Spaces:
Running on Zero
Running on Zero
Add OpenCerebral models
Browse files
app.py
CHANGED
|
@@ -31,6 +31,8 @@ MODEL_IDS: List[str] = [
|
|
| 31 |
"BananaMind/BananaMind-2-Medium-Chat",
|
| 32 |
"SupraLabs/Supra2-100M-Instruct",
|
| 33 |
"HuggingFaceTB/SmolLM2-135M-Instruct",
|
|
|
|
|
|
|
| 34 |
]
|
| 35 |
|
| 36 |
MODEL_DISPLAY: Dict[str, str] = {
|
|
@@ -38,6 +40,8 @@ MODEL_DISPLAY: Dict[str, str] = {
|
|
| 38 |
"BananaMind/BananaMind-2-Medium-Chat": "BananaMind-2-Medium-Chat",
|
| 39 |
"SupraLabs/Supra2-100M-Instruct": "Supra2-100M-Instruct",
|
| 40 |
"HuggingFaceTB/SmolLM2-135M-Instruct": "SmolLM2-135M-Instruct",
|
|
|
|
|
|
|
| 41 |
}
|
| 42 |
|
| 43 |
BASE_MODEL_IDS: List[str] = [
|
|
@@ -45,6 +49,8 @@ BASE_MODEL_IDS: List[str] = [
|
|
| 45 |
"AxiomicLabs/GPT-X2.5-135M",
|
| 46 |
"BananaMind/BananaMind-2-Pro",
|
| 47 |
"HuggingFaceTB/SmolLM2-135M",
|
|
|
|
|
|
|
| 48 |
]
|
| 49 |
|
| 50 |
BASE_MODEL_DISPLAY: Dict[str, str] = {
|
|
@@ -52,6 +58,8 @@ BASE_MODEL_DISPLAY: Dict[str, str] = {
|
|
| 52 |
"AxiomicLabs/GPT-X2.5-135M": "GPT-X2.5-135M",
|
| 53 |
"BananaMind/BananaMind-2-Pro": "BananaMind-2-Pro",
|
| 54 |
"HuggingFaceTB/SmolLM2-135M": "SmolLM2-135M",
|
|
|
|
|
|
|
| 55 |
}
|
| 56 |
|
| 57 |
FALLBACK_IDS: Dict[str, str] = {}
|
|
@@ -130,6 +138,10 @@ GEN_DEFAULTS: Dict[str, dict] = {
|
|
| 130 |
"AxiomicLabs/GPT-X2.5-135M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
|
| 131 |
"BananaMind/BananaMind-2-Pro": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
|
| 132 |
"HuggingFaceTB/SmolLM2-135M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
}
|
| 134 |
|
| 135 |
MODEL_CONTEXT: Dict[str, int] = {
|
|
@@ -141,6 +153,10 @@ MODEL_CONTEXT: Dict[str, int] = {
|
|
| 141 |
"AxiomicLabs/GPT-X2.5-135M": 2048,
|
| 142 |
"BananaMind/BananaMind-2-Pro": 3072,
|
| 143 |
"HuggingFaceTB/SmolLM2-135M": 2048,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 144 |
}
|
| 145 |
|
| 146 |
|
|
|
|
| 31 |
"BananaMind/BananaMind-2-Medium-Chat",
|
| 32 |
"SupraLabs/Supra2-100M-Instruct",
|
| 33 |
"HuggingFaceTB/SmolLM2-135M-Instruct",
|
| 34 |
+
"OpenCerebral/Boris-1.3-125M-Instruct",
|
| 35 |
+
"OpenCerebral/Boris-1.3-75M-Instruct",
|
| 36 |
]
|
| 37 |
|
| 38 |
MODEL_DISPLAY: Dict[str, str] = {
|
|
|
|
| 40 |
"BananaMind/BananaMind-2-Medium-Chat": "BananaMind-2-Medium-Chat",
|
| 41 |
"SupraLabs/Supra2-100M-Instruct": "Supra2-100M-Instruct",
|
| 42 |
"HuggingFaceTB/SmolLM2-135M-Instruct": "SmolLM2-135M-Instruct",
|
| 43 |
+
"OpenCerebral/Boris-1.3-125M-Instruct": "Boris-1.3-125M-Instruct",
|
| 44 |
+
"OpenCerebral/Boris-1.3-75M-Instruct": "Boris-1.3-75M-Instruct",
|
| 45 |
}
|
| 46 |
|
| 47 |
BASE_MODEL_IDS: List[str] = [
|
|
|
|
| 49 |
"AxiomicLabs/GPT-X2.5-135M",
|
| 50 |
"BananaMind/BananaMind-2-Pro",
|
| 51 |
"HuggingFaceTB/SmolLM2-135M",
|
| 52 |
+
"OpenCerebral/Boris-1.3-125M",
|
| 53 |
+
"OpenCerebral/Boris-1.3-75M",
|
| 54 |
]
|
| 55 |
|
| 56 |
BASE_MODEL_DISPLAY: Dict[str, str] = {
|
|
|
|
| 58 |
"AxiomicLabs/GPT-X2.5-135M": "GPT-X2.5-135M",
|
| 59 |
"BananaMind/BananaMind-2-Pro": "BananaMind-2-Pro",
|
| 60 |
"HuggingFaceTB/SmolLM2-135M": "SmolLM2-135M",
|
| 61 |
+
"OpenCerebral/Boris-1.3-125M": "Boris-1.3-125M",
|
| 62 |
+
"OpenCerebral/Boris-1.3-75M": "Boris-1.3-75M",
|
| 63 |
}
|
| 64 |
|
| 65 |
FALLBACK_IDS: Dict[str, str] = {}
|
|
|
|
| 138 |
"AxiomicLabs/GPT-X2.5-135M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
|
| 139 |
"BananaMind/BananaMind-2-Pro": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
|
| 140 |
"HuggingFaceTB/SmolLM2-135M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
|
| 141 |
+
"OpenCerebral/Boris-1.3-125M-Instruct": {"max_new_tokens": 64, "temperature": 0.7, "top_p": 0.9, "repetition_penalty": 1.1, "do_sample": True},
|
| 142 |
+
"OpenCerebral/Boris-1.3-75M-Instruct": {"max_new_tokens": 64, "temperature": 0.7, "top_p": 0.9, "repetition_penalty": 1.1, "do_sample": True},
|
| 143 |
+
"OpenCerebral/Boris-1.3-125M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
|
| 144 |
+
"OpenCerebral/Boris-1.3-75M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
|
| 145 |
}
|
| 146 |
|
| 147 |
MODEL_CONTEXT: Dict[str, int] = {
|
|
|
|
| 153 |
"AxiomicLabs/GPT-X2.5-135M": 2048,
|
| 154 |
"BananaMind/BananaMind-2-Pro": 3072,
|
| 155 |
"HuggingFaceTB/SmolLM2-135M": 2048,
|
| 156 |
+
"OpenCerebral/Boris-1.3-125M-Instruct": 2048,
|
| 157 |
+
"OpenCerebral/Boris-1.3-75M-Instruct": 2048,
|
| 158 |
+
"OpenCerebral/Boris-1.3-125M": 2048,
|
| 159 |
+
"OpenCerebral/Boris-1.3-75M": 2048,
|
| 160 |
}
|
| 161 |
|
| 162 |
|