lollms-client 0.32.0__py3-none-any.whl → 0.33.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of lollms-client might be problematic. Click here for more details.
- lollms_client/__init__.py +1 -1
- lollms_client/llm_bindings/groq/__init__.py +2 -3
- lollms_client/llm_bindings/llamacpp/__init__.py +207 -328
- lollms_client/llm_bindings/mistral/__init__.py +57 -26
- lollms_client/llm_bindings/ollama/__init__.py +88 -0
- lollms_client/llm_bindings/open_router/__init__.py +43 -10
- lollms_client/lollms_discussion.py +6 -1
- lollms_client/lollms_llm_binding.py +403 -2
- {lollms_client-0.32.0.dist-info → lollms_client-0.33.0.dist-info}/METADATA +1 -1
- {lollms_client-0.32.0.dist-info → lollms_client-0.33.0.dist-info}/RECORD +13 -13
- {lollms_client-0.32.0.dist-info → lollms_client-0.33.0.dist-info}/WHEEL +0 -0
- {lollms_client-0.32.0.dist-info → lollms_client-0.33.0.dist-info}/licenses/LICENSE +0 -0
- {lollms_client-0.32.0.dist-info → lollms_client-0.33.0.dist-info}/top_level.txt +0 -0
|
@@ -154,8 +154,409 @@ class LollmsLLMBinding(ABC):
|
|
|
154
154
|
"""
|
|
155
155
|
pass
|
|
156
156
|
|
|
157
|
-
def get_ctx_size(self, model_name:str
|
|
158
|
-
|
|
157
|
+
def get_ctx_size(self, model_name: Optional[str] = None) -> Optional[int]:
|
|
158
|
+
"""
|
|
159
|
+
Retrieves context size for a model from a hardcoded list.
|
|
160
|
+
|
|
161
|
+
This method checks if the model name contains a known base model identifier
|
|
162
|
+
(e.g., 'llama3.1', 'gemma2') to determine its context length. It's intended
|
|
163
|
+
as a failsafe when the context size cannot be retrieved directly from the
|
|
164
|
+
Ollama API.
|
|
165
|
+
"""
|
|
166
|
+
if model_name is None:
|
|
167
|
+
model_name = self.model_name
|
|
168
|
+
|
|
169
|
+
# Hardcoded context sizes for popular models. More specific names (e.g., 'llama3.1')
|
|
170
|
+
# should appear, as they will be checked first due to the sorting logic below.
|
|
171
|
+
known_contexts = {
|
|
172
|
+
'agentica-org/deepcoder-14b-preview': 8192,
|
|
173
|
+
'agentica-org/deepcoder-14b-preview:free': 8192,
|
|
174
|
+
'ai21/jamba-large-1.7': 256000,
|
|
175
|
+
'ai21/jamba-mini-1.7': 256000,
|
|
176
|
+
'aion-labs/aion-1.0': 8192,
|
|
177
|
+
'aion-labs/aion-1.0-mini': 8192,
|
|
178
|
+
'aion-labs/aion-rp-llama-3.1-8b': 131072,
|
|
179
|
+
'alfredpros/codellama-7b-instruct-solidity': 16384,
|
|
180
|
+
'alpindale/goliath-120b': 4096,
|
|
181
|
+
'amazon/nova-lite-v1': 32768,
|
|
182
|
+
'amazon/nova-micro-v1': 32768,
|
|
183
|
+
'amazon/nova-pro-v1': 32768,
|
|
184
|
+
'anthracite-org/magnum-v2-72b': 131072,
|
|
185
|
+
'anthracite-org/magnum-v4-72b': 131072,
|
|
186
|
+
'anthropic/claude-3-haiku': 200000,
|
|
187
|
+
'anthropic/claude-3-haiku:beta': 200000,
|
|
188
|
+
'anthropic/claude-3-opus': 200000,
|
|
189
|
+
'anthropic/claude-3-opus:beta': 200000,
|
|
190
|
+
'anthropic/claude-3.5-haiku': 200000,
|
|
191
|
+
'anthropic/claude-3.5-haiku-20241022': 200000,
|
|
192
|
+
'anthropic/claude-3.5-haiku:beta': 200000,
|
|
193
|
+
'anthropic/claude-3.5-sonnet': 200000,
|
|
194
|
+
'anthropic/claude-3.5-sonnet-20240620': 200000,
|
|
195
|
+
'anthropic/claude-3.5-sonnet-20240620:beta': 200000,
|
|
196
|
+
'anthropic/claude-3.5-sonnet:beta': 200000,
|
|
197
|
+
'anthropic/claude-3.7-sonnet': 200000,
|
|
198
|
+
'anthropic/claude-3.7-sonnet:beta': 200000,
|
|
199
|
+
'anthropic/claude-3.7-sonnet:thinking': 200000,
|
|
200
|
+
'anthropic/claude-opus-4': 200000,
|
|
201
|
+
'anthropic/claude-opus-4.1': 200000,
|
|
202
|
+
'anthropic/claude-sonnet-4': 200000,
|
|
203
|
+
'arcee-ai/coder-large': 32768,
|
|
204
|
+
'arcee-ai/maestro-reasoning': 32768,
|
|
205
|
+
'arcee-ai/spotlight': 32768,
|
|
206
|
+
'arcee-ai/virtuoso-large': 32768,
|
|
207
|
+
'arliai/qwq-32b-arliai-rpr-v1': 8192,
|
|
208
|
+
'arliai/qwq-32b-arliai-rpr-v1:free': 8192,
|
|
209
|
+
'baidu/ernie-4.5-300b-a47b': 128000,
|
|
210
|
+
'bytedance/ui-tars-1.5-7b': 8192,
|
|
211
|
+
'cognitivecomputations/dolphin-mistral-24b-venice-edition:free': 32768,
|
|
212
|
+
'cognitivecomputations/dolphin-mixtral-8x22b': 65536,
|
|
213
|
+
'cognitivecomputations/dolphin3.0-mistral-24b': 32768,
|
|
214
|
+
'cognitivecomputations/dolphin3.0-mistral-24b:free': 32768,
|
|
215
|
+
'cognitivecomputations/dolphin3.0-r1-mistral-24b': 32768,
|
|
216
|
+
'cognitivecomputations/dolphin3.0-r1-mistral-24b:free': 32768,
|
|
217
|
+
'cohere/command': 8192,
|
|
218
|
+
'cohere/command-a': 8192,
|
|
219
|
+
'cohere/command-r': 128000,
|
|
220
|
+
'cohere/command-r-03-2024': 128000,
|
|
221
|
+
'cohere/command-r-08-2024': 128000,
|
|
222
|
+
'cohere/command-r-plus': 128000,
|
|
223
|
+
'cohere/command-r-plus-04-2024': 128000,
|
|
224
|
+
'cohere/command-r-plus-08-2024': 128000,
|
|
225
|
+
'cohere/command-r7b-12-2024': 128000,
|
|
226
|
+
'deepseek/deepseek-chat': 32768,
|
|
227
|
+
'deepseek/deepseek-chat-v3-0324': 32768,
|
|
228
|
+
'deepseek/deepseek-chat-v3-0324:free': 32768,
|
|
229
|
+
'deepseek/deepseek-prover-v2': 131072,
|
|
230
|
+
'deepseek/deepseek-r1': 32768,
|
|
231
|
+
'deepseek/deepseek-r1-0528': 32768,
|
|
232
|
+
'deepseek/deepseek-r1-0528-qwen3-8b': 32768,
|
|
233
|
+
'deepseek/deepseek-r1-0528-qwen3-8b:free': 32768,
|
|
234
|
+
'deepseek/deepseek-r1-0528:free': 32768,
|
|
235
|
+
'deepseek/deepseek-r1-distill-llama-70b': 131072,
|
|
236
|
+
'deepseek/deepseek-r1-distill-llama-70b:free': 131072,
|
|
237
|
+
'deepseek/deepseek-r1-distill-llama-8b': 131072,
|
|
238
|
+
'deepseek/deepseek-r1-distill-qwen-1.5b': 32768,
|
|
239
|
+
'deepseek/deepseek-r1-distill-qwen-14b': 32768,
|
|
240
|
+
'deepseek/deepseek-r1-distill-qwen-14b:free': 32768,
|
|
241
|
+
'deepseek/deepseek-r1-distill-qwen-32b': 32768,
|
|
242
|
+
'deepseek/deepseek-r1-distill-qwen-7b': 32768,
|
|
243
|
+
'deepseek/deepseek-r1:free': 32768,
|
|
244
|
+
'deepseek/deepseek-v3-base': 32768,
|
|
245
|
+
'eleutherai/llemma_7b': 8192,
|
|
246
|
+
'featherless/qwerky-72b:free': 8192,
|
|
247
|
+
'google/gemini-2.0-flash-001': 1000000,
|
|
248
|
+
'google/gemini-2.0-flash-exp:free': 1000000,
|
|
249
|
+
'google/gemini-2.0-flash-lite-001': 1000000,
|
|
250
|
+
'google/gemini-2.5-flash': 1000000,
|
|
251
|
+
'google/gemini-2.5-flash-lite': 1000000,
|
|
252
|
+
'google/gemini-2.5-flash-lite-preview-06-17': 1000000,
|
|
253
|
+
'google/gemini-2.5-pro': 2000000,
|
|
254
|
+
'google/gemini-2.5-pro-exp-03-25': 2000000,
|
|
255
|
+
'google/gemini-2.5-pro-preview': 2000000,
|
|
256
|
+
'google/gemini-2.5-pro-preview-05-06': 2000000,
|
|
257
|
+
'google/gemini-flash-1.5': 1000000,
|
|
258
|
+
'google/gemini-flash-1.5-8b': 1000000,
|
|
259
|
+
'google/gemini-pro-1.5': 2000000,
|
|
260
|
+
'google/gemma-2-27b-it': 8192,
|
|
261
|
+
'google/gemma-2-9b-it': 8192,
|
|
262
|
+
'google/gemma-2-9b-it:free': 8192,
|
|
263
|
+
'google/gemma-3-12b-it': 131072,
|
|
264
|
+
'google/gemma-3-12b-it:free': 131072,
|
|
265
|
+
'google/gemma-3-27b-it': 131072,
|
|
266
|
+
'google/gemma-3-27b-it:free': 131072,
|
|
267
|
+
'google/gemma-3-4b-it': 131072,
|
|
268
|
+
'google/gemma-3-4b-it:free': 131072,
|
|
269
|
+
'google/gemma-3n-e2b-it:free': 131072,
|
|
270
|
+
'google/gemma-3n-e4b-it': 131072,
|
|
271
|
+
'google/gemma-3n-e4b-it:free': 131072,
|
|
272
|
+
'gryphe/mythomax-l2-13b': 4096,
|
|
273
|
+
'inception/mercury': 32768,
|
|
274
|
+
'inception/mercury-coder': 32768,
|
|
275
|
+
'infermatic/mn-inferor-12b': 8192,
|
|
276
|
+
'inflection/inflection-3-pi': 128000,
|
|
277
|
+
'inflection/inflection-3-productivity': 128000,
|
|
278
|
+
'liquid/lfm-3b': 8192,
|
|
279
|
+
'liquid/lfm-40b': 8192,
|
|
280
|
+
'liquid/lfm-7b': 8192,
|
|
281
|
+
'mancer/weaver': 8192,
|
|
282
|
+
'meta-llama/llama-3-70b-instruct': 8192,
|
|
283
|
+
'meta-llama/llama-3-8b-instruct': 8192,
|
|
284
|
+
'meta-llama/llama-3.1-405b': 131072,
|
|
285
|
+
'meta-llama/llama-3.1-405b-instruct': 131072,
|
|
286
|
+
'meta-llama/llama-3.1-405b-instruct:free': 131072,
|
|
287
|
+
'meta-llama/llama-3.1-70b-instruct': 131072,
|
|
288
|
+
'meta-llama/llama-3.1-8b-instruct': 131072,
|
|
289
|
+
'meta-llama/llama-3.2-11b-vision-instruct': 131072,
|
|
290
|
+
'meta-llama/llama-3.2-11b-vision-instruct:free': 131072,
|
|
291
|
+
'meta-llama/llama-3.2-1b-instruct': 131072,
|
|
292
|
+
'meta-llama/llama-3.2-3b-instruct': 131072,
|
|
293
|
+
'meta-llama/llama-3.2-3b-instruct:free': 131072,
|
|
294
|
+
'meta-llama/llama-3.2-90b-vision-instruct': 131072,
|
|
295
|
+
'meta-llama/llama-3.3-70b-instruct': 131072,
|
|
296
|
+
'meta-llama/llama-3.3-70b-instruct:free': 131072,
|
|
297
|
+
'meta-llama/llama-4-maverick': 131072,
|
|
298
|
+
'meta-llama/llama-4-scout': 131072,
|
|
299
|
+
'meta-llama/llama-guard-2-8b': 8192,
|
|
300
|
+
'meta-llama/llama-guard-3-8b': 131072,
|
|
301
|
+
'meta-llama/llama-guard-4-12b': 131072,
|
|
302
|
+
'microsoft/mai-ds-r1': 32768,
|
|
303
|
+
'microsoft/mai-ds-r1:free': 32768,
|
|
304
|
+
'microsoft/phi-3-medium-128k-instruct': 131072,
|
|
305
|
+
'microsoft/phi-3-mini-128k-instruct': 131072,
|
|
306
|
+
'microsoft/phi-3.5-mini-128k-instruct': 131072,
|
|
307
|
+
'microsoft/phi-4': 131072,
|
|
308
|
+
'microsoft/phi-4-multimodal-instruct': 131072,
|
|
309
|
+
'microsoft/phi-4-reasoning-plus': 131072,
|
|
310
|
+
'microsoft/wizardlm-2-8x22b': 65536,
|
|
311
|
+
'minimax/minimax-01': 200000,
|
|
312
|
+
'minimax/minimax-m1': 200000,
|
|
313
|
+
'mistralai/codestral-2501': 32768,
|
|
314
|
+
'mistralai/codestral-2508': 32768,
|
|
315
|
+
'mistralai/devstral-medium': 32768,
|
|
316
|
+
'mistralai/devstral-small': 32768,
|
|
317
|
+
'mistralai/devstral-small-2505': 32768,
|
|
318
|
+
'mistralai/devstral-small-2505:free': 32768,
|
|
319
|
+
'mistralai/magistral-medium-2506': 32768,
|
|
320
|
+
'mistralai/magistral-medium-2506:thinking': 32768,
|
|
321
|
+
'mistralai/magistral-small-2506': 32768,
|
|
322
|
+
'mistralai/ministral-3b': 32768,
|
|
323
|
+
'mistralai/ministral-8b': 32768,
|
|
324
|
+
'mistralai/mistral-7b-instruct': 32768,
|
|
325
|
+
'mistralai/mistral-7b-instruct-v0.1': 8192,
|
|
326
|
+
'mistralai/mistral-7b-instruct-v0.2': 32768,
|
|
327
|
+
'mistralai/mistral-7b-instruct-v0.3': 32768,
|
|
328
|
+
'mistralai/mistral-7b-instruct:free': 32768,
|
|
329
|
+
'mistralai/mistral-large': 32768,
|
|
330
|
+
'mistralai/mistral-large-2407': 128000,
|
|
331
|
+
'mistralai/mistral-large-2411': 128000,
|
|
332
|
+
'mistralai/mistral-medium-3': 32768,
|
|
333
|
+
'mistralai/mistral-nemo': 128000,
|
|
334
|
+
'mistralai/mistral-nemo:free': 128000,
|
|
335
|
+
'mistralai/mistral-saba': 32768,
|
|
336
|
+
'mistralai/mistral-small': 32768,
|
|
337
|
+
'mistralai/mistral-small-24b-instruct-2501': 32768,
|
|
338
|
+
'mistralai/mistral-small-24b-instruct-2501:free': 32768,
|
|
339
|
+
'mistralai/mistral-small-3.1-24b-instruct': 32768,
|
|
340
|
+
'mistralai/mistral-small-3.1-24b-instruct:free': 32768,
|
|
341
|
+
'mistralai/mistral-small-3.2-24b-instruct': 32768,
|
|
342
|
+
'mistralai/mistral-small-3.2-24b-instruct:free': 32768,
|
|
343
|
+
'mistralai/mistral-tiny': 32768,
|
|
344
|
+
'mistralai/mixtral-8x22b-instruct': 65536,
|
|
345
|
+
'mistralai/mixtral-8x7b-instruct': 32768,
|
|
346
|
+
'mistralai/pixtral-12b': 128000,
|
|
347
|
+
'mistralai/pixtral-large-2411': 128000,
|
|
348
|
+
'moonshotai/kimi-dev-72b:free': 200000,
|
|
349
|
+
'moonshotai/kimi-k2': 200000,
|
|
350
|
+
'moonshotai/kimi-k2:free': 200000,
|
|
351
|
+
'moonshotai/kimi-vl-a3b-thinking': 200000,
|
|
352
|
+
'moonshotai/kimi-vl-a3b-thinking:free': 200000,
|
|
353
|
+
'morph/morph-v3-fast': 8192,
|
|
354
|
+
'morph/morph-v3-large': 8192,
|
|
355
|
+
'neversleep/llama-3-lumimaid-70b': 8192,
|
|
356
|
+
'neversleep/llama-3.1-lumimaid-8b': 131072,
|
|
357
|
+
'neversleep/noromaid-20b': 32768,
|
|
358
|
+
'nousresearch/deephermes-3-llama-3-8b-preview:free': 8192,
|
|
359
|
+
'nousresearch/deephermes-3-mistral-24b-preview': 32768,
|
|
360
|
+
'nousresearch/hermes-2-pro-llama-3-8b': 8192,
|
|
361
|
+
'nousresearch/hermes-3-llama-3.1-405b': 131072,
|
|
362
|
+
'nousresearch/hermes-3-llama-3.1-70b': 131072,
|
|
363
|
+
'nousresearch/nous-hermes-2-mixtral-8x7b-dpo': 32768,
|
|
364
|
+
'nvidia/llama-3.1-nemotron-70b-instruct': 131072,
|
|
365
|
+
'nvidia/llama-3.1-nemotron-ultra-253b-v1': 131072,
|
|
366
|
+
'nvidia/llama-3.1-nemotron-ultra-253b-v1:free': 131072,
|
|
367
|
+
'nvidia/llama-3.3-nemotron-super-49b-v1': 131072,
|
|
368
|
+
'openai/chatgpt-4o-latest': 128000,
|
|
369
|
+
'openai/codex-mini': 2048,
|
|
370
|
+
'openai/gpt-3.5-turbo': 4096,
|
|
371
|
+
'openai/gpt-3.5-turbo-0613': 4096,
|
|
372
|
+
'openai/gpt-3.5-turbo-16k': 16384,
|
|
373
|
+
'openai/gpt-3.5-turbo-instruct': 4096,
|
|
374
|
+
'openai/gpt-4': 8192,
|
|
375
|
+
'openai/gpt-4-0314': 8192,
|
|
376
|
+
'openai/gpt-4-1106-preview': 128000,
|
|
377
|
+
'openai/gpt-4-turbo': 128000,
|
|
378
|
+
'openai/gpt-4-turbo-preview': 128000,
|
|
379
|
+
'openai/gpt-4.1': 128000,
|
|
380
|
+
'openai/gpt-4.1-mini': 128000,
|
|
381
|
+
'openai/gpt-4.1-nano': 128000,
|
|
382
|
+
'openai/gpt-4o': 128000,
|
|
383
|
+
'openai/gpt-4o-2024-05-13': 128000,
|
|
384
|
+
'openai/gpt-4o-2024-08-06': 128000,
|
|
385
|
+
'openai/gpt-4o-2024-11-20': 128000,
|
|
386
|
+
'openai/gpt-4o-mini': 128000,
|
|
387
|
+
'openai/gpt-4o-mini-2024-07-18': 128000,
|
|
388
|
+
'openai/gpt-4o-mini-search-preview': 128000,
|
|
389
|
+
'openai/gpt-4o-search-preview': 128000,
|
|
390
|
+
'openai/gpt-4o:extended': 128000,
|
|
391
|
+
'openai/gpt-5': 200000,
|
|
392
|
+
'openai/gpt-5-chat': 200000,
|
|
393
|
+
'openai/gpt-5-mini': 200000,
|
|
394
|
+
'openai/gpt-5-nano': 200000,
|
|
395
|
+
'openai/gpt-oss-120b': 128000,
|
|
396
|
+
'openai/gpt-oss-20b': 128000,
|
|
397
|
+
'openai/gpt-oss-20b:free': 128000,
|
|
398
|
+
'openai/o1': 128000,
|
|
399
|
+
'openai/o1-mini': 128000,
|
|
400
|
+
'openai/o1-mini-2024-09-12': 128000,
|
|
401
|
+
'openai/o1-pro': 128000,
|
|
402
|
+
'openai/o3': 200000,
|
|
403
|
+
'openai/o3-mini': 200000,
|
|
404
|
+
'openai/o3-mini-high': 200000,
|
|
405
|
+
'openai/o3-pro': 200000,
|
|
406
|
+
'openai/o4-mini': 128000,
|
|
407
|
+
'openai/o4-mini-high': 128000,
|
|
408
|
+
'opengvlab/internvl3-14b': 8192,
|
|
409
|
+
'openrouter/auto': 8192,
|
|
410
|
+
'perplexity/r1-1776': 32768,
|
|
411
|
+
'perplexity/sonar': 32768,
|
|
412
|
+
'perplexity/sonar-deep-research': 32768,
|
|
413
|
+
'perplexity/sonar-pro': 32768,
|
|
414
|
+
'perplexity/sonar-reasoning': 32768,
|
|
415
|
+
'perplexity/sonar-reasoning-pro': 32768,
|
|
416
|
+
'pygmalionai/mythalion-13b': 4096,
|
|
417
|
+
'qwen/qwen-2-72b-instruct': 32768,
|
|
418
|
+
'qwen/qwen-2.5-72b-instruct': 131072,
|
|
419
|
+
'qwen/qwen-2.5-72b-instruct:free': 131072,
|
|
420
|
+
'qwen/qwen-2.5-7b-instruct': 131072,
|
|
421
|
+
'qwen/qwen-2.5-coder-32b-instruct': 131072,
|
|
422
|
+
'qwen/qwen-2.5-coder-32b-instruct:free': 131072,
|
|
423
|
+
'qwen/qwen-2.5-vl-7b-instruct': 131072,
|
|
424
|
+
'qwen/qwen-max': 32768,
|
|
425
|
+
'qwen/qwen-plus': 32768,
|
|
426
|
+
'qwen/qwen-turbo': 8192,
|
|
427
|
+
'qwen/qwen-vl-max': 32768,
|
|
428
|
+
'qwen/qwen-vl-plus': 32768,
|
|
429
|
+
'qwen/qwen2.5-vl-32b-instruct': 131072,
|
|
430
|
+
'qwen/qwen2.5-vl-32b-instruct:free': 131072,
|
|
431
|
+
'qwen/qwen2.5-vl-72b-instruct': 131072,
|
|
432
|
+
'qwen/qwen2.5-vl-72b-instruct:free': 131072,
|
|
433
|
+
'qwen/qwen3-14b': 32768,
|
|
434
|
+
'qwen/qwen3-14b:free': 32768,
|
|
435
|
+
'qwen/qwen3-235b-a22b': 32768,
|
|
436
|
+
'qwen/qwen3-235b-a22b-2507': 32768,
|
|
437
|
+
'qwen/qwen3-235b-a22b-thinking-2507': 32768,
|
|
438
|
+
'qwen/qwen3-235b-a22b:free': 32768,
|
|
439
|
+
'qwen/qwen3-30b-a3b': 32768,
|
|
440
|
+
'qwen/qwen3-30b-a3b-instruct-2507': 32768,
|
|
441
|
+
'qwen/qwen3-30b-a3b:free': 32768,
|
|
442
|
+
'qwen/qwen3-32b': 32768,
|
|
443
|
+
'qwen/qwen3-4b:free': 32768,
|
|
444
|
+
'qwen/qwen3-8b': 32768,
|
|
445
|
+
'qwen/qwen3-8b:free': 32768,
|
|
446
|
+
'qwen/qwen3-coder': 32768,
|
|
447
|
+
'qwen/qwen3-coder:free': 32768,
|
|
448
|
+
'qwen/qwq-32b': 32768,
|
|
449
|
+
'qwen/qwq-32b-preview': 32768,
|
|
450
|
+
'qwen/qwq-32b:free': 32768,
|
|
451
|
+
'raifle/sorcererlm-8x22b': 65536,
|
|
452
|
+
'rekaai/reka-flash-3:free': 128000,
|
|
453
|
+
'sao10k/l3-euryale-70b': 8192,
|
|
454
|
+
'sao10k/l3-lunaris-8b': 8192,
|
|
455
|
+
'sao10k/l3.1-euryale-70b': 131072,
|
|
456
|
+
'sao10k/l3.3-euryale-70b': 131072,
|
|
457
|
+
'sarvamai/sarvam-m:free': 8192,
|
|
458
|
+
'scb10x/llama3.1-typhoon2-70b-instruct': 131072,
|
|
459
|
+
'shisa-ai/shisa-v2-llama3.3-70b': 131072,
|
|
460
|
+
'shisa-ai/shisa-v2-llama3.3-70b:free': 131072,
|
|
461
|
+
'sophosympatheia/midnight-rose-70b': 4096,
|
|
462
|
+
'switchpoint/router': 8192,
|
|
463
|
+
'tencent/hunyuan-a13b-instruct': 8192,
|
|
464
|
+
'tencent/hunyuan-a13b-instruct:free': 8192,
|
|
465
|
+
'thedrummer/anubis-70b-v1.1': 8192,
|
|
466
|
+
'thedrummer/anubis-pro-105b-v1': 8192,
|
|
467
|
+
'thedrummer/rocinante-12b': 8192,
|
|
468
|
+
'thedrummer/skyfall-36b-v2': 8192,
|
|
469
|
+
'thedrummer/unslopnemo-12b': 128000,
|
|
470
|
+
'thedrummer/valkyrie-49b-v1': 8192,
|
|
471
|
+
'thudm/glm-4-32b': 2000000,
|
|
472
|
+
'thudm/glm-4.1v-9b-thinking': 2000000,
|
|
473
|
+
'thudm/glm-z1-32b:free': 2000000,
|
|
474
|
+
'tngtech/deepseek-r1t-chimera': 32768,
|
|
475
|
+
'tngtech/deepseek-r1t-chimera:free': 32768,
|
|
476
|
+
'tngtech/deepseek-r1t2-chimera:free': 32768,
|
|
477
|
+
'undi95/remm-slerp-l2-13b': 4096,
|
|
478
|
+
'x-ai/grok-2-1212': 128000,
|
|
479
|
+
'x-ai/grok-2-vision-1212': 128000,
|
|
480
|
+
'x-ai/grok-3': 128000,
|
|
481
|
+
'x-ai/grok-3-beta': 128000,
|
|
482
|
+
'x-ai/grok-3-mini': 128000,
|
|
483
|
+
'x-ai/grok-3-mini-beta': 128000,
|
|
484
|
+
'x-ai/grok-4': 128000,
|
|
485
|
+
'x-ai/grok-vision-beta': 128000,
|
|
486
|
+
'z-ai/glm-4-32b': 2000000,
|
|
487
|
+
'z-ai/glm-4.5': 2000000,
|
|
488
|
+
'z-ai/glm-4.5-air': 2000000,
|
|
489
|
+
'z-ai/glm-4.5-air:free': 2000000,
|
|
490
|
+
'llama3.1': 131072, # Llama 3.1 extended context
|
|
491
|
+
'llama3.2': 131072, # Llama 3.2 extended context
|
|
492
|
+
'llama3.3': 131072, # Assuming similar to 3.1/3.2
|
|
493
|
+
'llama3': 8192, # Llama 3 default
|
|
494
|
+
'llama2': 4096, # Llama 2 default
|
|
495
|
+
'mixtral8x22b': 65536, # Mixtral 8x22B default
|
|
496
|
+
'mixtral': 32768, # Mixtral 8x7B default
|
|
497
|
+
'mistral': 32768, # Mistral 7B v0.2+ default
|
|
498
|
+
'gemma3': 131072, # Gemma 3 with 128K context
|
|
499
|
+
'gemma2': 8192, # Gemma 2 default
|
|
500
|
+
'gemma': 8192, # Gemma default
|
|
501
|
+
'phi3': 131072, # Phi-3 variants often use 128K (mini/medium extended)
|
|
502
|
+
'phi2': 2048, # Phi-2 default
|
|
503
|
+
'phi': 2048, # Phi default (older)
|
|
504
|
+
'qwen2.5': 131072, # Qwen2.5 with 128K
|
|
505
|
+
'qwen2': 32768, # Qwen2 default for 7B
|
|
506
|
+
'qwen': 8192, # Qwen default
|
|
507
|
+
'codellama': 16384, # CodeLlama extended
|
|
508
|
+
'codegemma': 8192, # CodeGemma default
|
|
509
|
+
'deepseek-coder-v2': 131072, # DeepSeek-Coder V2 with 128K
|
|
510
|
+
'deepseek-coder': 16384, # DeepSeek-Coder V1 default
|
|
511
|
+
'deepseek-v2': 131072, # DeepSeek-V2 with 128K
|
|
512
|
+
'deepseek-llm': 4096, # DeepSeek-LLM default
|
|
513
|
+
'yi1.5': 32768, # Yi-1.5 with 32K
|
|
514
|
+
'yi': 4096, # Yi base default
|
|
515
|
+
'command-r': 131072, # Command-R with 128K
|
|
516
|
+
'wizardlm2': 32768, # WizardLM2 (Mistral-based)
|
|
517
|
+
'wizardlm': 16384, # WizardLM default
|
|
518
|
+
'zephyr': 65536, # Zephyr beta (Mistral-based extended)
|
|
519
|
+
'vicuna': 2048, # Vicuna default (up to 16K in some variants)
|
|
520
|
+
'falcon': 2048, # Falcon default
|
|
521
|
+
'starcoder': 8192, # StarCoder default
|
|
522
|
+
'stablelm': 4096, # StableLM default
|
|
523
|
+
'orca2': 4096, # Orca 2 default
|
|
524
|
+
'orca': 4096, # Orca default
|
|
525
|
+
'dolphin': 32768, # Dolphin (often Mistral-based)
|
|
526
|
+
'openhermes': 8192, # OpenHermes default
|
|
527
|
+
'gpt-oss': 128000, # GPT-OSS with 128K context
|
|
528
|
+
'gpt-3.5-turbo': 4096, # GPT-3.5 Turbo default
|
|
529
|
+
'gpt-4': 8192, # GPT-4 default
|
|
530
|
+
'grok-2': 128000,
|
|
531
|
+
'grok-2-1212': 128000,
|
|
532
|
+
'grok-2-vision-1212': 128000,
|
|
533
|
+
'grok-3': 128000,
|
|
534
|
+
'grok-3-fast': 128000,
|
|
535
|
+
'grok-3-beta': 128000,
|
|
536
|
+
'grok-3-mini': 128000,
|
|
537
|
+
'grok-3-mini-beta': 128000,
|
|
538
|
+
'grok-3-mini-fast': 128000,
|
|
539
|
+
'grok-4-0709': 128000,
|
|
540
|
+
'grok-4': 128000,
|
|
541
|
+
'grok-vision-beta': 128000,
|
|
542
|
+
}
|
|
543
|
+
|
|
544
|
+
normalized_model_name = model_name.lower().strip()
|
|
545
|
+
|
|
546
|
+
# Sort keys by length in descending order. This ensures that a more specific
|
|
547
|
+
# name like 'llama3.1' is checked before a less specific name like 'llama3'.
|
|
548
|
+
sorted_base_models = sorted(known_contexts.keys(), key=len, reverse=True)
|
|
549
|
+
|
|
550
|
+
for base_name in sorted_base_models:
|
|
551
|
+
if base_name in normalized_model_name:
|
|
552
|
+
context_size = known_contexts[base_name]
|
|
553
|
+
ASCIIColors.warning(
|
|
554
|
+
f"Using hardcoded context size for model '{model_name}' "
|
|
555
|
+
f"based on base name '{base_name}': {context_size}"
|
|
556
|
+
)
|
|
557
|
+
return context_size
|
|
558
|
+
|
|
559
|
+
ASCIIColors.warning(f"Context size not found for model '{model_name}' in the hardcoded list.")
|
|
159
560
|
return None
|
|
160
561
|
|
|
161
562
|
|
|
@@ -29,12 +29,12 @@ examples/mcp_examples/openai_mcp.py,sha256=7IEnPGPXZgYZyiES_VaUbQ6viQjenpcUxGiHE
|
|
|
29
29
|
examples/mcp_examples/run_remote_mcp_example_v2.py,sha256=bbNn93NO_lKcFzfIsdvJJijGx2ePFTYfknofqZxMuRM,14626
|
|
30
30
|
examples/mcp_examples/run_standard_mcp_example.py,sha256=GSZpaACPf3mDPsjA8esBQVUsIi7owI39ca5avsmvCxA,9419
|
|
31
31
|
examples/test_local_models/local_chat.py,sha256=slakja2zaHOEAUsn2tn_VmI4kLx6luLBrPqAeaNsix8,456
|
|
32
|
-
lollms_client/__init__.py,sha256=
|
|
32
|
+
lollms_client/__init__.py,sha256=47yhAwjjK7irs9nhUU68Bk1NDWYRMIP23TCDociofi8,1147
|
|
33
33
|
lollms_client/lollms_config.py,sha256=goEseDwDxYJf3WkYJ4IrLXwg3Tfw73CXV2Avg45M_hE,21876
|
|
34
34
|
lollms_client/lollms_core.py,sha256=gDhpB62AluEmbVFvPm7vdnZgP2hGBymDLun57K1jrOM,177352
|
|
35
|
-
lollms_client/lollms_discussion.py,sha256=
|
|
35
|
+
lollms_client/lollms_discussion.py,sha256=RDX4V5R4sKCxuTjL2ILyGrDlHlyefFPf3x98_mnra3M,85608
|
|
36
36
|
lollms_client/lollms_js_analyzer.py,sha256=01zUvuO2F_lnUe_0NLxe1MF5aHE1hO8RZi48mNPv-aw,8361
|
|
37
|
-
lollms_client/lollms_llm_binding.py,sha256=
|
|
37
|
+
lollms_client/lollms_llm_binding.py,sha256=8jJ8TPtkxh6TSKaYdrUrEI9ulY9gvN1RGHIrbPOWsDs,35963
|
|
38
38
|
lollms_client/lollms_mcp_binding.py,sha256=0rK9HQCBEGryNc8ApBmtOlhKE1Yfn7X7xIQssXxS2Zc,8933
|
|
39
39
|
lollms_client/lollms_mcp_security.py,sha256=FhVTDhSBjksGEZnopVnjFmEF5dv7D8bBTqoaj4BiF0E,3562
|
|
40
40
|
lollms_client/lollms_personality.py,sha256=O-9nqZhazcITOkxjT24ENTxTmIoZLgqIsQ9WtWs0Id0,8719
|
|
@@ -51,15 +51,15 @@ lollms_client/llm_bindings/azure_openai/__init__.py,sha256=8C-gXoVa-OI9FmFM3PaMg
|
|
|
51
51
|
lollms_client/llm_bindings/claude/__init__.py,sha256=CsWILXAFytXtxp1ZAoNwq8KycW0POQ2MCmpT6Bz0Hd0,24877
|
|
52
52
|
lollms_client/llm_bindings/gemini/__init__.py,sha256=ZflZVwAkAa-GfctuehOWIav977oTCdXUisQy253PFsk,21611
|
|
53
53
|
lollms_client/llm_bindings/grok/__init__.py,sha256=5tIf3348RgAEaSp6FdG-LM9N8R7aR0t7OFspHf3XATs,23141
|
|
54
|
-
lollms_client/llm_bindings/groq/__init__.py,sha256=
|
|
54
|
+
lollms_client/llm_bindings/groq/__init__.py,sha256=qDCZXIzldblNHyb3LfcZkM0a8m1hSWilb2m9l-xvkZ8,12180
|
|
55
55
|
lollms_client/llm_bindings/hugging_face_inference_api/__init__.py,sha256=PxgeRqT8dpa9GZoXwtSncy9AUgAN2cDKrvp_nbaWq0E,14027
|
|
56
56
|
lollms_client/llm_bindings/litellm/__init__.py,sha256=pNkwyRPeENvTM4CDh6Pj3kQfxHfhX2pvXhGJDjKjp30,12340
|
|
57
|
-
lollms_client/llm_bindings/llamacpp/__init__.py,sha256=
|
|
57
|
+
lollms_client/llm_bindings/llamacpp/__init__.py,sha256=6LHrsSD_4Xdq57sJaGf8gSndmG4hHcOS9wlsfa62TPQ,58650
|
|
58
58
|
lollms_client/llm_bindings/lollms/__init__.py,sha256=scGHEKzlGX5fw2XwefVicsf28GrwgN3wU5nl4EPJ_Sk,24424
|
|
59
59
|
lollms_client/llm_bindings/lollms_webui/__init__.py,sha256=Thoq3PJR2e03Y2Kd_FBb-DULJK0zT5-2ID1YIJLcPlw,17864
|
|
60
|
-
lollms_client/llm_bindings/mistral/__init__.py,sha256=
|
|
61
|
-
lollms_client/llm_bindings/ollama/__init__.py,sha256=
|
|
62
|
-
lollms_client/llm_bindings/open_router/__init__.py,sha256=
|
|
60
|
+
lollms_client/llm_bindings/mistral/__init__.py,sha256=DFQAcrUR69oF1FhtKi1glMXqCF4jhqN2ctRN19tmrcM,14193
|
|
61
|
+
lollms_client/llm_bindings/ollama/__init__.py,sha256=dXKHIeQCS9pz5AS07GF1eWj3ieWiz3aFOtxOX7yojbs,41314
|
|
62
|
+
lollms_client/llm_bindings/open_router/__init__.py,sha256=tcG8yWd4ULIhqrfMURqqJbnAEDw8H3zU500FSHkoXMM,14977
|
|
63
63
|
lollms_client/llm_bindings/openai/__init__.py,sha256=Z0zNTfBgBGwkwArN375kBt4otrUTI_84pHgVuyuDy0c,26253
|
|
64
64
|
lollms_client/llm_bindings/openllm/__init__.py,sha256=xv2XDhJNCYe6NPnWBboDs24AQ1VJBOzsTuMcmuQ6xYY,29864
|
|
65
65
|
lollms_client/llm_bindings/pythonllamacpp/__init__.py,sha256=VNa6NXe7bY44Oev8r6q5XlQbxqWU2nBV62SFlsPPH78,31810
|
|
@@ -93,9 +93,9 @@ lollms_client/tts_bindings/piper_tts/__init__.py,sha256=0IEWG4zH3_sOkSb9WbZzkeV5
|
|
|
93
93
|
lollms_client/tts_bindings/xtts/__init__.py,sha256=FgcdUH06X6ZR806WQe5ixaYx0QoxtAcOgYo87a2qxYc,18266
|
|
94
94
|
lollms_client/ttv_bindings/__init__.py,sha256=UZ8o2izQOJLQgtZ1D1cXoNST7rzqW22rL2Vufc7ddRc,3141
|
|
95
95
|
lollms_client/ttv_bindings/lollms/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
96
|
-
lollms_client-0.
|
|
96
|
+
lollms_client-0.33.0.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
|
|
97
97
|
test/test_lollms_discussion.py,sha256=KxTsV1bPdNz8QqZd7tIof9kTWkeXLUtAMU08BQmoY6U,16829
|
|
98
|
-
lollms_client-0.
|
|
99
|
-
lollms_client-0.
|
|
100
|
-
lollms_client-0.
|
|
101
|
-
lollms_client-0.
|
|
98
|
+
lollms_client-0.33.0.dist-info/METADATA,sha256=kPveiEdFJW9h1_mj_DYJJ9Gq1-upw6YaFd2a70lLhWo,38717
|
|
99
|
+
lollms_client-0.33.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
100
|
+
lollms_client-0.33.0.dist-info/top_level.txt,sha256=1jIpjTnOSGEGtIW2rGAFM6tVRzgsDdMOiox_SmDH_zw,28
|
|
101
|
+
lollms_client-0.33.0.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|