RAG LoRA fuse (Bielik-4.5B, iter-400/effective-500, rank 128)
Browse files- README.md +7 -0
- chat_template.jinja +4 -0
- config.json +43 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- model.safetensors.index.json +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
README.md
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
library_name: mlx
|
| 4 |
+
tags:
|
| 5 |
+
- mlx
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
---
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
+
' + message['content'] + '<|im_end|>' + '
|
| 3 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
+
' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": [
|
| 9 |
+
4,
|
| 10 |
+
2
|
| 11 |
+
],
|
| 12 |
+
"head_dim": 128,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 2048,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 11008,
|
| 17 |
+
"max_position_embeddings": 32768,
|
| 18 |
+
"mlp_bias": true,
|
| 19 |
+
"model_type": "llama",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 60,
|
| 22 |
+
"num_key_value_heads": 2,
|
| 23 |
+
"pad_token_id": 2,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"quantization": {
|
| 26 |
+
"group_size": 64,
|
| 27 |
+
"bits": 4,
|
| 28 |
+
"mode": "affine"
|
| 29 |
+
},
|
| 30 |
+
"quantization_config": {
|
| 31 |
+
"group_size": 64,
|
| 32 |
+
"bits": 4,
|
| 33 |
+
"mode": "affine"
|
| 34 |
+
},
|
| 35 |
+
"rms_norm_eps": 1e-06,
|
| 36 |
+
"rope_scaling": null,
|
| 37 |
+
"rope_theta": 1000000,
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"torch_dtype": "bfloat16",
|
| 40 |
+
"transformers_version": "4.51.3",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 32000
|
| 43 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [ 4, 2 ],
|
| 5 |
+
"pad_token_id": 2,
|
| 6 |
+
"transformers_version": "4.51.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0e70ece8f77b1671cb905c4d2e747c07d13e898378cdec762b87ab31e8a2690
|
| 3 |
+
size 2678991340
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "</s>",
|
| 10 |
+
"sp_model_kwargs": {},
|
| 11 |
+
"spaces_between_special_tokens": false,
|
| 12 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 13 |
+
"unk_token": "<unk>",
|
| 14 |
+
"use_default_system_prompt": false
|
| 15 |
+
}
|