Neo39982 commited on
Commit
9eb9896
·
verified ·
1 Parent(s): 8387fb1

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: TheDrummer/Behemoth-R1-123B-v2
3
+ tags:
4
+ - mlx
5
+ ---
6
+
7
+ # Neo39982/Behemoth-R1-123B-v2-mlx-4Bit
8
+
9
+ The Model [Neo39982/Behemoth-R1-123B-v2-mlx-4Bit](https://huggingface.co/Neo39982/Behemoth-R1-123B-v2-mlx-4Bit) was converted to MLX format from [TheDrummer/Behemoth-R1-123B-v2](https://huggingface.co/TheDrummer/Behemoth-R1-123B-v2) using mlx-lm version **0.31.2**.
10
+
11
+ ## Use with mlx
12
+
13
+ ```bash
14
+ pip install mlx-lm
15
+ ```
16
+
17
+ ```python
18
+ from mlx_lm import load, generate
19
+
20
+ model, tokenizer = load("Neo39982/Behemoth-R1-123B-v2-mlx-4Bit")
21
+
22
+ prompt="hello"
23
+
24
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
25
+ messages = [{"role": "user", "content": prompt}]
26
+ prompt = tokenizer.apply_chat_template(
27
+ messages, tokenize=False, add_generation_prompt=True
28
+ )
29
+
30
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
31
+ ```
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 12288,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 131072,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 96,
16
+ "num_hidden_layers": 88,
17
+ "num_key_value_heads": 8,
18
+ "quantization": {
19
+ "group_size": 64,
20
+ "bits": 4,
21
+ "mode": "affine"
22
+ },
23
+ "quantization_config": {
24
+ "group_size": 64,
25
+ "bits": 4,
26
+ "mode": "affine"
27
+ },
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": null,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.55.2",
34
+ "use_cache": true,
35
+ "vocab_size": 32768
36
+ }
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc0183097eefae83012a31041b6a2a185d4dca51323511f1720abe2c43396305
3
+ size 5280417270
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0746992a2e99acd0eef9edbf9922d530f3de415230638d95ad4ef431893107
3
+ size 5252155204
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f72b12fb73634e4703578053a4a5bb27f05536e2814c5643ef92ff90fdbf17
3
+ size 5365401460
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f42d46a268266a7e35863f511ad74902029c89dac45981c12727bdbd470a8e
3
+ size 5351245024
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6efbda73ee14e1fae66131fd32f85ed64c3ab35e4685b049a03d56f2f1192e3d
3
+ size 5252105900
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6acf228ecb6b8215fb27ab7b346142c66e73e51f86a1af8d04156b72ad26b34
3
+ size 5252155303
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f2ef2ad5991148c0a3e36191088b1268edd6b82835bc267a852fb5ede7ad45
3
+ size 5252155295
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd66245d64fa3c4c1f8c34d88f836043e0a96b60ad936d2e96aa6513e75755d
3
+ size 5365401498
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c6a570dc2cd7ead63231b0c09415189e0faf4689349653cc36e1a05c0eb5fe
3
+ size 5351245036
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1ad0fd80bdcc17730bb974a3e66e5da059d738a6c1da3fad36a6e362b047cb
3
+ size 5252105932
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15c680b01cb5365370ccfbd7b3444a4079d811b7bfffb467530e7bdfaa2784ca
3
+ size 5252155279
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5855852bd4624b6c713ddd1364a9b124907e7761d5ec2c81495739fa95b8b17d
3
+ size 5252155273
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0949bb1c36450b0453559a6f62966647b91bdc01f393ed2912813d577a11b909
3
+ size 5266334648
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349771ad8a9c737f329bdfdc0f8058aedf86f1cff40a4465330dc27ef23d59ae
3
+ size 226492718
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": true,
8
+ "legacy": true,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": null,
11
+ "sp_model_kwargs": {},
12
+ "spaces_between_special_tokens": false,
13
+ "tokenizer_class": "TokenizersBackend",
14
+ "unk_token": "<unk>",
15
+ "use_default_system_prompt": false
16
+ }