danielhanchen
commited on
Add files using upload-large-folder tool
Browse files- .gitattributes +8 -0
- Mistral-Small-24B-Instruct-2501-Q2_K.gguf +3 -0
- Mistral-Small-24B-Instruct-2501-Q2_K_L.gguf +3 -0
- Mistral-Small-24B-Instruct-2501-Q3_K_M.gguf +3 -0
- Mistral-Small-24B-Instruct-2501-Q4_K_M.gguf +3 -0
- Mistral-Small-24B-Instruct-2501-Q5_K.gguf +3 -0
- Mistral-Small-24B-Instruct-2501-Q6_K.gguf +3 -0
- Mistral-Small-24B-Instruct-2501.BF16.gguf +3 -0
- Mistral-Small-24B-Instruct-2501.Q8_0.gguf +3 -0
- config.json +29 -0
.gitattributes
CHANGED
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
Mistral-Small-24B-Instruct-2501-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Mistral-Small-24B-Instruct-2501-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Mistral-Small-24B-Instruct-2501-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Mistral-Small-24B-Instruct-2501-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Mistral-Small-24B-Instruct-2501-Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Mistral-Small-24B-Instruct-2501-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Mistral-Small-24B-Instruct-2501.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Mistral-Small-24B-Instruct-2501.BF16.gguf filter=lfs diff=lfs merge=lfs -text
|
Mistral-Small-24B-Instruct-2501-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbe3f102cb4ecf0c016fc5960265ac60c41d34b6ab7a638e42552537e96c39c8
|
3 |
+
size 8890325248
|
Mistral-Small-24B-Instruct-2501-Q2_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b94d8eaa0357086aa51829aac000228d08351b10e17c90fbd3c6ad00141deae
|
3 |
+
size 9047611648
|
Mistral-Small-24B-Instruct-2501-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:798f8b1fc991d67f48404b12937362a6b70d51229651c6309bd81f7ce6cb859f
|
3 |
+
size 11474082048
|
Mistral-Small-24B-Instruct-2501-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f6d64ea75d659445a2d0a4824af6b124ddcd97bcc5e6045417b35b40ee28bf8
|
3 |
+
size 14333909248
|
Mistral-Small-24B-Instruct-2501-Q5_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2d9b86191fb7f94b95d2ad4aeffe8c188ece2d9e82b7cc1626b6d7385a132aa
|
3 |
+
size 16763984128
|
Mistral-Small-24B-Instruct-2501-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f50116d2faef535f206373245820dedbdb8a4bfcac66590f53b27aeac2ba180
|
3 |
+
size 19345938688
|
Mistral-Small-24B-Instruct-2501.BF16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3771a0ac1ae847e1dd0a9f3ef0df7f3c958ec9ec41ff89dd62894aaf1f3104
|
3 |
+
size 47153518848
|
Mistral-Small-24B-Instruct-2501.Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bd473246cb69f603c5210e72080d216a14eb5f73055f0c58580148e97330ed3
|
3 |
+
size 25054779648
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-Small-24B-Instruct-2501",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 32768,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 40,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 11,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_theta": 100000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.48.2",
|
26 |
+
"unsloth_fixed": true,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 131072
|
29 |
+
}
|