Update README.md
Browse files
README.md
CHANGED
@@ -268,4 +268,156 @@ Traceback (most recent call last):
|
|
268 |
File "/teamspace/studios/this_studio/mergekit/mergekit/io/tasks.py", line 86, in execute
|
269 |
raise RuntimeError(
|
270 |
RuntimeError: Tensor lm_head.weight required but not present in model meta-llama/Llama-3.2-1B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
271 |
```
|
|
|
268 |
File "/teamspace/studios/this_studio/mergekit/mergekit/io/tasks.py", line 86, in execute
|
269 |
raise RuntimeError(
|
270 |
RuntimeError: Tensor lm_head.weight required but not present in model meta-llama/Llama-3.2-1B
|
271 |
+
```
|
272 |
+
|
273 |
+
which seems odd given the following output layers from llama-3-1b:
|
274 |
+
|
275 |
+
```
|
276 |
+
model.embed_tokens.weight
|
277 |
+
model.layers.0.self_attn.q_proj.weight
|
278 |
+
model.layers.0.self_attn.k_proj.weight
|
279 |
+
model.layers.0.self_attn.v_proj.weight
|
280 |
+
model.layers.0.self_attn.o_proj.weight
|
281 |
+
model.layers.0.mlp.gate_proj.weight
|
282 |
+
model.layers.0.mlp.up_proj.weight
|
283 |
+
model.layers.0.mlp.down_proj.weight
|
284 |
+
model.layers.0.input_layernorm.weight
|
285 |
+
model.layers.0.post_attention_layernorm.weight
|
286 |
+
model.layers.1.self_attn.q_proj.weight
|
287 |
+
model.layers.1.self_attn.k_proj.weight
|
288 |
+
model.layers.1.self_attn.v_proj.weight
|
289 |
+
model.layers.1.self_attn.o_proj.weight
|
290 |
+
model.layers.1.mlp.gate_proj.weight
|
291 |
+
model.layers.1.mlp.up_proj.weight
|
292 |
+
model.layers.1.mlp.down_proj.weight
|
293 |
+
model.layers.1.input_layernorm.weight
|
294 |
+
model.layers.1.post_attention_layernorm.weight
|
295 |
+
model.layers.2.self_attn.q_proj.weight
|
296 |
+
model.layers.2.self_attn.k_proj.weight
|
297 |
+
model.layers.2.self_attn.v_proj.weight
|
298 |
+
model.layers.2.self_attn.o_proj.weight
|
299 |
+
model.layers.2.mlp.gate_proj.weight
|
300 |
+
model.layers.2.mlp.up_proj.weight
|
301 |
+
model.layers.2.mlp.down_proj.weight
|
302 |
+
model.layers.2.input_layernorm.weight
|
303 |
+
model.layers.2.post_attention_layernorm.weight
|
304 |
+
model.layers.3.self_attn.q_proj.weight
|
305 |
+
model.layers.3.self_attn.k_proj.weight
|
306 |
+
model.layers.3.self_attn.v_proj.weight
|
307 |
+
model.layers.3.self_attn.o_proj.weight
|
308 |
+
model.layers.3.mlp.gate_proj.weight
|
309 |
+
model.layers.3.mlp.up_proj.weight
|
310 |
+
model.layers.3.mlp.down_proj.weight
|
311 |
+
model.layers.3.input_layernorm.weight
|
312 |
+
model.layers.3.post_attention_layernorm.weight
|
313 |
+
model.layers.4.self_attn.q_proj.weight
|
314 |
+
model.layers.4.self_attn.k_proj.weight
|
315 |
+
model.layers.4.self_attn.v_proj.weight
|
316 |
+
model.layers.4.self_attn.o_proj.weight
|
317 |
+
model.layers.4.mlp.gate_proj.weight
|
318 |
+
model.layers.4.mlp.up_proj.weight
|
319 |
+
model.layers.4.mlp.down_proj.weight
|
320 |
+
model.layers.4.input_layernorm.weight
|
321 |
+
model.layers.4.post_attention_layernorm.weight
|
322 |
+
model.layers.5.self_attn.q_proj.weight
|
323 |
+
model.layers.5.self_attn.k_proj.weight
|
324 |
+
model.layers.5.self_attn.v_proj.weight
|
325 |
+
model.layers.5.self_attn.o_proj.weight
|
326 |
+
model.layers.5.mlp.gate_proj.weight
|
327 |
+
model.layers.5.mlp.up_proj.weight
|
328 |
+
model.layers.5.mlp.down_proj.weight
|
329 |
+
model.layers.5.input_layernorm.weight
|
330 |
+
model.layers.5.post_attention_layernorm.weight
|
331 |
+
model.layers.6.self_attn.q_proj.weight
|
332 |
+
model.layers.6.self_attn.k_proj.weight
|
333 |
+
model.layers.6.self_attn.v_proj.weight
|
334 |
+
model.layers.6.self_attn.o_proj.weight
|
335 |
+
model.layers.6.mlp.gate_proj.weight
|
336 |
+
model.layers.6.mlp.up_proj.weight
|
337 |
+
model.layers.6.mlp.down_proj.weight
|
338 |
+
model.layers.6.input_layernorm.weight
|
339 |
+
model.layers.6.post_attention_layernorm.weight
|
340 |
+
model.layers.7.self_attn.q_proj.weight
|
341 |
+
model.layers.7.self_attn.k_proj.weight
|
342 |
+
model.layers.7.self_attn.v_proj.weight
|
343 |
+
model.layers.7.self_attn.o_proj.weight
|
344 |
+
model.layers.7.mlp.gate_proj.weight
|
345 |
+
model.layers.7.mlp.up_proj.weight
|
346 |
+
model.layers.7.mlp.down_proj.weight
|
347 |
+
model.layers.7.input_layernorm.weight
|
348 |
+
model.layers.7.post_attention_layernorm.weight
|
349 |
+
model.layers.8.self_attn.q_proj.weight
|
350 |
+
model.layers.8.self_attn.k_proj.weight
|
351 |
+
model.layers.8.self_attn.v_proj.weight
|
352 |
+
model.layers.8.self_attn.o_proj.weight
|
353 |
+
model.layers.8.mlp.gate_proj.weight
|
354 |
+
model.layers.8.mlp.up_proj.weight
|
355 |
+
model.layers.8.mlp.down_proj.weight
|
356 |
+
model.layers.8.input_layernorm.weight
|
357 |
+
model.layers.8.post_attention_layernorm.weight
|
358 |
+
model.layers.9.self_attn.q_proj.weight
|
359 |
+
model.layers.9.self_attn.k_proj.weight
|
360 |
+
model.layers.9.self_attn.v_proj.weight
|
361 |
+
model.layers.9.self_attn.o_proj.weight
|
362 |
+
model.layers.9.mlp.gate_proj.weight
|
363 |
+
model.layers.9.mlp.up_proj.weight
|
364 |
+
model.layers.9.mlp.down_proj.weight
|
365 |
+
model.layers.9.input_layernorm.weight
|
366 |
+
model.layers.9.post_attention_layernorm.weight
|
367 |
+
model.layers.10.self_attn.q_proj.weight
|
368 |
+
model.layers.10.self_attn.k_proj.weight
|
369 |
+
model.layers.10.self_attn.v_proj.weight
|
370 |
+
model.layers.10.self_attn.o_proj.weight
|
371 |
+
model.layers.10.mlp.gate_proj.weight
|
372 |
+
model.layers.10.mlp.up_proj.weight
|
373 |
+
model.layers.10.mlp.down_proj.weight
|
374 |
+
model.layers.10.input_layernorm.weight
|
375 |
+
model.layers.10.post_attention_layernorm.weight
|
376 |
+
model.layers.11.self_attn.q_proj.weight
|
377 |
+
model.layers.11.self_attn.k_proj.weight
|
378 |
+
model.layers.11.self_attn.v_proj.weight
|
379 |
+
model.layers.11.self_attn.o_proj.weight
|
380 |
+
model.layers.11.mlp.gate_proj.weight
|
381 |
+
model.layers.11.mlp.up_proj.weight
|
382 |
+
model.layers.11.mlp.down_proj.weight
|
383 |
+
model.layers.11.input_layernorm.weight
|
384 |
+
model.layers.11.post_attention_layernorm.weight
|
385 |
+
model.layers.12.self_attn.q_proj.weight
|
386 |
+
model.layers.12.self_attn.k_proj.weight
|
387 |
+
model.layers.12.self_attn.v_proj.weight
|
388 |
+
model.layers.12.self_attn.o_proj.weight
|
389 |
+
model.layers.12.mlp.gate_proj.weight
|
390 |
+
model.layers.12.mlp.up_proj.weight
|
391 |
+
model.layers.12.mlp.down_proj.weight
|
392 |
+
model.layers.12.input_layernorm.weight
|
393 |
+
model.layers.12.post_attention_layernorm.weight
|
394 |
+
model.layers.13.self_attn.q_proj.weight
|
395 |
+
model.layers.13.self_attn.k_proj.weight
|
396 |
+
model.layers.13.self_attn.v_proj.weight
|
397 |
+
model.layers.13.self_attn.o_proj.weight
|
398 |
+
model.layers.13.mlp.gate_proj.weight
|
399 |
+
model.layers.13.mlp.up_proj.weight
|
400 |
+
model.layers.13.mlp.down_proj.weight
|
401 |
+
model.layers.13.input_layernorm.weight
|
402 |
+
model.layers.13.post_attention_layernorm.weight
|
403 |
+
model.layers.14.self_attn.q_proj.weight
|
404 |
+
model.layers.14.self_attn.k_proj.weight
|
405 |
+
model.layers.14.self_attn.v_proj.weight
|
406 |
+
model.layers.14.self_attn.o_proj.weight
|
407 |
+
model.layers.14.mlp.gate_proj.weight
|
408 |
+
model.layers.14.mlp.up_proj.weight
|
409 |
+
model.layers.14.mlp.down_proj.weight
|
410 |
+
model.layers.14.input_layernorm.weight
|
411 |
+
model.layers.14.post_attention_layernorm.weight
|
412 |
+
model.layers.15.self_attn.q_proj.weight
|
413 |
+
model.layers.15.self_attn.k_proj.weight
|
414 |
+
model.layers.15.self_attn.v_proj.weight
|
415 |
+
model.layers.15.self_attn.o_proj.weight
|
416 |
+
model.layers.15.mlp.gate_proj.weight
|
417 |
+
model.layers.15.mlp.up_proj.weight
|
418 |
+
model.layers.15.mlp.down_proj.weight
|
419 |
+
model.layers.15.input_layernorm.weight
|
420 |
+
model.layers.15.post_attention_layernorm.weight
|
421 |
+
model.norm.weight
|
422 |
+
lm_head.weight
|
423 |
```
|