Kumpulan Wang Simpanan Pekerja. Ia adalah sebuah institusi simpanan persaraan yang ditubuhkan oleh Kementerian Kewangan Malaysia untuk tujuan mengumpul simpanan ahli untuk dibayar pada umur persaraan, penuh atau penuh persaraan penuh. KWSP ditubuhkan pada tahun 1951 dan mula beroperasi pada tahun 1952. KWSP adalah salah satu institusi simpanan persaraan terbesar di dunia, dengan pangkalan ahli sekitar 14 juta ahli.</s>
+```
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "fpf-1b-instructions-16k/checkpoint-14000",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.2"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5940bcf35808e56c517450c21d166be513ce6b62aba3e3f6968f0f0942594ee1
+size 2246257208
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<pad>",
+    "<s>",
+    "</s>",
+    "<unk>"
+  ],
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab85dbb9764201eb6e7ad48f07922777e4abaf5b3d00c91e6cfdaa789c72667f
+size 1343999
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<pad>",
+    "<s>",
+    "</s>",
+    "<unk>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "max_length": 20480,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`